Engineering › Civil and Structural Engineering

Infrastructure Maintenance and Monitoring

Works Count: 67499

Wikipedia

Description

This cluster of papers focuses on the automated inspection and maintenance of pavement and civil infrastructure using deep learning, image processing, and convolutional neural networks. The research covers topics such as crack detection, defect classification, road surface monitoring, bridge inspection, and infrastructure condition assessment.

Keywords

Deep Learning; Pavement; Crack Detection; Image Processing; Infrastructure Inspection; Convolutional Neural Networks; Defect Detection; Road Maintenance; Bridge Inspection; Civil Infrastructure

Pavement Management for Airports, Roads, and Parking Lots

1994-01-01

M Y Shahin

Computer vision techniques for construction safety and health monitoring

2015-02-21

JoonOh Seo , SangUk Han , Sang Hyun Lee +1 more

Automatic Road Crack Detection and Characterization

2012-08-07

Henrique Oliveira , Paulo Lobato Correia

A fully integrated system for the automatic detection and characterization of cracks in road flexible pavement surfaces, which does not require manually labeled samples, is proposed to minimize the human … A fully integrated system for the automatic detection and characterization of cracks in road flexible pavement surfaces, which does not require manually labeled samples, is proposed to minimize the human subjectivity resulting from traditional visual surveys. The first task addressed, i.e., crack detection, is based on a learning from samples paradigm, where a subset of the available image database is automatically selected and used for unsupervised training of the system. The system classifies nonoverlapping image blocks as either containing crack pixels or not. The second task deals with crack type characterization, for which another classification system is constructed, to characterize the detected cracks' connect components. Cracks are labeled according to the types defined in the Portuguese Distress Catalog, with each different crack present in a given image receiving the appropriate label. Moreover, a novel methodology for the assignment of crack severity levels is introduced, computing an estimate for the width of each detected crack. Experimental crack detection and characterization results are presented based on images captured during a visual road pavement surface survey over Portuguese roads, with promising results. This is shown by the quantitative evaluation methodology introduced for the evaluation of this type of system, including a comparison with human experts' manual labeling results.

Prediction of concrete strength using artificial neural networks

2003-04-30

Seung-Chang Lee

Analysis of Edge-Detection Techniques for Crack Identification in Bridges

2003-09-19

Ikhlas Abdel‐Qader , Osama Abudayyeh , Michael Kelly

Bridge monitoring and maintenance is an expensive yet essential task in maintaining a safe national transportation infrastructure. Traditional monitoring methods use visual inspection of bridges on a regular basis and … Bridge monitoring and maintenance is an expensive yet essential task in maintaining a safe national transportation infrastructure. Traditional monitoring methods use visual inspection of bridges on a regular basis and often require inspectors to travel to the bridge of concern and determine the deterioration level of the bridge. Automation of this process may result in great monetary savings and can lead to more frequent inspection cycles. One aspect of this automation is the detection of cracks and deterioration of a bridge. This paper provides a comparison of the effectiveness of four crack-detection techniques: fast Haar transform (FHT), fast Fourier transform, Sobel, and Canny. These imaging edge-detection algorithms were implemented in MatLab and simulated using a sample of 50 concrete bridge images (25 with cracks and 25 without). The results show that the FHT was significantly more reliable than the other three edge-detection techniques in identifying cracks.

The description of road surface roughness

1973-01-01

Colin J. Dodds , J.D. Robson

Pothole detection in asphalt pavement images

2011-02-02

Christian Koch , Ioannis Brilakis

Solving two-stage robust optimization problems using a column-and-constraint generation method

2013-06-03

Bo Zeng , Long Zhao

Maintenance and management of civil infrastructure based on condition, safety, optimization, and life-cycle cost∗

2006-03-22

Dan M. Frangopol , Min Liu

Cost-competent maintenance and management of civil infrastructure requires balanced consideration of both the structure performance and the total cost accrued over the entire life-cycle. Most existing maintenance and management systems … Cost-competent maintenance and management of civil infrastructure requires balanced consideration of both the structure performance and the total cost accrued over the entire life-cycle. Most existing maintenance and management systems are developed on the basis of life-cycle cost minimization only. The single maintenance and management solution thus obtained, however, does not necessarily result in satisfactory long-term structure performance. Another concern is that the structure performance is usually described by the visual inspection-based structure condition states. The actual structure safety level, however, has not been explicitly or adequately considered in determining maintenance management decisions. This paper reviews the recent development of life-cycle maintenance and management planning for deteriorating civil infrastructure with emphasis on bridges using optimization techniques and considering simultaneously multiple and often competing criteria in terms of condition, safety and life-cycle cost. This multiple-objective approach leads to a large pool of alternative maintenance and management solutions that helps active decision-making by choosing a compromise solution of preferably balancing structure performance and life-cycle cost.

Multi-column deep neural network for traffic sign classification

2012-02-14

Dan Cireşan , Ueli Meier , Jonathan Masci +1 more

View PDF Chat

Neural Networks in Civil Engineering: 1989–2000

2001-03-01

Hojjat Adeli

The first journal article on neural network application in civil/structural engineering was published by in this journal in 1989. This article reviews neural network articles published in archival research journals … The first journal article on neural network application in civil/structural engineering was published by in this journal in 1989. This article reviews neural network articles published in archival research journals since then. The emphasis of the review is on the two fields of structural engineering and construction engineering and management. Neural networks articles published in other civil engineering areas are also reviewed, including environmental and water resources engineering, traffic engineering, highway engineering, and geotechnical engineering. The great majority of civil engineering applications of neural networks are based on the simple backpropagation algorithm. Applications of other recent, more powerful and efficient neural networks models are also reviewed. Recent works on integration of neural networks with other computing paradigms such as genetic algorithm, fuzzy logic, and wavelet to enhance the performance of neural network models are presented.

Vision‐Based Automated Crack Detection for Bridge Inspection

2015-05-15

Chul Min Yeum , Shirley J. Dyke

Abstract Visual inspection of bridges is customarily used to identify and evaluate faults. However, current procedures followed by human inspectors demand long inspection times to examine large and difficult to … Abstract Visual inspection of bridges is customarily used to identify and evaluate faults. However, current procedures followed by human inspectors demand long inspection times to examine large and difficult to access bridges. Also, highly relying on an inspector's subjective or empirical knowledge induces false evaluation. To address these limitations, a vision‐based visual inspection technique is proposed by automatically processing and analyzing a large volume of collected images. Images used in this technique are captured without controlling angles and positions of cameras and no need for preliminary calibration. As a pilot study, cracks near bolts on a steel structure are identified from images. Using images from many different angles and prior knowledge of the typical appearance and characteristics of this class of faults, the proposed technique can successfully detect cracks near bolts.

A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure

2015-02-21

Christian Koch , Hristina Georgieva , Varun Kasireddy +2 more

View PDF Chat

CrackTree: Automatic crack detection from pavement images

2011-11-14

Qin Zou , Yu Cao , Qingquan Li +2 more

Automated Crack Detection on Concrete Bridges

2014-10-07

Prateek Prasanna , Kristin Dana , Nenad Gucunski +4 more

Detection of cracks on bridge decks is a vital task for maintaining the structural health and reliability of concrete bridges. Robotic imaging can be used to obtain bridge surface image … Detection of cracks on bridge decks is a vital task for maintaining the structural health and reliability of concrete bridges. Robotic imaging can be used to obtain bridge surface image sets for automated on-site analysis. We present a novel automated crack detection algorithm, the STRUM (spatially tuned robust multifeature) classifier, and demonstrate results on real bridge data using a state-of-the-art robotic bridge scanning system. By using machine learning classification, we eliminate the need for manually tuning threshold parameters. The algorithm uses robust curve fitting to spatially localize potential crack regions even in the presence of noise. Multiple visual features that are spatially tuned to these regions are computed. Feature computation includes examining the scale-space of the local feature in order to represent the information and the unknown salient scale of the crack. The classification results are obtained with real bridge data from hundreds of crack regions over two bridges. This comprehensive analysis shows a peak STRUM classifier performance of 95% compared with 69% accuracy from a more typical image-based approach. In order to create a composite global view of a large bridge span, an image sequence from the robot is aligned computationally to create a continuous mosaic. A crack density map for the bridge mosaic provides a computational description as well as a global view of the spatial patterns of bridge deck cracking. The bridges surveyed for data collection and testing include Long-Term Bridge Performance program's (LTBP) pilot project bridges at Haymarket, VA, USA, and Sacramento, CA, USA.

Automatic Road Crack Detection Using Random Structured Forests

2016-05-18

Yong Shi , Limeng Cui , Zhiquan Qi +2 more

Cracks are a growing threat to road conditions and have drawn much attention to the construction of intelligent transportation systems. However, as the key part of an intelligent transportation system, … Cracks are a growing threat to road conditions and have drawn much attention to the construction of intelligent transportation systems. However, as the key part of an intelligent transportation system, automatic road crack detection has been challenged because of the intense inhomogeneity along the cracks, the topology complexity of cracks, the inference of noises with similar texture to the cracks, and so on. In this paper, we propose CrackForest, a novel road crack detection framework based on random structured forests, to address these issues. Our contributions are shown as follows: 1) apply the integral channel features to redefine the tokens that constitute a crack and get better representation of the cracks with intensity inhomogeneity; 2) introduce random structured forests to generate a high-performance crack detector, which can identify arbitrarily complex cracks; and 3) propose a new crack descriptor to characterize cracks and discern them from noises effectively. In addition, our method is faster and easier to parallel. Experimental results prove the state-of-the-art detection precision of CrackForest compared with competing methods.

Road crack detection using deep convolutional neural network

2016-08-17

Lei Zhang , Fan Yang , Yimin D. Zhang +1 more

Automatic detection of pavement cracks is an important task in transportation maintenance for driving safety assurance. However, it remains a challenging task due to the intensity inhomogeneity of cracks and … Automatic detection of pavement cracks is an important task in transportation maintenance for driving safety assurance. However, it remains a challenging task due to the intensity inhomogeneity of cracks and complexity of the background, e.g., the low contrast with surrounding pavement and possible shadows with similar intensity. Inspired by recent success on applying deep learning to computer vision and medical problems, a deep-learning based method for crack detection is proposed in this paper. A supervised deep convolutional neural network is trained to classify each image patch in the collected images. Quantitative evaluation conducted on a data set of 500 images of size 3264 χ 2448, collected by a low-cost smart phone, demonstrates that the learned deep features with the proposed deep learning framework provide superior crack detection performance when compared with features extracted with existing hand-craft methods.

Automatic Crack Detection on Two-Dimensional Pavement Images: An Algorithm Based on Minimal Path Selection

2016-09-20

Rabih Amhaz , Sylvie Chambon , Jérôme Idier +1 more

This paper proposes a new algorithm for automatic crack detection from 2D pavement images. It strongly relies on the localization of minimal paths within each image, a path being a … This paper proposes a new algorithm for automatic crack detection from 2D pavement images. It strongly relies on the localization of minimal paths within each image, a path being a series of neighboring pixels and its score being the sum of their intensities. The originality of the approach stems from the proposed way to select a set of minimal paths and the two postprocessing steps introduced to improve the quality of the detection. Such an approach is a natural way to take account of both the photometric and geometric characteristics of pavement images. An intensive validation is performed on both synthetic and real images (from five different acquisition systems), with comparisons to five existing methods. The proposed algorithm provides very robust and precise results in a wide range of situations, in a fully unsupervised manner, which is beyond the current state of the art.

View PDF Chat

Crack detection using image processing: A critical review and analysis

2017-02-16

Arun K Mohan , Sumathi Poobal

Cracks on the concrete surface are one of the earliest indications of degradation of the structure which is critical for the maintenance as well the continuous exposure will lead to … Cracks on the concrete surface are one of the earliest indications of degradation of the structure which is critical for the maintenance as well the continuous exposure will lead to the severe damage to the environment. Manual inspection is the acclaimed method for the crack inspection. In the manual inspection, the sketch of the crack is prepared manually, and the conditions of the irregularities are noted. Since the manual approach completely depends on the specialist’s knowledge and experience, it lacks objectivity in the quantitative analysis. So, automatic image-based crack detection is proposed as a replacement. Literature presents different techniques to automatically identify the crack and its depth using image processing techniques. In this research, a detailed survey is conducted to identify the research challenges and the achievements till in this field. Accordingly, 50 research papers are taken related to crack detection, and those research papers are reviewed. Based on the review, analysis is provided based on the image processing techniques, objectives, accuracy level, error level, and the image data sets. Finally, we present the various research issues which can be useful for the researchers to accomplish further research on the crack detection.

Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks

2017-03-23

Young‐Jin Cha , Wooram Choi , Oral Büyüköztürk

Abstract A number of image processing techniques (IPTs) have been implemented for detecting civil infrastructure defects to partially replace human‐conducted onsite inspections. These IPTs are primarily used to manipulate images … Abstract A number of image processing techniques (IPTs) have been implemented for detecting civil infrastructure defects to partially replace human‐conducted onsite inspections. These IPTs are primarily used to manipulate images to extract defect features, such as cracks in concrete and steel surfaces. However, the extensively varying real‐world situations (e.g., lighting and shadow changes) can lead to challenges to the wide adoption of IPTs. To overcome these challenges, this article proposes a vision‐based method using a deep architecture of convolutional neural networks (CNNs) for detecting concrete cracks without calculating the defect features. As CNNs are capable of learning image features automatically, the proposed method works without the conjugation of IPTs for extracting features. The designed CNN is trained on 40 K images of 256 × 256 pixel resolutions and, consequently, records with about 98% accuracy. The trained CNN is combined with a sliding window technique to scan any image size larger than 256 × 256 pixel resolutions. The robustness and adaptability of the proposed approach are tested on 55 images of 5,888 × 3,584 pixel resolutions taken from a different structure which is not used for training and validation processes under various conditions (e.g., strong light spot, shadows, and very thin cracks). Comparative studies are conducted to examine the performance of the proposed CNN using traditional Canny and Sobel edge detection methods. The results show that the proposed method shows quite better performances and can indeed find concrete cracks in realistic situations.

View PDF Chat

Automated Pixel‐Level Pavement Crack Detection on 3D Asphalt Surfaces Using a Deep‐Learning Network

2017-08-21

Allen Zhang , Kelvin C. P. Wang , Baoxian Li +7 more

Abstract The CrackNet, an efficient architecture based on the Convolutional Neural Network (CNN), is proposed in this article for automated pavement crack detection on 3D asphalt surfaces with explicit objective … Abstract The CrackNet, an efficient architecture based on the Convolutional Neural Network (CNN), is proposed in this article for automated pavement crack detection on 3D asphalt surfaces with explicit objective of pixel‐perfect accuracy. Unlike the commonly used CNN, CrackNet does not have any pooling layers which downsize the outputs of previous layers. CrackNet fundamentally ensures pixel‐perfect accuracy using the newly developed technique of invariant image width and height through all layers. CrackNet consists of five layers and includes more than one million parameters that are trained in the learning process. The input data of the CrackNet are feature maps generated by the feature extractor using the proposed line filters with various orientations, widths, and lengths. The output of CrackNet is the set of predicted class scores for all pixels. The hidden layers of CrackNet are convolutional layers and fully connected layers. CrackNet is trained with 1,800 3D pavement images and is then demonstrated to be successful in detecting cracks under various conditions using another set of 200 3D pavement images. The experiment using the 200 testing 3D images showed that CrackNet can achieve high Precision (90.13%), Recall (87.63%) and F‐measure (88.86%) simultaneously. Compared with recently developed crack detection methods based on traditional machine learning and imaging algorithms, the CrackNet significantly outperforms the traditional approaches in terms of F‐measure. Using parallel computing techniques, CrackNet is programmed to be efficiently used in conjunction with the data collection software.

Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection

2017-09-23

Kasthurirangan Gopalakrishnan , Siddhartha Kumar Khaitan , Alok Choudhary +1 more

View PDF Chat

NB-CNN: Deep Learning-Based Crack Detection Using Convolutional Neural Network and Naïve Bayes Data Fusion

2017-10-19

Fu‐Chen Chen , Mohammad R. Jahanshahi

Regular inspection of nuclear power plant components is important to guarantee safe operations. However, current practice is time consuming, tedious, and subjective, which involves human technicians reviewing the inspection videos … Regular inspection of nuclear power plant components is important to guarantee safe operations. However, current practice is time consuming, tedious, and subjective, which involves human technicians reviewing the inspection videos and identifying cracks on reactors. A few vision-based crack detection approaches have been developed for metallic surfaces, and they typically perform poorly when used for analyzing nuclear inspection videos. Detecting these cracks is a challenging task since they are tiny, and noisy patterns exist on the components' surfaces. This study proposes a deep learning framework, based on a convolutional neural network (CNN) and a Naïve Bayes data fusion scheme, called NB-CNN, to analyze individual video frames for crack detection while a novel data fusion scheme is proposed to aggregate the information extracted from each video frame to enhance the overall performance and robustness of the system. To this end, a CNN is proposed to detect crack patches in each video frame, while the proposed data fusion scheme maintains the spatiotemporal coherence of cracks in videos, and the Naïve Bayes decision making discards false positives effectively. The proposed framework achieves a 98.3% hit rate against 0.1 false positives per frame that is significantly higher than state-of-the-art approaches as presented in this paper.

Autonomous Structural Visual Inspection Using Region‐Based Deep Learning for Detecting Multiple Damage Types

2017-11-28

Young‐Jin Cha , Wooram Choi , Gahyun Suh +2 more

Abstract Computer vision‐based techniques were developed to overcome the limitations of visual inspection by trained human resources and to detect structural damage in images remotely, but most methods detect only … Abstract Computer vision‐based techniques were developed to overcome the limitations of visual inspection by trained human resources and to detect structural damage in images remotely, but most methods detect only specific types of damage, such as concrete or steel cracks. To provide quasi real‐time simultaneous detection of multiple types of damages, a Faster Region‐based Convolutional Neural Network (Faster R‐CNN)‐based structural visual inspection method is proposed. To realize this, a database including 2,366 images (with 500 × 375 pixels) labeled for five types of damages—concrete crack, steel corrosion with two levels (medium and high), bolt corrosion, and steel delamination—is developed. Then, the architecture of the Faster R‐CNN is modified, trained, validated, and tested using this database. Results show 90.6%, 83.4%, 82.1%, 98.1%, and 84.7% average precision (AP) ratings for the five damage types, respectively, with a mean AP of 87.8%. The robustness of the trained Faster R‐CNN is evaluated and demonstrated using 11 new 6,000 × 4,000‐pixel images taken of different structures. Its performance is also compared to that of the traditional CNN‐based method. Considering that the proposed method provides a remarkably fast test speed (0.03 seconds per image with 500 × 375 resolution), a framework for quasi real‐time damage detection on video using the trained networks is developed.

Automatic Defect Detection of Fasteners on the Catenary Support Device Using Deep Convolutional Neural Network

2017-12-04

Junwen Chen , Zhigang Liu , Hongrui Wang +2 more

The excitation and vibration triggered by the long-term operation of railway vehicles inevitably result in defective states of catenary support devices. With the massive construction of high-speed electrified railways, automatic … The excitation and vibration triggered by the long-term operation of railway vehicles inevitably result in defective states of catenary support devices. With the massive construction of high-speed electrified railways, automatic defect detection of diverse and plentiful fasteners on the catenary support device is of great significance for operation safety and cost reduction. Nowadays, the catenary support devices are periodically captured by the cameras mounted on the inspection vehicles during the night, but the inspection still mostly relies on human visual interpretation. To reduce the human involvement, this paper proposes a novel vision-based method that applies the deep convolutional neural networks (DCNNs) in the defect detection of the fasteners. Our system cascades three DCNN-based detection stages in a coarse-to-fine manner, including two detectors to sequentially localize the cantilever joints and their fasteners and a classifier to diagnose the fasteners' defects. Extensive experiments and comparisons of the defect detection of catenary support devices along the Wuhan-Guangzhou high-speed railway line indicate that the system can achieve a high detection rate with good adaptation and robustness in complex environments.

View PDF Chat

Computer vision and deep learning–based data anomaly detection method for structural health monitoring

2018-02-19

Yuequan Bao , Zhiyi Tang , Hui Li +1 more

The widespread application of sophisticated structural health monitoring systems in civil infrastructures produces a large volume of data. As a result, the analysis and mining of structural health monitoring data … The widespread application of sophisticated structural health monitoring systems in civil infrastructures produces a large volume of data. As a result, the analysis and mining of structural health monitoring data have become hot research topics in the field of civil engineering. However, the harsh environment of civil structures causes the data measured by structural health monitoring systems to be contaminated by multiple anomalies, which seriously affect the data analysis results. This is one of the main barriers to automatic real-time warning, because it is difficult to distinguish the anomalies caused by structural damage from those related to incorrect data. Existing methods for data cleansing mainly focus on noise filtering, whereas the detection of incorrect data requires expertise and is very time-consuming. Inspired by the real-world manual inspection process, this article proposes a computer vision and deep learning–based data anomaly detection method. In particular, the framework of the proposed method includes two steps: data conversion by data visualization, and the construction and training of deep neural networks for anomaly classification. This process imitates human biological vision and logical thinking. In the data visualization step, the time series signals are transformed into image vectors that are plotted piecewise in grayscale images. In the second step, a training dataset consisting of randomly selected and manually labeled image vectors is input into a deep neural network or a cluster of deep neural networks, which are trained via techniques termed stacked autoencoders and greedy layer-wise training. The trained deep neural networks can be used to detect potential anomalies in large amounts of unchecked structural health monitoring data. To illustrate the training procedure and validate the performance of the proposed method, acceleration data from the structural health monitoring system of a real long-span bridge in China are employed. The results show that the multi-pattern anomalies of the data can be automatically detected with high accuracy.

Deep learning based image recognition for crack and leakage defects of metro shield tunnel

2018-04-09

Hongwei Huang , Qing-tong Li , Dongming Zhang

Deep Transfer Learning for Image‐Based Structural Damage Recognition

2018-04-16

Yuqing Gao , Khalid M. Mosalam

Abstract This article implements the state‐of‐the‐art deep learning technologies for a civil engineering application, namely recognition of structural damage from images. Inspired by ImageNet Challenge and the development of computer … Abstract This article implements the state‐of‐the‐art deep learning technologies for a civil engineering application, namely recognition of structural damage from images. Inspired by ImageNet Challenge and the development of computer hardware, the concept of Structural ImageNet is proposed herein with four naïve baseline recognition tasks: component type identification, spalling condition check, damage level evaluation, and damage type determination. A relatively small number of images (2,000) are selected from the Structural ImageNet and manually labeled according to the four recognition tasks. In order to avoid overfitting, Transfer Learning (TL) based on VGGNet (Visual Geometry Group) is introduced and applied using two different strategies, namely feature extractor and fine‐tuning. Two experiments are designed based on properties of these two strategies to find the relative optimal model parameters and scope of application. Models obtained by both strategies indicate the promising recognition results and different application potentials where feature extractor and fine‐tuning can be respectively used for preliminary analysis and for further improvement. These results also reveal the potential uses of deep TL in image‐based structural damage recognition.

Emerging artificial intelligence methods in structural engineering

2018-05-30

Hadi Salehi , Rigoberto Burgueño

View PDF Chat

Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete

2018-08-11

Sattar Dorafshan , Robert J. Thomas , Marc Maguire

View PDF Chat

Automatic Pixel‐Level Crack Detection and Measurement Using Fully Convolutional Network

2018-08-29

Xincong Yang , Heng Li , Yantao Yu +3 more

Abstract The spatial characteristics of cracks are significant indicators to assess and evaluate the health of existing buildings and infrastructures. However, the current manual crack description method is time consuming … Abstract The spatial characteristics of cracks are significant indicators to assess and evaluate the health of existing buildings and infrastructures. However, the current manual crack description method is time consuming and labor consuming. To improve the efficiency of crack inspection, advanced computer vision‐based techniques have been utilized to detect cracks automatically at image level and grid‐cell level. But existing crack detections are of (high specificity) low generality and inefficient, in terms that conventional approaches are unable to identify and measure diverse cracks concurrently at pixel level. Therefore, this research implements a novel deep learning technique named fully convolutional network (FCN) to address this problem. First, FCN is trained by feeding multiple types of cracks to semantically identify and segment pixel‐wise cracks at different scales. Then, the predicted crack segmentations are represented by single‐pixel width skeletons to quantitatively measure the morphological features of cracks, providing valuable crack indicators for assessment in practice, such as crack topology, crack length, max width, and mean width. To validate the prediction, the predicted segmentations are compared with recent advanced method for crack recognition and ground truth. For crack segmentation, the accuracy, precision, recall, and F1 score are 97.96%, 81.73%, 78.97%, and 79.95%, respectively. For crack length, the relative measurement error varies from −48.03% to 177.79%, meanwhile that ranges from −13.27% to 24.01% for crack width. The results show that FCN is feasible and sufficient for crack identification and measurement. Although the accuracy is not as high as CrackNet because of three types of errors, the prediction has been increased to pixel level and the training time has been dramatically decreased to several per cents of previous methods due to the novel end‐to‐end structure of FCN, which combines typical convolutional neural networks and deconvolutional layers.

DeepCrack: Learning Hierarchical Convolutional Features for Crack Detection

2018-10-31

Qin Zou , Zheng Zhang , Qingquan Li +3 more

Cracks are typical line structures that are of interest in many computer-vision applications. In practice, many cracks, e.g., pavement cracks, show poor continuity and low contrast, which brings great challenges … Cracks are typical line structures that are of interest in many computer-vision applications. In practice, many cracks, e.g., pavement cracks, show poor continuity and low contrast, which brings great challenges to image-based crack detection by using low-level features. In this paper, we propose DeepCrack - an end-to-end trainable deep convolutional neural network for automatic crack detection by learning high-level features for crack representation. In this method, multi-scale deep convolutional features learned at hierarchical convolutional stages are fused together to capture the line structures. More detailed representations are made in larger-scale feature maps and more holistic representations are made in smaller-scale feature maps. We build DeepCrack net on the encoder-decoder architecture of SegNet, and pairwisely fuse the convolutional features generated in the encoder network and in the decoder network at the same scale. We train DeepCrack net on one crack dataset and evaluate it on three others. The experimental results demonstrate that DeepCrack achieves F-Measure over 0.87 on the three challenging datasets in average and outperforms the current state-of-the-art methods.

Autonomous concrete crack detection using deep fully convolutional neural network

2018-12-13

Cao Vu Dung , Anh Duc Le

Automatic pixel‐level multiple damage detection of concrete structure using fully convolutional network

2019-01-19

Shengyuan Li , Xuefeng Zhao , Guangyi Zhou

Abstract Deep learning‐based structural damage detection methods overcome the limitation of inferior adaptability caused by extensively varying real‐world situations (e.g., lighting and shadow changes). However, most deep learning‐based methods detect … Abstract Deep learning‐based structural damage detection methods overcome the limitation of inferior adaptability caused by extensively varying real‐world situations (e.g., lighting and shadow changes). However, most deep learning‐based methods detect structural damage at the image level and grid‐cell level. To provide pixel‐level detection of multiple damages, a Fully Convolutional Network (FCN)‐based multiple damages detection method for concrete structure is proposed. To realize this method, a database of 2,750 images (with 504 × 376 pixels) including crack, spalling, efflorescence, and hole images in concrete structure is built, and the four damages included in those images are labeled manually. Then, the architecture of the FCN is modified, trained, validated, and tested using this database. A strategy of model‐based transfer learning is used to initialize the parameters of the FCN during the training process. The results show 98.61% pixel accuracy (PA), 91.59% mean pixel accuracy (MPA), 84.53% mean intersection over union (MIoU), and 97.34% frequency weighted intersection over union (FWIoU). Subsequently, the robustness and adaptability of the trained FCN model is tested and the damage is extracted, where damage areas are provided according to a calibrated relation between the ratio (the pixel area and true area of the detected object) and the distance from the smartphone to the concrete surface using a laser range finder. A comparative study is conducted to examine the performance of the proposed FCN‐based approach using a SegNet‐based method. The results show that the proposed method substantiates quite better performance and can indeed detect multiple concrete damages at the pixel level in realistic situations.

DeepCrack: A deep hierarchical feature learning architecture for crack segmentation

2019-01-23

Yahui Liu , Jian Yao , Xiaohu Lu +2 more

Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring

2019-03-07

Billie F. Spencer , Vedhus Hoskere , Yasutaka Narazaki

Computer vision techniques, in conjunction with acquisition through remote cameras and unmanned aerial vehicles (UAVs), offer promising non-contact solutions to civil infrastructure condition assessment. The ultimate goal of such a … Computer vision techniques, in conjunction with acquisition through remote cameras and unmanned aerial vehicles (UAVs), offer promising non-contact solutions to civil infrastructure condition assessment. The ultimate goal of such a system is to automatically and robustly convert the image or video data into actionable information. This paper provides an overview of recent advances in computer vision techniques as they apply to the problem of civil infrastructure condition assessment. In particular, relevant research in the fields of computer vision, machine learning, and structural engineering is presented. The work reviewed is classified into two types: inspection applications and monitoring applications. The inspection applications reviewed include identifying context such as structural components, characterizing local and global visible damage, and detecting changes from a reference image. The monitoring applications discussed include static measurement of strain and displacement, as well as dynamic measurement of displacement for modal analysis. Subsequently, some of the key challenges that persist toward the goal of automated vision-based civil infrastructure and monitoring are presented. The paper concludes with ongoing work aimed at addressing some of these stated challenges.

Computer vision-based concrete crack detection using U-net fully convolutional networks

2019-04-24

Zhenqing Liu , Yiwen Cao , Yize Wang +1 more

Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection

2019-04-25

Fan Yang , Lei Zhang , Sijia Yu +3 more

Pavement crack detection is a critical task for insuring road safety. Manual crack detection is extremely time-consuming. Therefore, an automatic road crack detection method is required to boost this progress. … Pavement crack detection is a critical task for insuring road safety. Manual crack detection is extremely time-consuming. Therefore, an automatic road crack detection method is required to boost this progress. However, it remains a challenging task due to the intensity inhomogeneity of cracks and complexity of the background, e.g., the low contrast with surrounding pavements and possible shadows with a similar intensity. Inspired by recent advances of deep learning in computer vision, we propose a novel network architecture, named feature pyramid and hierarchical boosting network (FPHBN), for pavement crack detection. The proposed network integrates context information to low-level features for crack detection in a feature pyramid way, and it balances the contributions of both easy and hard samples to loss by nested sample reweighting in a hierarchical way during training. In addition, we propose a novel measurement for crack detection named average intersection over union (AIU). To demonstrate the superiority and generalizability of the proposed method, we evaluate it on five crack datasets and compare it with the state-of-the-art crack detection, edge detection, and semantic segmentation methods. The extensive experiments show that the proposed method outperforms these methods in terms of accuracy and generalizability. Code and data can be found in https://github.com/fyangneil/pavement-crack-detection.

View PDF Chat

Image-based concrete crack detection in tunnels using deep fully convolutional networks

2019-11-08

Yupeng Ren , Jisheng Huang , Zhiyou Hong +4 more

Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review

2020-05-13

Mohsen Azimi , Armin Dadras Eslamlou , Gökhan Pekcan

Data-driven methods in structural health monitoring (SHM) is gaining popularity due to recent technological advancements in sensors, as well as high-speed internet and cloud-based computation. Since the introduction of deep … Data-driven methods in structural health monitoring (SHM) is gaining popularity due to recent technological advancements in sensors, as well as high-speed internet and cloud-based computation. Since the introduction of deep learning (DL) in civil engineering, particularly in SHM, this emerging and promising tool has attracted significant attention among researchers. The main goal of this paper is to review the latest publications in SHM using emerging DL-based methods and provide readers with an overall understanding of various SHM applications. After a brief introduction, an overview of various DL methods (e.g., deep neural networks, transfer learning, etc.) is presented. The procedure and application of vibration-based, vision-based monitoring, along with some of the recent technologies used for SHM, such as sensors, unmanned aerial vehicles (UAVs), etc. are discussed. The review concludes with prospects and potential limitations of DL-based methods in SHM applications.

View PDF Chat

Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach

2020-06-12

Sujith Mangalathu , Seong‐Hoon Hwang , Jong‐Su Jeon

Machine learning prediction of mechanical properties of concrete: Critical review

2020-06-23

Wassim Ben Chaabene , Majdi Flah , Moncef L. Nehdi

Deep learning in the construction industry: A review of present status and future innovations

2020-09-19

Taofeek Akinosho , Lukumon O. Oyedele , Muhammad Bilal +4 more

The construction industry is known to be overwhelmed with resource planning, risk management and logistic challenges which often result in design defects, project delivery delays, cost overruns and contractual disputes. … The construction industry is known to be overwhelmed with resource planning, risk management and logistic challenges which often result in design defects, project delivery delays, cost overruns and contractual disputes. These challenges have instigated research in the application of advanced machine learning algorithms such as deep learning to help with diagnostic and prescriptive analysis of causes and preventive measures. However, the publicity created by tech firms like Google, Facebook and Amazon about Artificial Intelligence and applications to unstructured data is not the end of the field. There abound many applications of deep learning, particularly within the construction sector in areas such as site planning and management, health and safety and construction cost prediction, which are yet to be explored. The overall aim of this article was to review existing studies that have applied deep learning to prevalent construction challenges like structural health monitoring, construction site safety, building occupancy modelling and energy demand prediction. To the best of our knowledge, there is currently no extensive survey of the applications of deep learning techniques within the construction industry. This review would inspire future research into how best to apply image processing, computer vision, natural language processing techniques of deep learning to numerous challenges in the industry. Limitations of deep learning such as the black box challenge, ethics and GDPR, cybersecurity and cost, that can be expected by construction researchers and practitioners when adopting some of these techniques were also discussed.

View PDF Chat

Machine learning applications for building structural design and performance assessment: State-of-the-art review

2020-09-21

Han Sun , Henry Burton , Honglan Huang

View PDF Chat

Road Damage Detection and Classification Using Deep Neural Networks with Smartphone Images

2018-06-30

Hiroya Maeda , Yoshihide Sekimoto , Toshikazu Seto +2 more

Research on damage detection of road surfaces using image processing techniques has been actively conducted, achieving considerably high detection accuracies. Many studies only focus on the detection of the presence … Research on damage detection of road surfaces using image processing techniques has been actively conducted, achieving considerably high detection accuracies. Many studies only focus on the detection of the presence or absence of damage. However, in a real-world scenario, when the road managers from a governing body need to repair such damage, they need to clearly understand the type of damage in order to take effective action. In addition, in many of these previous studies, the researchers acquire their own data using different methods. Hence, there is no uniform road damage dataset available openly, leading to the absence of a benchmark for road damage detection. This study makes three contributions to address these issues. First, to the best of our knowledge, for the first time, a large-scale road damage dataset is prepared. This dataset is composed of 9,053 road damage images captured with a smartphone installed on a car, with 15,435 instances of road surface damage included in these road images. In order to generate this dataset, we cooperated with 7 municipalities in Japan and acquired road images for more than 40 hours. These images were captured in a wide variety of weather and illuminance conditions. In each image, we annotated the bounding box representing the location and type of damage. Next, we used a state-of-the-art object detection method using convolutional neural networks to train the damage detection model with our dataset, and compared the accuracy and runtime speed on both, using a GPU server and a smartphone. Finally, we demonstrate that the type of damage can be classified into eight types with high accuracy by applying the proposed object detection method. The road damage dataset, our experimental results, and the developed smartphone application used in this study are publicly available (https://github.com/sekilab/RoadDamageDetector/).

View PDF Chat

Application of deep learning algorithms in geotechnical engineering: a short critical review

2021-02-16

Wengang Zhang , Hongrui Li , Yongqin Li +3 more

View PDF Chat

Machine learning for structural engineering: A state-of-the-art review

2022-02-15

Huu‐Tai Thai

QUANTIFYING TEST-RETEST RELIABILITY USING THE INTRACLASS CORRELATION COEFFICIENT AND THE SEM

2005-02-01

Joseph P. Weir

Reliability, the consistency of a test or measurement, is frequently quantified in the movement sciences literature. A common metric is the intraclass correlation coefficient (ICC). In addition, the SEM, which … Reliability, the consistency of a test or measurement, is frequently quantified in the movement sciences literature. A common metric is the intraclass correlation coefficient (ICC). In addition, the SEM, which can be calculated from the ICC, is also frequently reported in reliability studies. However, there are several versions of the ICC, and confusion exists in the movement sciences regarding which ICC to use. Further, the utility of the SEM is not fully appreciated. In this review, the basics of classic reliability theory are addressed in the context of choosing and interpreting an ICC. The primary distinction between ICC equations is argued to be one concerning the inclusion (equations 2,1 and 2,k) or exclusion (equations 3,1 and 3,k) of systematic error in the denominator of the ICC equation. Inferential tests of mean differences, which are performed in the process of deriving the necessary variance components for the calculation of ICC values, are useful to determine if systematic error is present. If so, the measurement schedule should be modified (removing trials where learning and/or fatigue effects are present) to remove systematic error, and ICC equations that only consider random error may be safely used. The use of ICC values is discussed in the context of estimating the effects of measurement error on sample size, statistical power, and correlation attenuation. Finally, calculation and application of the SEM are discussed. It is shown how the SEM and its variants can be used to construct confidence intervals for individual scores and to determine the minimal difference needed to be exhibited for one to be confident that a true change in performance of an individual has occurred.

Artificial intelligence and smart vision for building and construction 4.0: Machine and deep learning methods and applications

2022-06-24

Shanaka Kristombu Baduge , P.S.M. Thilakarathna , Jude Shalitha Perera +5 more

This article presents a state-of-the-art review of the applications of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) in building and construction industry 4.0 in the facets of … This article presents a state-of-the-art review of the applications of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) in building and construction industry 4.0 in the facets of architectural design and visualization; material design and optimization; structural design and analysis; offsite manufacturing and automation; construction management, progress monitoring, and safety; smart operation, building management and health monitoring; and durability, life cycle analysis, and circular economy. This paper presents a unique perspective on applications of AI/DL/ML in these domains for the complete building lifecycle, from conceptual stage, design stage, construction stage, operational and maintenance stage until the end of life. Furthermore, data collection strategies using smart vision and sensors, data cleaning methods (post-processing), data storage for developing these models are discussed, and the challenges in model development and strategies to overcome these challenges are elaborated. Future trends in these domains and possible research avenues are also presented.

View PDF Chat

A Novel YOLO Algorithm Integrating Attention Mechanisms and Fuzzy Information for Pavement Crack Detection

2025-06-25

Qingqing Li , Tianshu Wu , Tingfa Xu +2 more | International Journal of Computational Intelligence Systems

Method for quality inspection during the execution of facades based on UAS images and Machine Learning algorithms

2025-06-24

Alisson Souza Silva , Roseneia Rodrigues Santos de Melo , Reymard Sávio Sampaio de Melo +1 more | International Journal of Construction Management

Leveraging data-driven artificial intelligence in optimization design for building structures: A review

2025-06-24

Sizhong Qin , Yifan Fei , Wenjie Liao +1 more | Engineering Structures

Field-data-driven assessment of an in-service skewed integral abutment bridge assisted by deep learning

2025-06-24

Ricardo Dorado , James M. LaFave , Larry A. Fahnestock | Bridge Structures

Integral abutment bridges (IABs) exhibit complex and evolving structural behavior due to their interaction with the foundation and surrounding soil. Long-term effects, such as backfill soil ratcheting and cumulative in-plan … Integral abutment bridges (IABs) exhibit complex and evolving structural behavior due to their interaction with the foundation and surrounding soil. Long-term effects, such as backfill soil ratcheting and cumulative in-plan superstructure rotation, can lead to unexpected structural responses that are not fully understood. This study analyzes more than 3 years of superstructure displacement, abutment rotation (tilt), and temperature data, collected at 0.5 Hz, from an in-service two-span skewed (45°) steel I-girder bridge with integral abutments and staggered-X-cross-frames. The study advances the understanding of IAB behavior, including behavioral anomalies, which could assist in the interpretation of stress deviations reported in previous studies. Findings show that the monitored IAB presents changing behavior, as well as an accumulation of transverse displacement and abutment tilt over time. Analysis indicates that boundary condition representation in finite element models should incorporate the flexibility provided by soil and pile deformation to accurately reflect field behavior. It is further observed that abutment tilt data displays different trends over short and long periods. Discrepancies between these trends underscore the complexity of IAB behavior under varying temperature conditions. Deep learning techniques, particularly long short-term memory models, assisted in identifying these behavioral patterns. This application demonstrates their potential for detecting subtle deviations in bridge response.

RLD-Net: an enhanced deep learning model for accurate pavement distress detection using UAV captured images

2025-06-24

H.D. Cheng , Junfei Zhang , HaoHui Yan +2 more | Multiscale and Multidisciplinary Modeling Experiments and Design

Explainable machine learning in the design of hollow-core slabs: integration between predictive modeling and structural practice

2025-06-24

Ademilton Matias Rocha Neto , Azaria Paz , Fabrício Castilho Pereira +2 more | Caderno Pedagógico

Hollow-core slabs are widely used in large-scale structures, such as shopping malls and parking garages, due to their ability to span large distances and their reduced weight compared to solid … Hollow-core slabs are widely used in large-scale structures, such as shopping malls and parking garages, due to their ability to span large distances and their reduced weight compared to solid slabs. However, their design must be carefully adapted to the specific characteristics of each project, such as the span magnitude, the loads to be supported, and the aesthetic requirements of the building. The thickness of the panels, the shape of the voids, and the necessary reinforcements are variables that directly influence the safety and economic efficiency of the application. The use of machine learning (ML) proves to be promising in this context, as it allows for the optimization of hollow-core slab design based on experimental data. Predictive modeling through techniques like Support Vector Regression (SVR) and explainability through SHAP provide more effective and transparent solutions, enabling engineers to understand the impact of each variable on the structural performance. By integrating synthetic data and machine learning algorithms, it is possible to optimize designs, considering the involved variables and minimizing uncertainties. The application of ML in hollow-core slab design not only increases the accuracy of calculations but also offers a more flexible and efficient approach to handling different design scenarios. By integrating explainable models, like SHAP, engineers can make more informed and secure decisions, adapting the slab design to the specific conditions of each project, optimizing costs, and increasing structural reliability. The methodology presented in this study offers a solid foundation for the use of computational tools in engineering practice, promoting innovation and sustainability in construction.

Optimizing deep learning-driven computer vision for civil infrastructure defect Identification: Challenges and strategies

2025-06-24

Ronghua Fu , Zhimeng Huang , Maosen Cao +3 more | Engineering Applications of Artificial Intelligence

Diseño y Gestión Sostenible de Pavimentos en Infraestructura Vial: Enfoque basado en el Ciclo de Vida y Análisis Multicriterio

2025-06-24

Luis Miguel León Torres , Denis Alexander Molina Morales , Wilmer Anastacio Zambrano Guerrero +2 more | Revista Veritas de Difusão Cientifica.

Este estudio examina estrategias sostenibles aplicadas al diseño y gestión de pavimentos en proyectos de infraestructura vial, integrando el enfoque de ciclo de vida y herramientas de análisis multicriterio. Se … Este estudio examina estrategias sostenibles aplicadas al diseño y gestión de pavimentos en proyectos de infraestructura vial, integrando el enfoque de ciclo de vida y herramientas de análisis multicriterio. Se evaluaron soluciones técnicas que incorporan materiales reciclados, tecnologías limpias y criterios de impacto ambiental, económico y social. Mediante un enfoque mixto, se analizaron datos de estudios de caso, entrevistas a profesionales y simulaciones de alternativas. Además, se incorporaron metodologías de evaluación del desempeño estructural con ensayos de laboratorio y simulaciones de comportamiento en el tiempo, así como herramientas de análisis de ciclo de vida (LCA) y toma de decisiones mediante análisis jerárquico (AHP). Las intervenciones experimentales incluyeron el uso de aditivos ecológicos, mezclas con residuos industriales y pavimentos de baja emisión, en distintas condiciones climáticas y de carga vehicular. Los resultados revelan que las decisiones sostenibles en pavimentación pueden reducir hasta un 30% la huella ambiental y mejorar la eficiencia de costos a largo plazo. Asimismo, se observaron beneficios sociales como la generación de empleos locales vinculados al reciclaje de materiales y mayor aceptación por parte de las comunidades beneficiadas. La percepción de los profesionales fue mayoritariamente favorable, destacando la necesidad de fortalecer marcos normativos e incentivos financieros para la adopción masiva de estas soluciones. Este trabajo contribuye a la toma de decisiones en proyectos viales bajo criterios de sostenibilidad integral, proponiendo un modelo replicable adaptable a distintas realidades territoriales. Finalmente, se resalta el papel estratégico de la planificación sostenible en la infraestructura vial para avanzar hacia un desarrollo más resiliente, eficiente y equitativo.

Comparative Study of Machine Learning Techniques for Predicting UCS Values Using Basic Soil Index Parameters in Pavement Construction

2025-06-24

Mudhaffer Alqudah , Haitham Saleh , Hakan Yasarer +2 more | Infrastructures

This study investigated the prediction of unconfined compressive strength (UCS), a common measure of soil’s undrained shear strength, using fundamental soil characteristics. While traditional pavement subgrade design often relies on … This study investigated the prediction of unconfined compressive strength (UCS), a common measure of soil’s undrained shear strength, using fundamental soil characteristics. While traditional pavement subgrade design often relies on parameters like the resilient modulus and California bearing ratio (CBR), researchers are exploring the potential of incorporating more easily obtainable strength indicators, such as UCS. To evaluate the potential effectiveness of UCS for pavement engineering applications, a dataset of 152 laboratory-tested soil samples was compiled to develop predictive models. For each sample, geotechnical properties including the Atterberg limits, liquid limit (LL), plastic limit (PL), water content (WC), and bulk density (determined using the Harvard miniature compaction apparatus), alongside the UCS, were measured. This dataset served to train various models to estimate the UCS from basic soil parameters. The methods employed included multi-linear regression (MLR), multi-nonlinear regression (MNLR), and several machine learning techniques: backpropagation artificial neural networks (ANNs), gradient boosting (GB), random forest (RF), support vector machine (SVM), and K-nearest neighbor (KNN). The aim was to establish a relationship between the dependent variable (UCS) and the independent basic geotechnical properties and to test the effectiveness of each ML algorithm in predicting UCS. The results indicate that the ANN-based model provided the most accurate predictions for UCS, achieving an R2 of 0.83, a root-mean-squared error (RMSE) of 1.11, and a mean absolute relative error (MARE) of 0.42. The performance ranking of the other models, from best to worst, was RF, GB, SV, KNN, MLR, and MNLR.

MVFD-Net: multi-view fusion detection network for occluded underwater dam cracks

2025-06-24

Yunzhe Wu , Xiaochen Qin , Lei Cai | Robotica

Abstract Detecting cracks in underwater dams is crucial for ensuring the quality and safety of the dam. However, underwater dam cracks are easily obscured by aquatic plants. Traditional single-view visual … Abstract Detecting cracks in underwater dams is crucial for ensuring the quality and safety of the dam. However, underwater dam cracks are easily obscured by aquatic plants. Traditional single-view visual inspection methods cannot effectively extract the feature information of the occluded cracks, while multi-view crack images can extract the occluded target features through feature fusion. At the same time, underwater turbulence leads to nonuniform diffusion of suspended sediments, resulting in nonuniform flooding of image feature noise from multiple viewpoints affecting the fusion effect. To address these issues, this paper proposes a multi-view fusion network (MVFD-Net) for crack detection in occluded underwater dams. First, we propose a feature reconstruction interaction encoder (FRI-Encoder), which interacts the multi-scale local features extracted by the convolutional neural network with the global features extracted by the transformer encoder and performs the feature reconstruction at the end of the encoder to enhance the feature extraction capability and at the same time in order to suppress the interference of the nonuniform scattering noise. Subsequently, a multi-scale gated adaptive fusion module is introduced between the encoder and the decoder for feature gated fusion, which further complements and recovers the noise flooding detail information. Additionally, this paper designs a multi-view feature fusion module to fuse multi-view image features to restore the occluded crack features and achieve the detection of occluded cracks. Through extensive experimental evaluations, the MVFD-Net algorithm achieves excellent performance when compared with current mainstream algorithms.

Smart prediction: Hybrid random forest for high-volume fly ash self-compacting concrete strength

2025-06-24

Shashikant Kumar , Rakesh Kumar , Sayan Sirimontree +4 more | Frontiers of Structural and Civil Engineering

Roadmap Construction Using Adaptive Signed Distance Field-based Probabilistic Maps

2025-06-24

JinSoo Yuk , Jongho Shin | Journal of Institute of Control Robotics and Systems

Type 3 Composite Container Leakage Study after Ambient Hydraulic Cycling Test

2025-06-24

Jeonghyeon Do , Jeong‐Won Lee , Do-Young Lee +1 more | Journal of the Korean Society of Manufacturing Process Engineers

Crack detection and categorisation on steel surfaces using machine learning techniques

2025-06-23

Maheswara Rao Bandi , Laxmi Narayana Pasupuleti , Anup Kumar Sah +1 more | Asian Journal of Civil Engineering

TableBorderNet: A Table Border Extraction Network Considering Topological Regularity

2025-06-23

Jing Yang , Shengqiang Zhou , X Li +2 more | Sensors

Accurate extraction of table borders in scanned road engineering drawings is crucial for the digital transformation of engineering archives, which is an essential step in the development of intelligent infrastructure … Accurate extraction of table borders in scanned road engineering drawings is crucial for the digital transformation of engineering archives, which is an essential step in the development of intelligent infrastructure systems. However, challenges such as degraded borders, image blur, and character adjoining often hinder the precise delineation of table structures, making automated parsing difficult. Existing solutions, including traditional OCR tools and deep learning methods, struggle to consistently delineate table borders in the presence of these visual distortions and fail to perform well without extensive annotated datasets, which limits their effectiveness in real-world applications. We propose TableBorderNet, a semantic segmentation framework designed for precise border extraction under complex visual conditions. The framework captures structural context by guiding convolutional feature extraction along explicit row and column directions, enabling more accurate delineation of table borders. To ensure topological consistency in complex or degraded inputs, a topology-aware loss function is introduced, which explicitly penalizes structural discontinuities during training. Additionally, a generative self-supervised strategy simulates common degradation patterns, allowing the model to achieve strong performance with minimal reliance on manually annotated data. Experiments demonstrate that the method achieves an Intersection-over-Union of 94.2% and a topological error of 1.07%, outperforming existing approaches. These results underscore its practicality and scalability for accelerating the digitization of engineering drawings in support of data-driven road asset management.

Automatic Detection of Landslide Surface Cracks from UAV Images Using Improved U-Network

2025-06-23

Hao Xu , Li Wang , Bao Shu +2 more | Remote Sensing

Surface cracks are key indicators of landslide deformation, crucial for early landslide identification and deformation pattern analysis. However, due to the complex terrain and landslide extent, manual surveys or traditional … Surface cracks are key indicators of landslide deformation, crucial for early landslide identification and deformation pattern analysis. However, due to the complex terrain and landslide extent, manual surveys or traditional digital image processing often face challenges with efficiency, precision, and interference susceptibility in detecting these cracks. Therefore, this study proposes a comprehensive automated pipeline to enhance the efficiency and accuracy of landslide surface crack detection. First, high-resolution images of landslide areas are collected using unmanned aerial vehicles (UAVs) to generate a digital orthophoto map (DOM). Subsequently, building upon the U-Net architecture, an improved encoder–decoder semantic segmentation network (IEDSSNet) was proposed to segment surface cracks from the images with complex backgrounds. The model enhances the extraction of crack features by integrating residual blocks and attention mechanisms within the encoder. Additionally, it incorporates multi-scale skip connections and channel-wise cross attention modules in the decoder to improve feature reconstruction capabilities. Finally, post-processing techniques such as morphological operations and dimension measurements were applied to crack masks to generate crack inventories. The proposed method was validated using data from the Heifangtai loess landslide in Gansu Province. Results demonstrate its superiority over current state-of-the-art semantic segmentation networks and open-source crack detection networks, achieving F1 scores and IOU of 82.11% and 69.65%, respectively—representing improvements of 3.31% and 4.63% over the baseline U-Net model. Furthermore, it maintained optimal performance with demonstrated generalization capability under varying illumination conditions. In this area, a total of 1658 surface cracks were detected and cataloged, achieving an accuracy of 85.22%. The method proposed in this study demonstrates strong performance in detecting surface cracks in landslide areas, providing essential data for landslide monitoring, early warning systems, and mitigation strategies.

Predictive modelling of concrete tensile strength using ANN and Supplementary Cementitious Materials (SCMs)

2025-06-23

Moutaman M. Abbas , Radu Muntean | Construction and Building Materials

Predicting interfacial bonding performance of CRTS III slab ballastless track structure via interfacial defects using the PSO-BP algorithm

2025-06-23

Wei Jiang , Bin Lei , En Wang +5 more | Engineering Structures

What lies within: Utilizing graph neural networks for subsurface detection in finite element simulations

2025-06-23

Ayatollah Yehia , Devin K. Harris , Amro Alabsi Aljundi | Engineering Structures

Computer vision framework for crack detection and esti- mation of air leakage through the straight-through cracks in buildings envelopes

2025-06-23

Maliheh Jahabakhsh , Andrea Ferrantelli | Rakenteiden Mekaniikka

Over time, buildings inevitably experience physical and functional deterioration. Regular and accurate inspections are essential to ensure safety and functionality, helping to avoid hazardous and uncomfortable conditions. Cracks, a common … Over time, buildings inevitably experience physical and functional deterioration. Regular and accurate inspections are essential to ensure safety and functionality, helping to avoid hazardous and uncomfortable conditions. Cracks, a common indicator of structural distress, also facilitate air infiltration due to pressure differences between the interior and exterior. The precise and efficient detection of cracks, along with the estimation of air infiltration through these cracks, is therefore critical for civil engineering applications that aim to reduce energy consumption and enhance indoor air quality. This paper introduces a novel image processing framework for automatic detection of cracks in building envelopes, coupled with the measurement of indoor and outdoor air parameters, which could be used to assess crack size and to estimate air infiltration rates by using heat transfer and fluid mechanics formulas. A computer vision-based system for automatic crack detection is first developed by using the Python OpenCV library through binarization, Otsu's thresholding and Canny operator; geometric quantification of the cracks is then obtained via skeletonization, and the resulting morphological characteristics of the cracks are finally used to estimate airflow by using common fluid mechanics formulas.

Experimental data-driven neural network model for predicting RC corbel shear strength via a web-based interface

2025-06-23

M. Abbas , Ammar Yasir Ali | Multiscale and Multidisciplinary Modeling Experiments and Design

Pavement Damage Detection Based on Embedded Design and Computer Vision

2025-06-23

Gao Xue | International Journal of Pavement Research and Technology

A systematic survey: role of deep learning-based image anomaly detection in industrial inspection contexts

2025-06-23

Vinita Shukla , Amit Shukla , Surya Prakash S. K +1 more | Frontiers in Robotics and AI

Industrial automation is rapidly evolving, encompassing tasks from initial assembly to final product quality inspection. Accurate anomaly detection is crucial for ensuring the reliability and robustness of automated systems. The … Industrial automation is rapidly evolving, encompassing tasks from initial assembly to final product quality inspection. Accurate anomaly detection is crucial for ensuring the reliability and robustness of automated systems. The intelligence of an industrial automation system is directly linked to its ability to detect and rectify abnormalities, thereby maintaining optimal performance. To advance intelligent manufacturing, sophisticated methods for high-quality process inspection are indispensable. This paper presents a systematic review of existing deep learning methodologies specifically designed for image anomaly detection in the context of industrial manufacturing. Through a comprehensive comparison, traditional techniques are evaluated against state-of-the-art advancements in deep learning-based anomaly detection methodologies, including supervised, unsupervised, and semi-supervised learning methods. Addressing inherent challenges such as real-time processing constraints and imbalanced datasets, this review offers a systematic analysis and mitigation strategies. Additionally, we explore popular anomaly detection datasets for surface defect detection and industrial anomaly detection, along with a critical examination of common evaluation metrics used in image anomaly detection. This review includes an analysis of the performance of current anomaly detection methods on various datasets, elucidating strengths and limitations across different scenarios. Moreover, we delve into the domain of drone-based, manipulator-based and AGV-based anomaly detections using deep learning techniques, highlighting the innovative applications of these methodologies. Lastly, the paper offers scholarly rigor and foresight by addressing emerging challenges and charting a course for future research opportunities, providing valuable insights to researchers in the field of deep learning-based surface defect detection and industrial image anomaly detection.

Crack-ConvT Net: A Convolutional Transformer Network for Crack Segmentation in Underwater Dams

2025-06-23

Pengfei Shi , H.B. Chen , Zaiming Geng +2 more | Complex & Intelligent Systems

Tension Force Estimation of Cable-Stayed Bridges Based on Computer Vision Without the Need for Direct Measurement of Mechanical Parameters of the Cables

2025-06-23

G. Michel Guzman-Acevedo , Juan A. Quintana-Rodriguez , E Vazquez +3 more | Sensors

Commonly, accelerometers are used to determine the tension force in cables through an indirect process; however, it is necessary to know the mechanical parameters of each element, such as mass … Commonly, accelerometers are used to determine the tension force in cables through an indirect process; however, it is necessary to know the mechanical parameters of each element, such as mass and length. Typically, obtaining or measuring these parameters is not feasible. Therefore, this research proposed an alternative methodology to indirectly estimate them based on historical information about the so-called classic instruments (accelerometers and hydraulic jack). This case study focused on the Rio Papaloapan Bridge located in Veracruz, Mexico, a structure that has experienced material casting issues due to inadequate heat treatment in some cable top anchor over its lifespan. Thirteen cables from the structure were selected to evaluate the proposed methodology, yielding results within 3.8% of difference compared to direct tension estimation generated by a hydraulic jack. Furthermore, to enhance data collection, this process was complemented using a computer vision methodology. This involved remotely measuring the vibration frequency of cables from high-resolution videos recorded with a smartphone. The non-contact method was validated in a laboratory using a vibrating table, successfully estimating oscillation frequencies from video-recording with a fixed camera. A field test on eight cables of a bridge was also conducted to assess the performance and feasibility of the proposed method. The results demonstrated an RMS Error of approximately 2 mHz and a percentage difference in the tension force estimation below 3% compared to an accelerometer measurement approach. Finally, it was determined that this composed methodology for indirect tension force determination is a viable option when: (1) cables are challenging to access; (2) there is no line of sight between the camera and cables outside the bridge; (3) there is a lack of information about the mechanical parameters of the cables.

Accurate identification of pavement cracks based on an improved segmentation model

2025-06-23

Quanman Zhao , Zhaohui Liu , C. H. T. Pan +2 more | International Journal of Pavement Engineering

Construction Concrete Price Prediction Based on a Double-Branch Physics-Informed Neural Network

2025-06-22

Ke Shi , Ruiqing Han , Zhipeng Li +1 more | Buildings

Traditional price prediction of construction material concrete often adopts macroeconomic indicators as independent variables. However, since there is often a closer relationship between the raw materials of construction concrete and … Traditional price prediction of construction material concrete often adopts macroeconomic indicators as independent variables. However, since there is often a closer relationship between the raw materials of construction concrete and the production of construction materials, the price prediction of construction concrete based on raw material prices can more directly ensure the prediction accuracy. Therefore, this study proposes a Double-Branch Physics-Informed Neural Network (DB-PINN) model based on both macroeconomic indicators and raw material price factors for the construction concrete price prediction. In particular, this model utilizes an Artificial Neural Network (ANN) as the baseline algorithm and incorporates physical constraints, such as a Multiple Linear Regression (MLR) model and a Vector Error Correction Model (VECM) to modify the loss function. To improve the prediction accuracy of the DB-PINN model, a feature analysis of the effect of the raw material price factors on the construction concrete price is conducted. Results showed that the proposed DB-PINN model has high accuracy in concrete price prediction. Further, to explore the specific ways in which macroeconomic indicators affect the concrete price prediction, a Marginal Effect Analysis (MEA) is conducted. Moreover, a comparative analysis using a traditional ANN model is conducted to verify the efficiency of the DB-PINN model, and a parameter sensitivity analysis is performed to reveal the impact of each raw material price factor and macroeconomic indicator on the construction concrete price. This study incorporates the introduction of raw material prices as input parameters for construction concrete price prediction, which facilitates the development of urban construction concrete price management in the pre-project phase.

CASOS REAIS DE OBRA COM CONCRETAGEM SUBAQUÁTICA

2025-06-22

María Bruno , José Silva , N. Santos +1 more | Revista fisio&terapia.

Underwater concreting is a technique widely used in infrastructure works, such as bridges, dams, ports and foundations in flooded environments and its durability is directly dependent on the interaction of … Underwater concreting is a technique widely used in infrastructure works, such as bridges, dams, ports and foundations in flooded environments and its durability is directly dependent on the interaction of concrete with the environment. This happens mainly due to the pathologies of the environment, whether by chemical agents, physical agents and biological agents. The main objective of the study is to understand some real cases and the techniques used in their constructions, presenting a theoretical overview of the use of methods such as tremie and submerged pockets, as well as normative aspects that control the quality of the specificity that involves civil engineering. The definition of a checklist of the steps with important items for an accurate diagnosis will also serve as an example for civil engineers when executing or evaluating work cases with underwater concreting. The Real Case Study highlights the work and takes into account the conditions of the environment, the material used, the methodologies used, the control of the problem presented in the case and also the results obtained with the possible insights for future planning. The case study methodology includes the study of different situations in concretes where diagnostic intervention and technical support were required.

CALC−ΔKth$$ \mathrm{CALC}-{\Delta \mathrm{K}}_{\mathrm{th}} $$: Automatic Assessment of the Stress Intensity Factor Threshold From VHCF Fracture Surfaces With Optically Dark Area

2025-06-22

Rujun Li , Wei Zhang , Davide Salvatore Paolino +3 more | Fatigue & Fracture of Engineering Materials & Structures

ABSTRACT is a assessing the stress intensity factor (SIF) threshold of materials from specimens failed in the very‐high‐cycle fatigue (VHCF) region and showing the typical fish‐eye morphology. The developed process … ABSTRACT is a assessing the stress intensity factor (SIF) threshold of materials from specimens failed in the very‐high‐cycle fatigue (VHCF) region and showing the typical fish‐eye morphology. The developed process involves two key parameters: the size of the optically dark area (ODA), which is a typical feature region on the fracture surface of specimens failing in the VHCF life region from internal defects, and the stress amplitude at the crack initiation site. Based on the optical image of the fracture surface input from the user side, the automatic detection of the ODA feature is obtained with a deep learning method. Thereafter, the analytical stress distribution in the specimen is assessed, thus allowing to compute the critical SIF threshold for the investigated specimen. This package requires minimal scanning prerequisites on specimens, featuring notable advantages in modularity, automation, and practical usability.

Estimating damage cost of truck overweight on flexible pavements in Oman using MEPDG rutting model

2025-06-21

Hossam F. H. Abdelfattah , Khalid Al-Shamsi | Innovative Infrastructure Solutions

Accuracy–Efficiency Trade-Off: Optimizing YOLOv8 for Structural Crack Detection

2025-06-21

Jing-Xing Zhang , З.В. Беляева , Yue Huang | Sensors

To address the accuracy–efficiency trade-off faced by deep learning models in structural crack detection, this paper proposes an optimized version of the YOLOv8 model. YOLO (You Only Look Once) is … To address the accuracy–efficiency trade-off faced by deep learning models in structural crack detection, this paper proposes an optimized version of the YOLOv8 model. YOLO (You Only Look Once) is a real-time object detection algorithm known for its high speed and decent accuracy. To improve crack feature representation, the backbone is enhanced with the SimAM attention mechanism. A lightweight C3Ghost module reduces parameter count and computation, while a bidirectional multi-scale feature fusion structure replaces the standard neck to enhance efficiency. Experimental results show that the proposed model achieves a mean Average Precision (mAP) of 88.7% at 0.5 IoU and 69.4% for [email protected]:0.95, with 12.3% fewer Giga Floating Point Operations (GFlops), and faster inference. These improvements significantly enhance the detection of fine cracks while maintaining real-time performance, making it suitable for engineering scenarios.

Influence of Substrate Surface Morphology on Bonding Behaviours at Shotcrete–Substrate Interface

2025-06-20

Kai Li , Hamed Lamei Ramandi , Chengguo Zhang +2 more | Rock Mechanics and Rock Engineering

Abstract This study investigates the influence of substrate morphology on bond strength at the interface. Circular surfaces with varying morphologies were created on plaster substrates and quantified by three three-dimensional … Abstract This study investigates the influence of substrate morphology on bond strength at the interface. Circular surfaces with varying morphologies were created on plaster substrates and quantified by three three-dimensional (3D) roughness parameters: joint roughness coefficient (JRC 3D ), area ratio ( R S ), and statistical parameter Z 2S . Plaster substrates were designed in a LEGO-style configuration, with various morphology surfaces placed on the upper surface of each cylindrical plaster base. Shotcrete was applied to these surfaces, cured for 28 days, and then subjected to direct pull-off tests to assess bond strength variations across surfaces with varying morphologies. Findings reveal that shotcrete’s shrinkage characteristics interact with surface morphologies to influence bond strength. A novel 3D surface morphological parameter, R Z × V P / V V , Adjusted Volume Ratio (AVR), was introduced. AVR showed a stronger correlation between surface morphology and bond strength than traditional 3D parameters, JRC 3D , R S , and Z 2S . Results indicate that bond strength generally increases with the AVR of the surface; however, excessively rough surfaces may reduce bond strength due to insufficient contact at the interface. Whilst 2D parameters do not represent the 3D nature of joint surfaces, the new 3D AVR, which can be incorporated into 3D surface imaging techniques such as photogrammetry, provides a reliable assessment of joint surface morphology for engineering applications.

Enhanced American Association of State Highway and Transportation Officials Cumulative Difference Approach for Pavement Data Segmentation

2025-06-20

Samer W. Katicha , Gerardo W. Flintsch | Transportation Research Record Journal of the Transportation Research Board

This paper proposes improving the American Association of State Highway and Transportation Officials cumulative difference approach to pavement data segmentation. Although this approach is popular in pavement management applications, it … This paper proposes improving the American Association of State Highway and Transportation Officials cumulative difference approach to pavement data segmentation. Although this approach is popular in pavement management applications, it is heuristic, based on visual inspection of plots of data, and has well-documented limitations. One main limitation is reliance on a change in sign of the slope of the cumulative sum of the data to identify segment breakpoints. This makes it very sensitive to small data variations (such as noise), and researchers have shown that segment breakpoints can occur without a change in the sign of the slope. Our proposed approach uses the maximum (in absolute value) of the cumulative sum to identify a potential breakpoint. Whether that maximum is because of random variation or the presence of a true breakpoint is rigorously tested at a user-specified significance level using the known statistical distribution of that maximum. The approach also allows specifying a minimum segment length and minimum difference between adjacent segments. Simulation studies show that when the process that generated the data consists of piecewise constant segments, the Type I error of erroneously identifying breakpoints is controlled at the chosen statistical significance level, both for normally distributed random variation in the data and any distribution with well-defined variance. When the process that generated the data does not consist of piecewise constant segments, the approach results in a segmentation with a very low mean square error or mean absolute error with respect to the data generating process. We show an application to traffic speed deflectometer deflection data.

A Deep Learning-Driven Framework for Real-Time Recognition and Quantification of Subway Tunnel Surface Defects Using High-Resolution Imaging

2025-06-20

Zunchao Ren , Wenbo Liu , Dukun Zhao +2 more | Urban Rail Transit

Abstract Subway tunnels, with their complex underground environment, frequently develop surface defects like cracks and water leakage over time. Traditional manual inspection methods are inadequate for current accuracy and efficiency … Abstract Subway tunnels, with their complex underground environment, frequently develop surface defects like cracks and water leakage over time. Traditional manual inspection methods are inadequate for current accuracy and efficiency needs. This paper introduces a deep learning approach to detect and assess these defects in subway tunnels, aiming for real-time detection and quantitative assessment. It proposes a data collection strategy for rapid detection and detailed exploration in subway shield tunnels. A multi-category dataset of tunnel defects was created, alongside an automatic identification method using the YOLO v7 algorithm for operational tunnels. This method, validated against Qingdao Metro’s manual inspection records, markedly reduces manual inspection costs during tunnel operation. Research indicates a strong correlation between image inspection equipment efficiency, defect detection accuracy, and actual project needs in subway tunnels. Image quality is positively linked to tunnel illumination intensity. A balance between inspection speed and focal length is crucial for image size and precision. Lowering the confidence threshold from 0.4 to 0.2 increases detection rates for cracks and water leakage by 20.60 and 4.06%, respectively, minimizing defect oversight. This study presents algorithms, frameworks, and methods for real-time quantification to enhance tunnel operation, maintenance, and manual processing.

Research on the Defect Detection Method of Steel-Reinforced Concrete Based on Piezoelectric Technology and Weight Analysis

2025-06-20

Yu Yin , Yulin Dong , Yulong Jiang +3 more | Sensors

Aiming at the complex internal working conditions of steel-reinforced concrete structures, this paper proposes an active detection method for the internal hollow defects of steel-reinforced concrete based on wave analysis … Aiming at the complex internal working conditions of steel-reinforced concrete structures, this paper proposes an active detection method for the internal hollow defects of steel-reinforced concrete based on wave analysis by using the driving and sensing functions of piezoelectric ceramic materials. The feasibility was verified through the single-condition detection test, revealing the propagation and attenuation characteristics of the stress wave signal under various detection conditions, and it was applied to the damage identification of steel-reinforced concrete rectangular section columns. Combined with the wavelet packet energy theory, the data processing of the original detection signal is carried out based on composite weighting by energy distribution entropy. Finally, the analytic hierarchy process (AHP) was introduced to study the weight vectors of different damage metrics on the detection signal, and a linear regression model based on different damage metrics was proposed as the comprehensive defect evaluation index. The research results show that the detection of internal defects in steel-reinforced concrete structures based on piezoelectric technology is applicable to concrete of different strength grades. With the increase of the detection distance and the degree of damage, the energy of the stress wave signal decreases. For example, under defect-free conditions, the energy value of the stress wave signal with a detection distance of 400 mm decreases by 92.94% compared to that with a detection distance of 100 mm. Meanwhile, it can be known from the defect detection test results of steel-reinforced concrete columns that the wavelet packet energy value under the defect condition with three obstacles decreased by 85.42% compared with the barrier-free condition, and the defect evaluation index (DI) gradually increased from 0 to 0.859. The comprehensive application of piezoelectric technology and weight analysis methods has achieved qualitative and quantitative analysis of defects, providing reference value for the maintenance and repair of steel-reinforced concrete structures.

Research on Fracture Energy Prediction and Size Effect of Concrete Based on Deep Learning with SHAP Interpretability Method

2025-06-20

Hui‐Ming Wang , Weiqi Zhang , Jie Lin +1 more | Buildings

Fracture energy plays a pivotal role in ensuring the safe design of concrete structures. Currently, experimental testing remains the predominant methodology for exploring fracture energy in concrete. Nevertheless, this approach … Fracture energy plays a pivotal role in ensuring the safe design of concrete structures. Currently, experimental testing remains the predominant methodology for exploring fracture energy in concrete. Nevertheless, this approach is hindered by protracted sample production cycles and test loading conditions that contribute to elevated expenses. Moreover, owing to the complex nonlinear behavior exhibited by concrete during the fracturing process, existing empirical formulas exhibit restricted precision when forecasting fracture energy. Therefore, in order to swiftly and accurately predict the fracture energy of concrete and investigate the impact of various factors on it, this study employs a deep learning algorithm to establish the correlation between parameters and fracture energy. Additionally, an interpretable deep learning prediction model for fracture energy is proposed, which is then compared with existing empirical formulas. Finally, the SHapley Additive exPlanations (SHAP) interpretability method is utilized to interpret and analyze the prediction results. The SHAP method can identify and visualize the contribution direction (positive/negative) and magnitude of the input features and reveal the relative importance of parameters at both local and global levels simultaneously. This analysis effectively explains the decision-making mechanism of the “black box” model and significantly improves the problem of insufficient interpretability that is common in traditional machine learning methods. The findings demonstrate that over 87% of the prediction results from the deep learning model in this study exhibit a relative error of less than 10% on the test set. The model effectively captures the intricate nonlinear relationship among characteristic parameters, exhibiting superior accuracy and generalization capabilities compared to empirical formulas. The SHAP values of the input parameters are visualized to assess their influence on fracture energy: initially, fracture energy increases and then decreases with increasing compressive strength, age, and coarse aggregate proportion; fracture energy increases with increasing maximum particle size of aggregate until it reaches 20 mm, after which it stabilizes; a high water–binder ratio reduces fracture energy; within the range of 400 mm, fracture energy increases with height, exhibiting a noticeable size effect; fracture energy increases with specimen width, but the size effect diminishes beyond 150 mm width; fracture energy decreases as span–height ratio increases; seam height ratio exhibits an initial increase followed by a decrease in fracture energy, with larger ratios showing a more pronounced size effect; an increase in ligament height enhances fracture energy while maintaining a significant size effect.

Prediction Analysis of Pre-Camber for Continuous Girder Bridge Cantilever Casting Construction Based on DBO-CNN-BiLSTM-Attention Neural Network

2025-06-20

J. S.Zhang , Haiqing Liu , Xiangen Gong +2 more | Buildings

During the cantilever casting construction process of continuous girder bridges, it is crucial to accurately predict the pre-camber of each cantilever segment to ensure smooth closure of the bridge, structural … During the cantilever casting construction process of continuous girder bridges, it is crucial to accurately predict the pre-camber of each cantilever segment to ensure smooth closure of the bridge, structural safety, and construction quality. However, traditional methods for predicting pre-camber have limited accuracy and primarily handle linear relationships. Therefore, this paper proposes a pre-camber prediction model based on a Convolutional-Bidirectional Long Short-Term Memory network with a fusion attention mechanism (CNN-BiLSTM-Attention) and utilizes the Dung Beetle Optimizer (DBO) algorithm to optimize the hyperparameters of the CNN-BiLSTM-Attention model to enhance its predictive performance. The research results indicate that compared to several other prediction models, the model proposed in this paper demonstrates superior performance in predicting the pre-camber of continuous girder bridges. Compared to other prediction models, the evaluation metrics MAE, RMSE, and MAPE of the model proposed in this paper are minimized to 2.76 mm, 3.47 mm, and 0.70%, respectively. Applying the model proposed in this paper to the cantilever casting stage of the elevated continuous girder bridges in Shenyang Metro, China, enables pre-camber prediction with an accuracy of an average absolute error of less than 2 mm, providing a new efficient method for pre-camber prediction in cantilever casting construction.

Deep learning-based crack detection and prediction for structural health monitoring

2025-06-20

Satyabrata Roy , Biswarup Yogi , Raj Majumdar +2 more | Deleted Journal

Transfer Learning Model for Crack Detection in Side SlopesBased on Crack-Net

2025-06-20

Na Li , Y. Zhang , ZhongXiang Zhang +1 more | Applied Sciences

Accurate detection of slope cracks plays a crucial role in early landslide disaster warning; however, traditional approaches often struggle to identify fine and irregular cracks. This study introduces a novel … Accurate detection of slope cracks plays a crucial role in early landslide disaster warning; however, traditional approaches often struggle to identify fine and irregular cracks. This study introduces a novel deep learning model, Crack-Net, which leverages a multi-modal feature fusion mechanism and is developed using transfer learning. To resolve the blurred representation of small-scale cracks, a nonlinear frequency-domain mapping module is employed to decouple amplitude and phase information, while a cross-domain attention mechanism facilitates adaptive feature fusion. In addition, a deep feature fusion module integrating deformable convolution and a dual attention mechanism is embedded within the encoder–decoder architecture to enhance multi-scale feature interactions and preserve crack topology. The model is pre-trained on the CrackVision12K dataset and fine-tuned on a custom dataset of slope cracks, effectively addressing performance degradation in small-sample scenarios. Experimental results show that Crack-Net achieves an average accuracy of 92.1%, outperforming existing models such as DeepLabV3 and CrackFormer by 9.4% and 5.4%, respectively. Furthermore, the use of transfer learning improves the average precision by 1.6%, highlighting the model’s strong generalization capability and practical effectiveness in real-world slope crack detection.

Rapid construction of large-scale bridge crack dataset using residual neural network

2025-06-19

Qian Fan , Yunhua Tan , Shengye Li +2 more | Measurement Science and Technology

Abstract In order to solve the problem of time-consuming and difficult construction of image datasets in bridge engineering, this paper proposes a fast construction method of large-scale bridge crack dataset … Abstract In order to solve the problem of time-consuming and difficult construction of image datasets in bridge engineering, this paper proposes a fast construction method of large-scale bridge crack dataset based on residual neural network (ResNet). Firstly, two image processing tools are developed for solving the problems of wrong classification of images due to the lack of relative spatial information and the omission of subtle image features, and environmental samples are introduced without losing recognition accuracy by combining the engineering requirements. Further, a detailed process of building a large dataset is given based on the ResNet50 model and transfer learning method. Finally, the validity and feasibility of the proposed method are analyzed through the construction of a large-scale bridge crack image dataset, and distribution pattern of image data behind the proposed method is revealed. By comparing the differences in time and accuracy of traditional dataset construction strategies, the superiority of the proposed dataset construction method is verified.&#xD;

Integrating Dynamic Sensors and Weigh-in-Motion Systems for Pavement Performance Assessment

2025-06-19

Silas Henrique Barbosa de Carvalho , Malik Noor Ul Amin Awan , Leila Hashemian +2 more | Canadian Journal of Civil Engineering

In July 2022, a newly instrumented test road was constructed in Edmonton, Alberta, Canada, to monitor pavement conditions through embedded sensors in the asphalt layers. The test road, located on … In July 2022, a newly instrumented test road was constructed in Edmonton, Alberta, Canada, to monitor pavement conditions through embedded sensors in the asphalt layers. The test road, located on a high-traffic access road to the Edmonton Waste Management Center. This study presents a comprehensive analysis of pavement performance by integrating data from dynamic sensors and a Weigh-in-Motion (WIM) system, employing both direct sensor measurements and outputs from a Layered Elastic Analysis (LEA) to evaluate the pavement's response to traffic loads. The findings revealed that the outer wheels of vehicles predominantly affected the middle longitudinal row of strain sensors, validating the need for multiple sensor rows to capture accurate strain data. Furthermore, relative errors of 4.3% for the horizontal strains and 22.5% for the vertical strains were found in the comparison between the observed data from the sensors and the calculated results from the computer software.

Application of spatial analysis using GIS and digital twins techniques in pavement management: a review

2025-06-19

Bara’ W. Al-Mistarehi , Amir Shtayat , Sara Moridpour +4 more | Innovative Infrastructure Solutions

Study on deformation–time law of airport runway during horizontal directional drilling

2025-06-19

Yue-Ya Shi , Wei Guo , Yankun Kong +1 more | Proceedings of the Institution of Civil Engineers - Transport

The study focuses on the lack of basis for surface deformation in airport navigational lighting aid projects using horizontal directional drilling (HDD) technology. Taking Guanghan airport as an example, a … The study focuses on the lack of basis for surface deformation in airport navigational lighting aid projects using horizontal directional drilling (HDD) technology. Taking Guanghan airport as an example, a runway test section was constructed to explore the time-series law of cement surface deformation during HDD installation of navigational lighting. Small-calibre (10 cm) HDD technology was used to simulate the actual process and verify its feasibility in the airport. Micro-deformation monitoring radar, ground-penetrating radar and a heavy weight deflectometer were employed for displacement monitoring and detecting the reaction characteristics of the base layer to reveal the intrinsic driving force of the runway surface deformation. The results showed that the intrinsic cause of surface deformation was structural changes in the runway structural layer during construction. The settlement, observed as a manifestation of surface deformation during HDD, could be divided into three stages – sharp settlement, slow rebound and stable settlement. After completion of construction activities, the cumulative displacement remained stable within −1.4 mm while the maximum change rate of the impact stiffness modulus did not exceed 1%, thereby meeting the requirements of airport flight operation management.

CBAM-U-Net and SCT-Based Outcrop Fracture Extraction and Connectivity Characterization with Limited Labeled Data

2025-06-19

Shan Pei , Tingen Fan , Jin‐Song Shen +2 more | Geoenergy Science and Engineering

Optimization of electric concrete transport vehicle configuration for long-distance tunnel construction considering driving range: a case study

2025-06-19

Xiaoxu Yang , Wenbin Guo , Shuo Yang | Eksploatacja i Niezawodnosc - Maintenance and Reliability

This study optimizes the configuration of Electric Concrete Transport Vehicles (ECTVs) for long-distance tunnel construction, focusing on the critical factors of driving range and reliability. A comprehensive model integrating tunnel … This study optimizes the configuration of Electric Concrete Transport Vehicles (ECTVs) for long-distance tunnel construction, focusing on the critical factors of driving range and reliability. A comprehensive model integrating tunnel length, terrain, construction schedules, vehicle load capacities, driving range, and reliability is developed. The study acknowledges limitations of traditional fuel-powered vehicles and proposes ECTVs as a sustainable and reliable alternative. The model is validated through a case study in a plateau region of Southwest China. Key findings show that the number of ECTVs required increases with excavation distance, seasonal variations significantly impact configuration, and balancing loading capacities with driving range and reliability is crucial for optimization. The study contributes a new approach to ECTV configuration by incorporating driving range and reliability into the model, offering practical guidance for construction managers to reduce costs, minimize delays, enhance efficiency, and improve reliability.

UCrack-DA: A Multi-Scale Unsupervised Domain Adaptation Method for Surface Crack Segmentation

2025-06-19

Fei Deng , Yang Shao-hui , Bin Wang +2 more | Remote Sensing

Surface cracks serve as early warning signals for potential geological hazards, and their precise segmentation is crucial for disaster risk assessment. Due to differences in acquisition conditions and the diversity … Surface cracks serve as early warning signals for potential geological hazards, and their precise segmentation is crucial for disaster risk assessment. Due to differences in acquisition conditions and the diversity of crack morphology, scale, and surface texture, there is a significant domain shift between different crack datasets, necessitating transfer training. However, in real work areas, the sparse distribution of cracks results in a limited number of samples, and the difficulty of crack annotation makes it highly inefficient to use a high proportion of annotated samples for transfer training to predict the remaining samples. Domain adaptation methods can achieve transfer training without relying on manual annotation, but traditional domain adaptation methods struggle to effectively address the characteristics of cracks. To address this issue, we propose an unsupervised domain adaptation method for crack segmentation. By employing a hierarchical adversarial mechanism and a prediction entropy minimization constraint, we extract domain-invariant features in a multi-scale feature space and sharpen decision boundaries. Additionally, by integrating a Mix-Transformer encoder, a multi-scale dilated attention module, and a mixed convolutional attention decoder, we effectively solve the challenges of cross-domain data distribution differences and complex scene crack segmentation. Experimental results show that UCrack-DA achieves superior performance compared to existing methods on both the Roboflow-Crack and UAV-Crack datasets, with significant improvements in metrics such as mIoU, mPA, and Accuracy. In UAV images captured in field scenarios, the model demonstrates excellent segmentation Accuracy for multi-scale and multi-morphology cracks, validating its practical application value in geological hazard monitoring.