Engineering › Control and Systems Engineering

Machine Fault Diagnosis Techniques

Works Count: 45629

Wikipedia

Description

This cluster of papers focuses on machine fault diagnosis and prognostics using methods such as Empirical Mode Decomposition, wavelet transform, and deep learning. It covers topics like condition monitoring, vibration analysis, and remaining useful life estimation for rotating machinery. The research explores the application of machine learning techniques, neural networks, and signal processing in fault detection and health management of various mechanical systems.

Keywords

Empirical Mode Decomposition; Fault Diagnosis; Machine Learning; Condition Monitoring; Vibration Analysis; Deep Learning; Remaining Useful Life Estimation; Wavelet Transform; Rotating Machinery; Neural Networks

Rolling element bearing diagnostics—A tutorial

2010-11-27

Robert B. Randall , Jérôme Antoni

COMPLEMENTARY ENSEMBLE EMPIRICAL MODE DECOMPOSITION: A NOVEL NOISE ENHANCED DATA ANALYSIS METHOD

2010-04-01

Jia‐Rong Yeh , Jiann-Shing Shieh , Norden E. Huang

The phenomenon of mode-mixing caused by intermittence signals is an annoying problem in Empirical Mode Decomposition (EMD) method. The noise assisted method of Ensemble EMD (EEMD) has not only effectively … The phenomenon of mode-mixing caused by intermittence signals is an annoying problem in Empirical Mode Decomposition (EMD) method. The noise assisted method of Ensemble EMD (EEMD) has not only effectively resolved this problem but also generated a new one, which tolerates the residue noise in the signal reconstruction. Of course, the relative magnitude of the residue noise could be reduced with large enough ensemble, it would be too time consuming to implement. An improved algorithm of noise enhanced data analysis method is suggested in this paper. In this approach, the residue of added white noises can be extracted from the mixtures of data and white noises via pairs of complementary ensemble IMFs with positive and negative added white noises. Though this new approach yields IMF with the similar RMS noise as EEMD, it effectively eliminated residue noise in the IMFs. Numerical experiments were conducted to demonstrate the new approach and also illustrate the problems of mode splitting and translation.

The spectral kurtosis: application to the vibratory surveillance and diagnostics of rotating machines

2004-11-09

Jérôme Antoni , Robert B. Randall

Recent advances in time–frequency analysis methods for machinery fault diagnosis: A review with application examples

2013-03-13

Zhipeng Feng , Ming Liang , Fulei Chu

Variational Mode Decomposition

2014-01-24

Konstantin Dragomiretskiy , Dominique Zosso

During the late 1990s, Huang introduced the algorithm called Empirical Mode Decomposition, which is widely used today to recursively decompose a signal into different modes of unknown but separate spectral … During the late 1990s, Huang introduced the algorithm called Empirical Mode Decomposition, which is widely used today to recursively decompose a signal into different modes of unknown but separate spectral bands. EMD is known for limitations like sensitivity to noise and sampling. These limitations could only partially be addressed by more mathematical attempts to this decomposition problem, like synchrosqueezing, empirical wavelets or recursive variational decomposition. Here, we propose an entirely non-recursive variational mode decomposition model, where the modes are extracted concurrently. The model looks for an ensemble of modes and their respective center frequencies, such that the modes collectively reproduce the input signal, while each being smooth after demodulation into baseband. In Fourier domain, this corresponds to a narrow-band prior. We show important relations to Wiener filter denoising. Indeed, the proposed method is a generalization of the classic Wiener filter into multiple, adaptive bands. Our model provides a solution to the decomposition problem that is theoretically well founded and still easy to understand. The variational model is efficiently optimized using an alternating direction method of multipliers approach. Preliminary results show attractive performance with respect to existing mode decomposition models. In particular, our proposed model is much more robust to sampling and noise. Finally, we show promising practical decomposition results on a series of artificial and real data.

Improved complete ensemble EMD: A suitable tool for biomedical signal processing

2014-07-17

Marcelo A. Colominas , Gastón Schlotthauer , Marı́a E. Torres

View PDF Chat

A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings

1999-08-01

N. Tandon , Achintya Choudhury

Empirical Wavelet Transform

2013-05-30

Jérôme Gilles

Some recent methods, like the Empirical Mode Decomposition (EMD), propose to decompose a signal accordingly to its contained information. Even though its adaptability seems useful for many applications, the main … Some recent methods, like the Empirical Mode Decomposition (EMD), propose to decompose a signal accordingly to its contained information. Even though its adaptability seems useful for many applications, the main issue with this approach is its lack of theory. This paper presents a new approach to build adaptive wavelets. The main idea is to extract the different modes of a signal by designing an appropriate wavelet filter bank. This construction leads us to a new wavelet transform, called the empirical wavelet transform. Many experiments are presented showing the usefulness of this method compared to the classic EMD.

View PDF Chat

Current signature analysis to detect induction motor faults

2001-01-01

William T. Thomson , M. Fenger

Three-phase induction motors are the "workhorses" of industry and are the most widely used electrical machines. In an industrialized nation, they can typically consume between 40 to 50% of all … Three-phase induction motors are the "workhorses" of industry and are the most widely used electrical machines. In an industrialized nation, they can typically consume between 40 to 50% of all the generated capacity of that country. This article focuses on the industrial application of motor current signature analysis (MCSA) to diagnose faults in three-phase induction motor drives. MCSA is a noninvasive, online monitoring technique for the diagnosis of problems in induction motors. Reliability-based maintenance (RBM) and condition-based maintenance (CBM) strategies are now widely used by industry, and health monitoring of electrical drives is a major feature in such programs.

A review on empirical mode decomposition in fault diagnosis of rotating machinery

2012-10-18

Yaguo Lei , Jing Lin , Zhengjia He +1 more

Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications

2013-08-30

Jay Lee , Fangji Wu , Wenyu Zhao +3 more

Condition monitoring and fault detection of wind turbines and related algorithms: A review

2007-08-21

Zafar Hameed , Youngsun Hong , Young-in Cho +2 more

A review on machinery diagnostics and prognostics implementing condition-based maintenance

2005-11-04

Andrew Jardine , Daming Lin , Dragan Banjević

The spectral kurtosis: a useful tool for characterising non-stationary signals

2004-12-16

Jérôme Antoni

Linear and quadratic time-frequency signal representations

1992-04-01

Franz Hlawatsch , G.F. Boudreaux-Bartels

A tutorial review of both linear and quadratic representations is given. The linear representations discussed are the short-time Fourier transform and the wavelet transform. The discussion of quadratic representations concentrates … A tutorial review of both linear and quadratic representations is given. The linear representations discussed are the short-time Fourier transform and the wavelet transform. The discussion of quadratic representations concentrates on the Wigner distribution, the ambiguity function, smoothed versions of the Wigner distribution, and various classes of quadratic time-frequency representations. Examples of the application of these representations to typical problems encountered in time-varying signal processing are provided.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

Wavelets for fault diagnosis of rotary machines: A review with applications

2013-04-22

Ruqiang Yan , Robert X. Gao , Xuefeng Chen

Rotating machinery prognostics: State of the art, challenges and opportunities

2008-07-02

Aiwina Heng , Sheng Zhang , Andy Tan +1 more

A comparison study of improved Hilbert–Huang transform and wavelet transform: Application to fault diagnosis for rolling bearing

2004-03-16

Zhike Peng , Peter W. Tse , Fulei Chu

Empirical Mode Decomposition as a Filter Bank

2004-02-01

Patrick Flandrin , Gabriel Rilling , Paulo Gonçalvès

Empirical mode decomposition (EMD) has recently been pioneered by Huang et al. for adaptively representing nonstationary signals as sums of zero-mean amplitude modulation frequency modulation components. In order to better … Empirical mode decomposition (EMD) has recently been pioneered by Huang et al. for adaptively representing nonstationary signals as sums of zero-mean amplitude modulation frequency modulation components. In order to better understand the way EMD behaves in stochastic situations involving broadband noise, we report here on numerical experiments based on fractional Gaussian noise. In such a case, it turns out that EMD acts essentially as a dyadic filter bank resembling those involved in wavelet decompositions. It is also pointed out that the hierarchy of the extracted modes may be similarly exploited for getting access to the Hurst exponent.

View PDF Chat

Support vector machine in machine condition monitoring and fault diagnosis

2007-01-17

Achmad Widodo , Bo‐Suk Yang

ENSEMBLE EMPIRICAL MODE DECOMPOSITION: A NOISE-ASSISTED DATA ANALYSIS METHOD

2008-10-17

Zhaohua Wu , Norden E. Huang

A new Ensemble Empirical Mode Decomposition (EEMD) is presented. This new approach consists of sifting an ensemble of white noise-added signal (data) and treats the mean as the final true … A new Ensemble Empirical Mode Decomposition (EEMD) is presented. This new approach consists of sifting an ensemble of white noise-added signal (data) and treats the mean as the final true result. Finite, not infinitesimal, amplitude white noise is necessary to force the ensemble to exhaust all possible solutions in the sifting process, thus making the different scale signals to collate in the proper intrinsic mode functions (IMF) dictated by the dyadic filter banks. As EEMD is a time–space analysis method, the added white noise is averaged out with sufficient number of trials; the only persistent part that survives the averaging process is the component of the signal (original data), which is then treated as the true and more physical meaningful answer. The effect of the added white noise is to provide a uniform reference frame in the time–frequency space; therefore, the added noise collates the portion of the signal of comparable scale in one IMF. With this ensemble mean, one can separate scales naturally without any a priori subjective criterion selection as in the intermittence test for the original EMD algorithm. This new approach utilizes the full advantage of the statistical characteristics of white noise to perturb the signal in its true solution neighborhood, and to cancel itself out after serving its purpose; therefore, it represents a substantial improvement over the original EMD and is a truly noise-assisted data analysis (NADA) method.

Condition monitoring of wind turbines: Techniques and methods

2012-04-04

Fausto Pedro Garcı́a Márquez , Andrew M. Tobias , Jesús María Pinar-Pérez +1 more

Estimating and interpreting the instantaneous frequency of a signal. I. Fundamentals

1992-04-01

B. Boashash

The concept of instantaneous frequency (IF), its definitions, and the correspondence between the various mathematical models formulated for representation of IF are discussed. The extent to which the IF corresponds … The concept of instantaneous frequency (IF), its definitions, and the correspondence between the various mathematical models formulated for representation of IF are discussed. The extent to which the IF corresponds to the intuitive expectation of reality is also considered. A historical review of the successive attempts to define the IF is presented. The relationships between the IF and the group-delay, analytic signal, and bandwidth-time (BT) product are explored, as well as the relationship with time-frequency distributions. The notions of monocomponent and multicomponent signals and instantaneous bandwidth are discussed. It is shown that these notions are well described in the context of the theory presented.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

A review of induction motors signature analysis as a medium for faults detection

2000-01-01

Mohamed Benbouzid

This paper is intended as a tutorial overview of induction motors signature analysis as a medium for fault detection. The purpose is to introduce in a concise manner the fundamental … This paper is intended as a tutorial overview of induction motors signature analysis as a medium for fault detection. The purpose is to introduce in a concise manner the fundamental theory, main results, and practical applications of motor signature analysis for the detection and the localization of abnormal electrical and mechanical conditions that indicate, or may lead to, a failure of induction motors. The paper is focused on the so-called motor current signature analysis which utilizes the results of spectral analysis of the stator current. The paper is purposefully written without "state-of-the-art" terminology for the benefit of practising engineers in facilities today who may not be familiar with signal processing.

Advances in Diagnostic Techniques for Induction Machines

2008-11-06

A. Bellini , F. Filippetti , C. Tassoni +1 more

This paper investigates diagnostic techniques for electrical machines with special reference to induction machines and to papers published in the last ten years. A comprehensive list of references is reported … This paper investigates diagnostic techniques for electrical machines with special reference to induction machines and to papers published in the last ten years. A comprehensive list of references is reported and examined, and research activities classified into four main topics: 1) electrical faults; 2) mechanical faults; 3) signal processing for analysis and monitoring; and 4) artificial intelligence and decision-making techniques.

Improved time-frequency representation of multicomponent signals using exponential kernels

1989-06-01

Heejun Choi , William J. Williams

The authors introduce a time-frequency distribution of L. Cohen's (1966) class and examines its properties. This distribution is called exponential distribution (ED) after its exponential kernel function. First, the authors … The authors introduce a time-frequency distribution of L. Cohen's (1966) class and examines its properties. This distribution is called exponential distribution (ED) after its exponential kernel function. First, the authors interpret the ED from the spectral-density-estimation point of view. They then show how the exponential kernel controls the cross terms as represented in the generalized ambiguity function domain, and they analyze the ED for two specific types of multicomponent signals: sinusoidal signals and chirp signals. Next, they define the ED for discrete-time signals and the running windowed exponential distribution (RWED), which is computationally efficient. Finally, the authors present numerical examples of the RWED using the synthetically generated signals. It is found that the ED is very effective in diminishing the effects of cross terms while retaining most of the properties which are useful for a time-frequency distribution.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

Matching pursuits with time-frequency dictionaries

1993-01-01

Stéphane Mallat , Zhifeng Zhang

The authors introduce an algorithm, called matching pursuit, that decomposes any signal into a linear expansion of waveforms that are selected from a redundant dictionary of functions. These waveforms are … The authors introduce an algorithm, called matching pursuit, that decomposes any signal into a linear expansion of waveforms that are selected from a redundant dictionary of functions. These waveforms are chosen in order to best match the signal structures. Matching pursuits are general procedures to compute adaptive signal representations. With a dictionary of Gabor functions a matching pursuit defines an adaptive time-frequency transform. They derive a signal energy distribution in the time-frequency plane, which does not include interference terms, unlike Wigner and Cohen class distributions. A matching pursuit isolates the signal structures that are coherent with respect to a given dictionary. An application to pattern extraction from noisy signals is described. They compare a matching pursuit decomposition with a signal expansion over an optimized wavepacket orthonormal basis, selected with the algorithm of Coifman and Wickerhauser see (IEEE Trans. Informat. Theory, vol. 38, Mar. 1992).< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

A study of the characteristics of white noise using the empirical mode decomposition method

2004-04-05

Zhaohua Wu , Norden E. Huang

Based on numerical experiments on white noise using the empirical mode decomposition (EMD) method, we find empirically that the EMD is effectively a dyadic filter, the intrinsic mode function (IMF) … Based on numerical experiments on white noise using the empirical mode decomposition (EMD) method, we find empirically that the EMD is effectively a dyadic filter, the intrinsic mode function (IMF) components are all normally distributed, and the Fourier spectra of the IMF components are all identical and cover the same area on a semi–logarithmic period scale. Expanding from these empirical findings, we further deduce that the product of the energy density of IMF and its corresponding averaged period is a constant, and that the energy–density function is chi–squared distributed. Furthermore, we derive the energy–density spread function of the IMF components. Through these results, we establish a method of assigning statistical significance of information content for IMF components from any noisy data. Southern Oscillation Index data are used to illustrate the methodology developed here.

Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data

2015-11-18

Feng Jia , Yaguo Lei , Jing Lin +2 more

An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data

2016-01-19

Yaguo Lei , Feng Jia , Jing Lin +2 more

Intelligent fault diagnosis is a promising tool to deal with mechanical big data due to its ability in rapidly and efficiently processing collected signals and providing accurate diagnosis results. In … Intelligent fault diagnosis is a promising tool to deal with mechanical big data due to its ability in rapidly and efficiently processing collected signals and providing accurate diagnosis results. In traditional intelligent diagnosis methods, however, the features are manually extracted depending on prior knowledge and diagnostic expertise. Such processes take advantage of human ingenuity but are time-consuming and labor-intensive. Inspired by the idea of unsupervised feature learning that uses artificial intelligence techniques to learn features from raw data, a two-stage learning method is proposed for intelligent diagnosis of machines. In the first learning stage of the method, sparse filtering, an unsupervised two-layer neural network, is used to directly learn features from mechanical vibration signals. In the second stage, softmax regression is employed to classify the health conditions based on the learned features. The proposed method is validated by a motor bearing dataset and a locomotive bearing dataset, respectively. The results show that the proposed method obtains fairly high diagnosis accuracies and is superior to the existing methods for the motor bearing dataset. Because of learning features adaptively, the proposed method reduces the need of human labor and makes intelligent fault diagnosis handle big data more easily.

Convolutional Neural Network Based Fault Detection for Rotating Machinery

2016-05-25

Olivier Janssens , Viktor Slavkovikj , Bram Vervisch +5 more

View PDF Chat

Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study

2015-05-11

Wade A. Smith , Robert B. Randall

Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks

2016-06-29

Türker İnce , Serkan Kıranyaz , Levent Eren +2 more

Early detection of the motor faults is essential and artificial neural networks are widely used for this purpose. The typical systems usually encapsulate two distinct blocks: feature extraction and classification. … Early detection of the motor faults is essential and artificial neural networks are widely used for this purpose. The typical systems usually encapsulate two distinct blocks: feature extraction and classification. Such fixed and hand-crafted features may be a suboptimal choice and require a significant computational cost that will prevent their usage for real-time applications. In this paper, we propose a fast and accurate motor condition monitoring and early fault-detection system using 1-D convolutional neural networks that has an inherent adaptive design to fuse the feature extraction and classification phases of the motor fault detection into a single learning body. The proposed approach is directly applicable to the raw data (signal), and, thus, eliminates the need for a separate feature extraction algorithm resulting in more efficient systems in terms of both speed and hardware. Experimental results obtained using real motor data demonstrate the effectiveness of the proposed method for real-time motor condition monitoring.

Condition Monitoring and Fault Diagnosis of Electrical Motors—A Review

2005-12-01

S. Nandi , Hamid A. Toliyat , Xiaodong Li

Recently, research has picked up a fervent pace in the area of fault diagnosis of electrical machines. The manufacturers and users of these drives are now keen to include diagnostic … Recently, research has picked up a fervent pace in the area of fault diagnosis of electrical machines. The manufacturers and users of these drives are now keen to include diagnostic features in the software to improve salability and reliability. Apart from locating specific harmonic components in the line current (popularly known as motor current signature analysis), other signals, such as speed, torque, noise, vibration etc., are also explored for their frequency contents. Sometimes, altogether different techniques, such as thermal measurements, chemical analysis, etc., are also employed to find out the nature and the degree of the fault. In addition, human involvement in the actual fault detection decision making is slowly being replaced by automated tools, such as expert systems, neural networks, fuzzy-logic-based systems; to name a few. It is indeed evident that this area is vast in scope. Hence, keeping in mind the need for future research, a review paper describing different types of faults and the signatures they generate and their diagnostics' schemes will not be entirely out of place. In particular, such a review helps to avoid repetition of past work and gives a bird's eye view to a new researcher in this area.

A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals

2017-02-22

Wei Zhang , Gaoliang Peng , Chuanhao Li +2 more

Intelligent fault diagnosis techniques have replaced time-consuming and unreliable human analysis, increasing the efficiency of fault diagnosis. Deep learning models can improve the accuracy of intelligent fault diagnosis with the … Intelligent fault diagnosis techniques have replaced time-consuming and unreliable human analysis, increasing the efficiency of fault diagnosis. Deep learning models can improve the accuracy of intelligent fault diagnosis with the help of their multilayer nonlinear mapping ability. This paper proposes a novel method named Deep Convolutional Neural Networks with Wide First-layer Kernels (WDCNN). The proposed method uses raw vibration signals as input (data augmentation is used to generate more inputs), and uses the wide kernels in the first convolutional layer for extracting features and suppressing high frequency noise. Small convolutional kernels in the preceding layers are used for multilayer nonlinear mapping. AdaBN is implemented to improve the domain adaptation ability of the model. The proposed model addresses the problem that currently, the accuracy of CNN applied to fault diagnosis is not very high. WDCNN can not only achieve 100% classification accuracy on normal signals, but also outperform the state-of-the-art DNN model which is based on frequency features under different working load and noisy environment conditions.

View PDF Chat

A recurrent neural network based health indicator for remaining useful life prediction of bearings

2017-02-23

Liang Guo , Naipeng Li , Feng Jia +2 more

A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load

2017-08-04

Wei Zhang , Chuanhao Li , Gaoliang Peng +2 more

A New Deep Transfer Learning Based on Sparse Auto-Encoder for Fault Diagnosis

2017-10-04

Long Wen , Liang Gao , Xinyu Li

Fault diagnosis plays an important role in modern industry. With the development of smart manufacturing, the data-driven fault diagnosis becomes hot. However, traditional methods have two shortcomings: 1) their performances … Fault diagnosis plays an important role in modern industry. With the development of smart manufacturing, the data-driven fault diagnosis becomes hot. However, traditional methods have two shortcomings: 1) their performances depend on the good design of handcrafted features of data, but it is difficult to predesign these features and 2) they work well under a general assumption: the training data and testing data should be drawn from the same distribution, but this assumption fails in many engineering applications. Since deep learning (DL) can extract the hierarchical representation features of raw data, and transfer learning provides a good way to perform a learning task on the different but related distribution datasets, deep transfer learning (DTL) has been developed for fault diagnosis. In this paper, a new DTL method is proposed. It uses a three-layer sparse auto-encoder to extract the features of raw data, and applies the maximum mean discrepancy term to minimizing the discrepancy penalty between the features from training data and testing data. The proposed DTL is tested on the famous motor bearing dataset from the Case Western Reserve University. The results show a good improvement, and DTL achieves higher prediction accuracies on most experiments than DL. The prediction accuracy of DTL, which is as high as 99.82%, is better than the results of other algorithms, including deep belief network, sparse filter, artificial neural network, support vector machine and some other traditional methods. What is more, two additional analytical experiments are conducted. The results show that a good unlabeled third dataset may be helpful to DTL, and a good linear relationship between the final prediction accuracies and their standard deviations have been observed.

A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method

2017-11-17

Long Wen , Xinyu Li , Liang Gao +1 more

Fault diagnosis is vital in manufacturing system, since early detections on the emerging problem can save invaluable time and cost. With the development of smart manufacturing, the data-driven fault diagnosis … Fault diagnosis is vital in manufacturing system, since early detections on the emerging problem can save invaluable time and cost. With the development of smart manufacturing, the data-driven fault diagnosis becomes a hot topic. However, the traditional data-driven fault diagnosis methods rely on the features extracted by experts. The feature extraction process is an exhausted work and greatly impacts the final result. Deep learning (DL) provides an effective way to extract the features of raw data automatically. Convolutional neural network (CNN) is an effective DL method. In this study, a new CNN based on LeNet-5 is proposed for fault diagnosis. Through a conversion method converting signals into two-dimensional (2-D) images, the proposed method can extract the features of the converted 2-D images and eliminate the effect of handcrafted features. The proposed method which is tested on three famous datasets, including motor bearing dataset, self-priming centrifugal pump dataset, and axial piston hydraulic pump dataset, has achieved prediction accuracy of 99.79%, 99.481%, and 100%, respectively. The results have been compared with other DL and traditional methods, including adaptive deep CNN, sparse filter, deep belief network, and support vector machine. The comparisons show that the proposed CNN-based data-driven fault diagnosis method has achieved significant improvements.

Remaining useful life estimation in prognostics using deep convolution neural networks

2017-12-02

Xiang Li , Qian Ding , Jian‐Qiao Sun

View PDF Chat

Machinery health prognostics: A systematic review from data acquisition to RUL prediction

2017-12-01

Yaguo Lei , Naipeng Li , Liang Guo +3 more

Artificial intelligence for fault diagnosis of rotating machinery: A review

2018-02-15

Ruonan Liu , Boyuan Yang , Enrico Zio +1 more

Highly Accurate Machine Fault Diagnosis Using Deep Transfer Learning

2018-08-10

Siyu Shao , Stephen McAleer , Ruqiang Yan +1 more

We develop a novel deep learning framework to achieve highly accurate machine fault diagnosis using transfer learning to enable and accelerate the training of deep neural network. Compared with existing … We develop a novel deep learning framework to achieve highly accurate machine fault diagnosis using transfer learning to enable and accelerate the training of deep neural network. Compared with existing methods, the proposed method is faster to train and more accurate. First, original sensor data are converted to images by conducting a Wavelet transformation to obtain time-frequency distributions. Next, a pretrained network is used to extract lower level features. The labeled time-frequency images are then used to fine-tune the higher levels of the neural network architecture. This paper creates a machine fault diagnosis pipeline and experiments are carried out to verify the effectiveness and generalization of the pipeline on three main mechanical datasets including induction motors, gearboxes, and bearings with sizes of 6000, 9000, and 5000 time series samples, respectively. We achieve state-of-the-art results on each dataset, with most datasets showing test accuracy near 100%, and in the gearbox dataset, we achieve significant improvement from 94.8% to 99.64%. We created a repository including these datasets located at mlmechanics.ics.uci.edu.

Deep Convolutional Transfer Learning Network: A New Method for Intelligent Fault Diagnosis of Machines With Unlabeled Data

2018-10-26

Liang Guo , Yaguo Lei , Saibo Xing +2 more

The success of intelligent fault diagnosis of machines relies on the following two conditions: 1) labeled data with fault information are available; and 2) the training and testing data are … The success of intelligent fault diagnosis of machines relies on the following two conditions: 1) labeled data with fault information are available; and 2) the training and testing data are drawn from the same probability distribution. However, for some machines, it is difficult to obtain massive labeled data. Moreover, even though labeled data can be obtained from some machines, the intelligent fault diagnosis method trained with such labeled data possibly fails in classifying unlabeled data acquired from the other machines due to data distribution discrepancy. These problems limit the successful applications of intelligent fault diagnosis of machines with unlabeled data. As a potential tool, transfer learning adapts a model trained in a source domain to its application in a target domain. Based on the transfer learning, we propose a new intelligent method named deep convolutional transfer learning network (DCTLN). A DCTLN consists of two modules: condition recognition and domain adaptation. The condition recognition module is constructed by a one-dimensional (1-D) convolutional neural network (CNN) to automatically learn features and recognize health conditions of machines. The domain adaptation module facilitates the 1-D CNN to learn domain-invariant features by maximizing domain recognition errors and minimizing the probability distribution distance. The effectiveness of the proposed method is verified using six transfer fault diagnosis experiments.

A Hybrid Prognostics Approach for Estimating Remaining Useful Life of Rolling Element Bearings

2018-12-14

Biao Wang , Yaguo Lei , Naipeng Li +1 more

Remaining useful life (RUL) prediction of rolling element bearings plays a pivotal role in reducing costly unplanned maintenance and increasing the reliability, availability, and safety of machines. This paper proposes … Remaining useful life (RUL) prediction of rolling element bearings plays a pivotal role in reducing costly unplanned maintenance and increasing the reliability, availability, and safety of machines. This paper proposes a hybrid prognostics approach for RUL prediction of rolling element bearings. First, degradation data of bearings are sparsely represented using relevance vector machine regressions with different kernel parameters. Then, exponential degradation models coupled with the Fréchet distance are employed to estimate the RUL adaptively. The proposed approach is evaluated using the vibration data from accelerated degradation tests of rolling element bearings and the public PRONOSTIA bearing datasets. Experimental results demonstrate the effectiveness of the proposed approach in improving the accuracy and convergence of RUL prediction of rolling element bearings.

A systematic literature review of machine learning methods applied to predictive maintenance

2019-09-05

Thyago Peres Carvalho , Fabrízzio Soares , Roberto Oliveira Vita +3 more

Deep Residual Shrinkage Networks for Fault Diagnosis

2019-09-27

Minghang Zhao , Shisheng Zhong , Xuyun Fu +2 more

This article develops new deep learning methods, namely, deep residual shrinkage networks, to improve the feature learning ability from highly noised vibration signals and achieve a high fault diagnosing accuracy. … This article develops new deep learning methods, namely, deep residual shrinkage networks, to improve the feature learning ability from highly noised vibration signals and achieve a high fault diagnosing accuracy. Soft thresholding is inserted as nonlinear transformation layers into the deep architectures to eliminate unimportant features. Moreover, considering that it is generally challenging to set proper values for the thresholds, the developed deep residual shrinkage networks integrate a few specialized neural networks as trainable modules to automatically determine the thresholds, so that professional expertise on signal processing is not required. The efficacy of the developed methods is validated through experiments with various types of noise.

Applications of machine learning to machine fault diagnosis: A review and roadmap

2020-01-05

Yaguo Lei , Bin Yang , Xinwei Jiang +3 more

View PDF Chat

Anti-shock Noise Intelligent Fault Identification for Wind Turbines Based on Feature-Embedded Deep Learning

2025-06-25

Jian Dang , Xiaoqin Cheng , Haolin Yin +3 more | Journal of Vibration Engineering & Technologies

AFMCNN: A convolutional fusion diagnostic framework based on global distance matrix for train transmission system

2025-06-25

Zeyu Jiang , Tianzhuang Yu , Yongchao Zhang +3 more | Journal of Vibration and Control

Sensor technology and continuously improved convolutional neural networks (CNN) are essential tools for intelligent diagnosis in train transmission systems. Numerous studies have focused on leveraging multi-sensor fusion and two-dimensional CNN … Sensor technology and continuously improved convolutional neural networks (CNN) are essential tools for intelligent diagnosis in train transmission systems. Numerous studies have focused on leveraging multi-sensor fusion and two-dimensional CNN to address diagnostic problems. However, research challenges remain to be addressed, such as expertise dependence and inadequate mapping when performing image coding. Additionally, many diagnostic frameworks still rely on conventional convolutional structures, constraining the extraction of features. Furthermore, the existing fusion approaches have seldom considered the issue of unbalanced distribution of diagnostic information among signals from different sources in the transmission system. To fill these research gaps, this paper proposes a global distance matrix (GDM) for image coding and an adaptive fusion multiscale CNN (AFMCNN) for multisensor fusion diagnosis in train transmission systems that can adaptively assign weights to different sensor information. First, the proposed GDM reflects the interrelationships of the time series data while preserving the temporal correlation. Then, a global attention mechanism is designed to improve the network’s attention to the global relationships of the data, considering the characteristics of the GDM. Furthermore, a novel multiscale convolution block is introduced to extract larger spatial information at different scales. Lastly, an adaptive fusion module is proposed to adaptively assign learnable weights for data from different sources at the channel dimension. The weights are visualized to increase the interpretability of the module. The excellent performance and generalization of the proposed methods are verified using bearing and gearbox datasets from the power transmission system.

Interpretable and robust fault diagnosis of rotating machinery in noisy environments via improved high-order spatial interactions network

2025-06-25

Bin Wang , Pengfei Liang , Ying Li +2 more | Engineering Applications of Artificial Intelligence

A novel method for variable-speed mechanical fault diagnosis using sparse threshold graph and adaptive loss weighting

2025-06-25

Haidong Shao , Yuan Gao , Hongyi Qu +2 more | Advanced Engineering Informatics

Machine Learning-Based Predictive Maintenance at Smart Ports Using IoT Sensor Data

2025-06-24

Sheraz Aslam , Alejandro Leonardo García Navarro , Andreas C. Aristotelous +7 more | Sensors

Maritime transportation plays a critical role in global containerized cargo logistics, with seaports serving as key nodes in this system. Ports are responsible for container loading and unloading, along with … Maritime transportation plays a critical role in global containerized cargo logistics, with seaports serving as key nodes in this system. Ports are responsible for container loading and unloading, along with inspection, storage, and timely delivery to the destination, all of which heavily depend on the performance of the container handling equipment (CHE). Inefficient maintenance strategies and unplanned maintenance of the port equipment can lead to operational disruptions, including unexpected delays and long waiting times in the supply chain. Therefore, the maritime industry must adopt intelligent maintenance strategies at the port to optimize operational efficiency and resource utilization. Towards this end, this study presents a machine learning (ML)-based approach for predicting faults in CHE to improve equipment reliability and overall port performance. Firstly, a statistical model was developed to check the status and health of the hydraulic system, as it is crucial for the operation of the machines. Then, several ML models were developed, including artificial neural networks (ANNs), decision trees (DTs), random forest (RF), Extreme Gradient Boosting (XGBoost), and Gaussian Naive Bayes (GNB) to predict inverter over-temperature faults due to fan failures, clogged filters, and other related issues. From the tested models, the ANNs achieved the highest performance in predicting the specific faults with a 98.7% accuracy and 98.0% F1-score.

Modeling and Simulation of Internal Incipient Faults in Electrical Transformers Using a Bond Graph Approach

2025-06-24

Arthur Cleary-Balderas , Gilberto González-A , Gerardo Ayala +1 more | Energies

Power transformers are a key piece of equipment located between the points of supply and consumption of electrical energy. Due to their continuous exposure to the environment, they may be … Power transformers are a key piece of equipment located between the points of supply and consumption of electrical energy. Due to their continuous exposure to the environment, they may be subject to failure. Thus, the modeling of transformers subject to incipient faults using a bond graph approach is presented in this study. In particular, incipient faults in the primary and secondary windings with respect to ground and a turn-to-turn fault in the primary winding are modeled. In order to develop a mathematical model capturing the incipient faults in transformers including magnetic saturation effects, a junction structure for the system applied to the bond graph model is proposed. The steady-state responses of the faulted transformer models using a bond graph approach are presented, leading to the proposal of a method for fault analysis in transformers with DC supply sources. Simulation results for the transformers with the different faults are presented, validating the results obtained according to expressions derived from the bond graph models.

Metric-guided graph contrastive learning: An unsupervised approach for few-shot gearbox fault diagnosis

2025-06-24

Peng Chen , Jia Gao , Ruijin Zhang +4 more | Measurement Science and Technology

Abstract Planetary gearboxes are critical mechanical components widely deployed in industrial applications such as wind turbines, helicopters, and hybrid vehicles, where their reliable operation directly impacts system performance and safety. … Abstract Planetary gearboxes are critical mechanical components widely deployed in industrial applications such as wind turbines, helicopters, and hybrid vehicles, where their reliable operation directly impacts system performance and safety. Traditional fault diagnosis approaches using Graph Neural Networks (GNNs) and Graph Contrastive Learning (GCL) face significant challenges, including prohibitive costs in fault sample acquisition, ineffective feature extraction from limited data, and semantic distortions in node embedding space that compromise diagnostic accuracy. Furthermore, existing methods struggle with insufficient supervision for complex fault classification and show vulnerability to distribution shifts in new environments. To address these limitations, this research proposes the Metric-guided Graph Contrastive Learning (MGCL) framework, featuring three innovative components: a feature-decoupled pre-training mechanism with graph data augmentation, a sophisticated cosine-Euclidean hybrid distance metric, and a two-stage training paradigm combining unsupervised pre-training with weakly supervised fine-tuning. MGCL significantly advances the field by effectively handling sample scarcity and annotation limitations while enhancing model robustness against domain shifts in real-world industrial applications, ultimately providing a more reliable and practical solution for industrial fault diagnosis.

A bearing fault diagnosis model with enhanced feature extraction based on the Kolmogorov–Arnold representation Theorem and an attention mechanism

2025-06-24

Hao Jin , Xueyi Li , Jun Yu +2 more | Applied Acoustics

Fault diagnosis of wind turbine bearings based on improved dung beetle optimizer optimized LSTM

2025-06-24

yucen yuan , Wei Wei | Engineering Research Express

Abstract Rolling bearing fault diagnosis of wind turbines is an important part to ensure the safe operation of wind turbines and reduce the operation and maintenance cost, but since the … Abstract Rolling bearing fault diagnosis of wind turbines is an important part to ensure the safe operation of wind turbines and reduce the operation and maintenance cost, but since the rolling bearing fault signals of wind turbines exhibit strong nonlinearity and non-stationarity, coupled with the influence of the surrounding harsh environment, the shock characteristics associated with bearing faults are often masked by the elevated noise level, which leads to feature extraction becoming difficult. In order to overcome this limitation, an improved dung beetle optimizer (IDBO) is proposed in this paper to optimize Long Short-Term Memory (LSTM) for wind turbine bearing fault diagnosis. Firstly, the Levy flight strategy and T-distribution perturbation strategy are integrated on the basis of the traditional dung beetle algorithm to strengthen the convergence accuracy and local optimization ability; then the IDBO algorithm is combined with the Long Short-Term Memory network to construct the IDBO-LSTM fault diagnosis model, which has the advantage of smaller parameter compared with the traditional&#xD;LSTM so that the model maintains the accuracy of the traditional temporal feature extraction methods while reduces the overall parametric and arithmetic volume of the module; finally, the open dataset of bearings from Case Western Reserve University is used as an example to verify that the fault diagnosis accuracy of the model can reach 98.3%. The experimental results show that the IDBO-LSTM algorithm can accurately recognize fault features even in the presence of cyclic interference and its accuracy is better than that of other models, which can effectively improve the fault diagnosis accuracy of rolling bearings in wind turbines.&#xD;

A study on degradation prediction modeling method for mechanical rotating components based on multi-modal data and improved structured state-space sequence model

2025-06-24

Z. John Zhang , Yaohua Deng , Xiali Liu | Journal of Intelligent Manufacturing

Broken Rotor Bar Fault Detection in Induction Motors Using Motor Current Signature Analysis (MCSA)

2025-06-24

Chenga Dorji , Jamyang Choda | Journal of Applied Engineering Technology and Management

Induction motors are commonly used in various industrial applications due to their reliability and robustness. However, they are susceptible to faults that can compromise their performance and efficiency. One of … Induction motors are commonly used in various industrial applications due to their reliability and robustness. However, they are susceptible to faults that can compromise their performance and efficiency. One of the common faults encountered in induction motors is Broken Rotor Bars, which can lead to rotor imbalance, increase vibration, and reduce the efficiency of the motor. Detecting and diagnosing this fault is critical to ensure the proper operation of the motors for industrial purposes and prevent costly downtime. This paper investigates the comparative current signature analysis of Broken Rotor Bar (BRB) fault detection in induction motors using different windowing functions. The study explores the effectiveness of various windowing functions including Hanning, Hamming, Blackman, and Flattop, in enhancing the analysis of stator current signals for fault detection purposes. The analysis is conducted using Fast Fourier Transform (FFT) techniques. The findings provide insights into the impact of windowing functions on fault detection performance and suitability for motor maintenance applications, specifically in detecting faults such as broken rotor bar faults in induction motors.

A temporal cross-contrastive self-supervised learning framework for high-speed train bearing fault diagnosis: addressing limited labeling and speed variability

2025-06-24

Yuyan Li , Tiantian Wang , Jingsong Xie +4 more | Engineering Applications of Artificial Intelligence

Rolling Bearing Early Fault Detection Method Based on Feature Clustering Fusion Degradation Index

2025-06-23

Xiangyang Xu , Haotian Wang , Xihui Liang +2 more | Chinese Journal of Mechanical Engineering

Abstract The research on rolling bearing early fault detection is mainly focused on degradation index extraction and adaptive setting of alarm threshold. The mainstream methods are to extract degradation indicators … Abstract The research on rolling bearing early fault detection is mainly focused on degradation index extraction and adaptive setting of alarm threshold. The mainstream methods are to extract degradation indicators based on adaptive features and set adaptive alarm thresholds based on the Shewhart control chart. However, the adaptive feature extraction method does not consider the correlation between features, and the Shewhart control chart is not sensitive to small fluctuations caused by early faults. In this study, a rolling bearing early fault detection method based on a feature clustering fusion degradation index is proposed. The multidomain statistical features are extracted to form the initial feature set, and the improved hierarchical clustering algorithm is combined with the feature evaluation index to select features to form a preferred feature subset, to ensure the richness of index information and reduce redundancy. After the construction of the degradation index, to suppress the interference caused by nonstationary and abnormal shocks in early fault detection, the accurate evaluation method and anomaly determination strategy of control chart parameters are studied, and an improved exponential weighted move average control chart is designed to monitor the degradation index. The effectiveness and superiority of the proposed method are verified by public data sets. This research provides a rolling bearing early fault detection method, which can provide comprehensive degradation indicators, eliminate interference caused by random anomalies and running in periods, and achieve an accurate detection of early bearing failures.

Transformer Fault Diagnosis Based on Knowledge Distillation and Residual Convolutional Neural Networks

2025-06-23

Haikun Shang , Yanlei Wei , Shen Zhang | Entropy

Dissolved Gas Analysis (DGA) of transformer oil is a critical technique for transformer fault diagnosis that involves analyzing the concentration of gases to detect potential transformer faults in a timely … Dissolved Gas Analysis (DGA) of transformer oil is a critical technique for transformer fault diagnosis that involves analyzing the concentration of gases to detect potential transformer faults in a timely manner. Given the issues of large model parameters and high computational resource demands in transformer DGA diagnostics, this study proposes a lightweight convolutional neural network (CNN) model for improving gas ratio methods, combining Knowledge Distillation (KD) and recursive plots. The approach begins by extracting features from DGA data using the ratio method and Multiscale sample entropy (MSE), then reconstructs the state space of the feature data using recursive plots to generate interpretable two-dimensional image features. A deep feature extraction process is performed using the ResNet50 model, integrated with the Convolutional Block Attention Module (CBAM). Subsequently, the Sparrow Optimization Algorithm (SSA) is applied to optimize the hyperparameters of the ResNet50 model, which is trained on DGA data as the teacher model. Finally, a dual-path distillation mechanism is introduced to transfer the efficient features and knowledge from the teacher model to the student model, MobileNetV3-Large. The experimental results show that the distilled model reduces memory usage by 83.5% and computation time by 73.2%, significantly lowering computational complexity while achieving favorable performance across various evaluation metrics. This provides a novel technical solution for the improvement of gas ratio methods.

Reconstructing In-Cylinder Pressure from Head Vibrations with Signal-to-Signal Deep Learning Architectures

2025-06-23

Mateusz Tabaszewski , Grzegorz M. Szymański , Maciej Tabaszewski +1 more | Applied Sciences

Considering that piston internal combustion engines will remain essential converters of chemical energy into mechanical energy for an extended period, providing optimal diagnostic tools for their operation is imperative. Mechanical … Considering that piston internal combustion engines will remain essential converters of chemical energy into mechanical energy for an extended period, providing optimal diagnostic tools for their operation is imperative. Mechanical vibrations generated during machine operation constitute one of the most valuable sources of information about their technical condition. Their primary advantage lies in conveying diagnostic data with minimal time delay. This article presents a novel approach to vibroacoustic diagnostics of the combustion process in internal combustion piston engines. It leverages vibration signals carrying information about the pressure in the engine cylinder during fuel–air mixture combustion. In the proposed method, cylinder pressure information is reconstructed from vibration signals recorded on the cylinder head of the internal combustion engine. This method of signal-to-signal processing uses deep artificial neural network (ANN) models for signal reconstruction, providing an extensive exploration of the abilities of the presented models in the reconstruction of the pressure measurements. Furthermore, a novel two-network model, utilizing a U-net architecture with a dedicated smoothing network (SmN), allows for producing signals with minimal noise and outperforms other commonly used signal-to-signal architectures explored in this paper. To test the proposed methods, the study was limited to a single-cylinder engine, which presents certain constraints. However, this initial approach may serve as an inspiration for researchers to extend its application to multi-cylinder engines.

A Spatio-Temporal Joint Diagnosis Framework for Bearing Faults via Graph Convolution and Attention-Enhanced Bidirectional Gated Networks

2025-06-23

Zhiguo Xiao , Xiaofeng Cao , Huihui Hao +3 more | Sensors

In recent years, Academia and industry have conducted extensive and in-depth research on bearing-fault-diagnosis technology. However, the current modeling of time–space coupling characteristics in rolling bearing fault diagnosis remains inadequate, … In recent years, Academia and industry have conducted extensive and in-depth research on bearing-fault-diagnosis technology. However, the current modeling of time–space coupling characteristics in rolling bearing fault diagnosis remains inadequate, and the integration of multi-modal correlations requires further improvement. To address these challenges, this paper proposes a joint diagnosis framework integrating graph convolutional networks (GCNs) with attention-enhanced bidirectional gated recurrent units (BiGRUs). The proposed framework first constructs an improved K-nearest neighbor-based spatio-temporal graph to enhance multidimensional spatial–temporal feature modeling through GCN-based spatial feature extraction. Subsequently, we design an end-to-end spatio-temporal joint learning architecture by implementing a global attention-enhanced BiGRU temporal modeling module. This architecture achieves the deep fusion of spatio-temporal features through the graph-structural transformation of vibration signals and a feature cascading strategy, thereby improving overall model performance. The experiment demonstrated a classification accuracy of 97.08% on three public datasets including CWRU, verifying that this method decouples bearing signals through dynamic spatial topological modeling, effectively combines multi-scale spatiotemporal features for representation, and accurately captures the impact characteristics of bearing faults.

Few-shot fault diagnosis of rail transit switch machine based on sparse convolution capsule relation network

2025-06-23

Zhiqiang He , Zhenpeng Lao | Nondestructive Testing And Evaluation

Research on feature extraction and intelligent diagnosis method of reciprocating compressor bearing clearance fault

2025-06-23

Feng Yan | Journal of Engineering and Applied Science

Abstract This study presents an innovative approach to fault diagnosis in sliding bearings, targeting the challenges posed by weak fault signals and heavy noise interference. The proposed method employs a … Abstract This study presents an innovative approach to fault diagnosis in sliding bearings, targeting the challenges posed by weak fault signals and heavy noise interference. The proposed method employs a generalized multi-scale permutation entropy (GMPE) algorithm, which utilizes a multi-scale mean coarse-graining strategy to effectively capture dynamic transitions in signals. To overcome the shortcomings of traditional binary tree support vector machine (BTSVM) classifiers—such as slow convergence and error accumulation due to early misclassifications—an enhanced BTSVM model is introduced to reduce error propagation. The effectiveness of the method is validated on both reciprocating compressor sliding bearings and automotive rolling bearings, achieving a fault diagnosis accuracy of over 99%. These results highlight a significant advancement in mechanical fault detection and demonstrate the strong potential of combining GMPE with an improved BTSVM for accurate fault diagnosis in complex machinery.

Rolling Bearing Fault Diagnosis via Temporal-Graph Convolutional Fusion

2025-06-23

Fan Li , Yunfeng Li , Dongfeng Wang | Sensors

To address the challenge of incomplete fault feature extraction in rolling bearing fault diagnosis under small-sample conditions, this paper proposes a Temporal-Graph Convolutional Fusion Network (T-GCFN). The method enhances diagnostic … To address the challenge of incomplete fault feature extraction in rolling bearing fault diagnosis under small-sample conditions, this paper proposes a Temporal-Graph Convolutional Fusion Network (T-GCFN). The method enhances diagnostic robustness through collaborative extraction and dynamic fusion of features from time-domain and frequency-domain branches. First, Variational Mode Decomposition (VMD) was employed to extract time-domain Intrinsic Mode Functions (IMFs). These were then input into a Temporal Convolutional Network (TCN) to capture multi-scale temporal dependencies. Simultaneously, frequency-domain features obtained via Fast Fourier Transform (FFT) were used to construct a K-Nearest Neighbors (KNN) graph, which was processed by a Graph Convolutional Network (GCN) to identify spatial correlations. Subsequently, a channel attention fusion layer was designed. This layer utilized global max pooling and average pooling to compress spatio-temporal features. A shared Multi-Layer Perceptron (MLP) then established inter-channel dependencies to generate attention weights, enhancing critical features for more complete fault information extraction. Finally, a SoftMax classifier performed end-to-end fault recognition. Experiments demonstrated that the proposed method significantly improved fault recognition accuracy under small-sample scenarios. These results validate the strong adaptability of the T-GCFN mechanism.

Bearing fault diagnosis method based on multi-scale residual and multi task depthwise separable network

2025-06-23

Yang Chengfei , Xing Shao , Jun Gao +2 more | Signal Image and Video Processing

A machine learning-based interpretable fault diagnosis method for rolling bearings under unbalanced samples

2025-06-23

Yingxue Chen , Guanxiang Feng , Huatao Chen +2 more | Engineering Applications of Artificial Intelligence

WOA-based Parameter Adaptive VMD Combined with Wavelet Thresholding for Bearing Fault Feature Extraction

2025-06-22

Xiaoqiang Wang , Linfeng Deng , Zhao Cheng +1 more | Journal of Nondestructive Evaluation

Mitigating Multicollinearity in Induction Motors Fault Diagnosis Through Hierarchical Clustering-Based Feature Selection

2025-06-21

Bassam A. Hemade , Sabbah Ataya , Attia A. El‐Fergany +1 more | Applied Sciences

This paper addresses the challenge of multicollinearity among input features in induction motor (IM) fault diagnosis, which often degrades the performance and reliability of machine learning classifiers. A novel feature … This paper addresses the challenge of multicollinearity among input features in induction motor (IM) fault diagnosis, which often degrades the performance and reliability of machine learning classifiers. A novel feature selection approach based on agglomerative hierarchical clustering (AHC) is proposed to mitigate feature redundancy and enhance model generalization. The method is applied using only voltage and current signals, excluding vibration or temperature data, to improve noise immunity and facilitate practical deployment. Experimental validation demonstrates the effectiveness of the AHC framework across multiple classifiers, particularly Support Vector Classifiers (SVCs) and Artificial Neural Networks (ANNs). Compared to random forest-based feature selection, AHC yields a 2% increase in accuracy for SVCs and a 0.6% improvement for ANNs. Moreover, both classifiers exhibit enhanced balance across fault categories, with macro-average recall and F1-score improvements of approximately 1.5%. These findings highlight the ability of AHC to handle complex fault scenarios, which offer a more efficient and generalized fault diagnosis model compared to ensemble methods-based feature selection.

Bearing Fault Diagnosis Using Domain Adaptation Approach for Acoustic Data

2025-06-21

Aamir Khowaja , Jawaid Daudpoto , Dileep Kumar +1 more | Transactions of the Canadian Society for Mechanical Engineering

Bearing failures are one of the most occurring problems in industrial machines. Thus, bearings require improved fault detection methods. In this direction, data-driven approaches for machine fault diagnosis have proven … Bearing failures are one of the most occurring problems in industrial machines. Thus, bearings require improved fault detection methods. In this direction, data-driven approaches for machine fault diagnosis have proven to be more effective than the model-based approaches. However, conventional data-driven methods in domain shift conditions are unable to yield optimal performance. Bearing faults usually occur under different operational conditions. Related to this, acoustic emissions as a non-invasive can capture valuable information about machine health conditions and it is considered as an effective alternative to vibration and current-based methods. Moreover, the application of acoustic data in the domain-shift scenario has not been much explored. In this research, we implement a transfer learning approach for bearing fault diagnosis using machine acoustic data while considering the domain shift problem. Three deep learning models including 1DCNN, 1DCNN-LSTM, and a Residual network are developed and investigated in this research. The pre-trained models are implemented based on the DCASE dataset. The pre-trained models are established using the Air Compressor dataset. By using transfer learning, the feature parameters obtained during model development on the Air compressor dataset are utilized to fine-tune the model on the DCASE dataset. The results demonstrate that the model accuracy through the proposed approach is improved to 89.7% for the target domain. The hybrid model 1DCNN-LSTM demonstrated the best results than the other two algorithms.

Bearing Fault Diagnosis Based on Time–Frequency Dual Domains and Feature Fusion of ResNet-CACNN-BiGRU-SDPA

2025-06-21

Jarula Yasenjiang , Yingjun Zhao , Yang Xiao +3 more | Sensors

As the most basic mechanical components, bearing troubleshooting is essential to ensure the safe and reliable operation of rotating machinery. Bearing fault diagnosis is challenging due to the scarcity of … As the most basic mechanical components, bearing troubleshooting is essential to ensure the safe and reliable operation of rotating machinery. Bearing fault diagnosis is challenging due to the scarcity of bearing fault diagnosis samples and the susceptibility of fault signals to external noise. To address these issues, a ResNet-CACNN-BiGRU-SDPA bearing fault diagnosis method based on time–frequency bi-domain and feature fusion is proposed. First, the model takes the augmented time-domain signals as inputs and reconstructs them into frequency-domain signals using FFT, which gives the signals a bi-directional time–frequency domain receptive field. Second, the long sequence time-domain signal is processed by a ResNet residual block structure, and a CACNN method is proposed to realize local feature extraction of the frequency-domain signal. Then, the extracted time–frequency domain long sequence features are fed into a two-layer BiGRU for bidirectional deep global feature mining. Finally, the long-range feature dependencies are dynamically captured by SDPA, while the global dual-domain features are spliced and passed into Softmax to obtain the model output. In order to verify the model performance, experiments were carried out on the CWRU and JNU bearing datasets, and the results showed that the method had high accuracy under both small sample size and noise perturbation conditions, which verified the model’s good fault-feature-learning capability and noise immunity performance.

AI driven fault diagnosis approach for stator turn to turn faults in induction motors

2025-06-20

Tamer A. Kawady , Wagdy M. Khater , Hagar G Abu-Faty +2 more | Scientific Reports

Abstract Induction motors (IMs) are vital in industrial applications. Although all motor faults can disrupt its operation significantly, stator turn to turn faults (ITFs) are the most challenging one due … Abstract Induction motors (IMs) are vital in industrial applications. Although all motor faults can disrupt its operation significantly, stator turn to turn faults (ITFs) are the most challenging one due to their detection difficulties. This paper introduces an AI-based approach to detect ITFs and assess their severity. A simulation based on an accurate mathematical model of the IM under ITFs is employed to generate the training data. Recognizing that ITFs directly affect the motor’s current balance, complex current unbalance coefficient is identified and used as the key feature for detecting ITFs. Since unbalanced supply voltage (USV) can also disrupt current balance, the AI models are trained to account for USV by incorporating complex voltage unbalance coefficient that helps to distinguish between ITF-induced and voltage-induced imbalances. After feature extraction, the AI models are trained and validated with simulation data. The approach’s effectiveness is further tested using an experimental setup, where measurements from motors under various fault conditions, including USV scenarios, are considered. The results indicate that the gradient boosting model outperforms other ML models in detecting ITFs in IMs and assessing their severity. In the pursuit of achieving highest possible performance, DNN is tested and compared with ML models. The study reveals that DNN demonstrates superior performance in all tested scenarios including USV making DNN the top performer that to be used in the proposed approach. The proposed AI-based approach based on DNN offers high accuracy in fault detection and can effectively distinguish between ITFs and USV-induced anomalies, maintaining low estimation errors and robust performance across different operational conditions.

Domain knowledge guided pseudo-label generation framework for semi-supervised domain generalization fault diagnosis

2025-06-20

Jiacheng Wei , Qibin Wang , Guowei Zhang +2 more | Advanced Engineering Informatics

Lightweight bearing fault diagnosis network based on acoustic signal

2025-06-20

Xianguo Li , F Wang , Yinglong Chen +2 more | Measurement Science and Technology

Abstract Bearings are an essential part of rotating machinery, but they frequently fail, particularly in situations requiring high-strength load bearing and fast rotation speed. This research suggests a unique strategy … Abstract Bearings are an essential part of rotating machinery, but they frequently fail, particularly in situations requiring high-strength load bearing and fast rotation speed. This research suggests a unique strategy based on acoustic signals to solve the issues of low accuracy and limited resilience in the current bearing failure detection methods. A lightweight fault diagnosis network, MS-GhostNet V3, is designed to enhance the performance and efficiency of bearing fault detection. Firstly, the acoustic signals produced by rotating machinery are collected using a linear microphone array, capturing the spatial distribution and phase characteristics of the acoustic signal. To improve fault characteristic expressiveness, the time-frequency domain feature map of the acoustic signal is obtained using the short-time Fourier transform. Then the MS-GhostNet V3 network is used to realize bearing fault diagnosis. MS-GhostNet V3 is composed of multi-scale convolution fusion module, ghost bottleneck module and classifier. To obtain multi-scale information, the multi-scale convolution parallel structure creates the multi-scale convolution fusion module. The ghost bottleneck module, integrating the ghost module with the spatial and channel synergistic attention module, facilitates a more comprehensive representation of fault characteristics across both spatial and channel dimensions. Consequently, this enhances defect identification precision. According to experimental results, the suggested approach yields accuracies of 96.19% and 96.88% on both private and publicly available datasets. These outcomes satisfy the requirements for real-time defect detection and lightweight operation. And compared to classical methods, it exhibits superior fault diagnosis performance, with enhanced accuracy and robustness under noise interference. The code is available at: https://github.com/xgli411/MS-GhostNet-V3.&#xD;

LSFConvformer: A lightweight method for mechanical fault diagnosis under small samples and variable speeds with time-frequency fusion

2025-06-20

Haidong Shao , Yanzuo Lai , Haoran Liu +2 more | Mechanical Systems and Signal Processing

Local Entropy Optimization–Adaptive Demodulation Reassignment Transform for Advanced Analysis of Non-stationary Mechanical Signals

2025-06-20

Y. L. Niu , Zhongchao Liang , Hengshan Wu +3 more | Entropy

This research proposes a new method for time–frequency analysis, termed the Local Entropy Optimization–Adaptive Demodulation Reassignment Transform (LEOADRT), which is specifically designed to efficiently analyze complex, non-stationary mechanical vibration signals … This research proposes a new method for time–frequency analysis, termed the Local Entropy Optimization–Adaptive Demodulation Reassignment Transform (LEOADRT), which is specifically designed to efficiently analyze complex, non-stationary mechanical vibration signals that exhibit multiple instantaneous frequencies or where the instantaneous frequency ridges are in close proximity to each other. The method introduces a demodulation term to account for the signal’s dynamic behavior over time, converting each component into a stationary signal. Based on the local optimal theory of Rényi entropy, the demodulation parameters are precisely determined to optimize the time–frequency analysis. Then, the energy redistribution of the ridges already generated in the time–frequency map is performed using the maximum local energy criterion, significantly improving time–frequency resolution. Experimental results demonstrate that the performance of the LEOADRT algorithm is superior to existing methods such as SBCT, EMCT, VSLCT, and GLCT, especially in processing complex non-stationary signals with non-proportionality and closely spaced frequency intervals. This method provides strong support for mechanical fault diagnosis, condition monitoring, and predictive maintenance, making it particularly suitable for real-time analysis of multi-component and cross-frequency signals.

Enhancing Power Converter Reliability Through a Logistic Regression-Based Non-Invasive Fault Diagnosis Technique

2025-06-20

Acácio M. R. Amaral | Applied Sciences

Sustainability can be achieved through the widespread adoption of electrification across multiple sectors of activity, which would thereby enable increased operational efficiency and reduce the environmental impact. The attainment of … Sustainability can be achieved through the widespread adoption of electrification across multiple sectors of activity, which would thereby enable increased operational efficiency and reduce the environmental impact. The attainment of this purpose relies on electrical circuits that convert electrical energy from renewable power plants into forms that are compatible with the specific requirements of the load. Failure of the aforementioned circuits, denominated as power converters, can lead to financial losses resulting from unexpected shutdowns and, in critical systems, can pose significant risks to human life. This article focuses on the topic of fault diagnosis in power converters. Some of the most vulnerable components of these converters are the capacitors used in the DC-link, whose failure evolves gradually. When the capacitor internal resistance (ESR) or the capacitor capacitance (C) exceeds a certain threshold value, it is advisable to propose a system shutdown, as soon as possible, to replace the capacitor. The solution presented in this article combines signal processing techniques (SPTs) with a machine learning (ML) algorithm to determine the optimal time for capacitor replacement. The ML algorithm employed herein was a logistic regression (LR) algorithm which classified the capacitor into one of two states: normal operation (0) or failure (1). To train and evaluate the LR model, two different datasets were created using various electrical quantities that can be measured non-invasively. The model demonstrated excellent performance, achieving an accuracy, precision, recall, and F1 score above 0.99.

Remaining useful life prediction of steer-by-wire system with intermittent faults and imperfect preventive maintenance

2025-06-20

Ming Yu , Qi Cheng , Rui Cheng +1 more | Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering

This paper develops a remaining useful life (RUL) prediction method for the steer-by-wire (SBW) system in the presence of intermittent faults and imperfect preventive maintenance (IPM). To extract the features … This paper develops a remaining useful life (RUL) prediction method for the steer-by-wire (SBW) system in the presence of intermittent faults and imperfect preventive maintenance (IPM). To extract the features of intermittent faults, the concept of variable-size window (VW) is proposed, by which the degradation properties of intermittent faults can be comprehensively reflected. Since the IPM is a common practice to improve the system health condition and the operation condition of the SBW system is variable, the operation condition dependent compound degradation models incorporating the IPM are developed. In these models, the piecewise functions divided by the VW subjected to IPM are proposed to capture the degradation behaviors of the extracted features, by which the varying degradation coefficients and the varying IPM effects can be accommodated. To aid the RUL prediction of intermittently faulty component, the unified health indicator is developed by which the extracted features are integrated. The comparative experiment demonstrates that the proposed method can achieve the relative accuracy of RUL prediction with 95.37% and 94.83% under two operation conditions for the feedback motor sensor fault. As for the steering motor sensor fault, the proposed method can achieve the relative accuracy of RUL prediction with 95.59% and 94.28% under two operation conditions.

GBLN: a new generative broad learning network for rolling bearing fault diagnosis

2025-06-19

Nana Deng , Haiyang Pan , Haoran Liu +3 more | Nondestructive Testing And Evaluation

AI-Driven Belt Failure Prediction and Prescriptive Maintenance with Motor Current Signature Analysis

2025-06-19

J. Costa , José Torres Farinha , Mateus Mendes +1 more | Applied Sciences

Industrial belt failures pose significant challenges to manufacturing operations, often resulting in costly downtime and maintenance interventions. This study presents a comprehensive approach to belt failure analysis, leveraging advanced monitoring … Industrial belt failures pose significant challenges to manufacturing operations, often resulting in costly downtime and maintenance interventions. This study presents a comprehensive approach to belt failure analysis, leveraging advanced monitoring and diagnostic techniques. Through the integration of motor current signature analysis (MCSA) and machine learning algorithms, particularly long short-term memory (LSTM) networks, this study aims to predict and detect belt degradation in real time. The methodology involves the collection and pre-processing of raw spectral data from industrial assets, followed by the training and optimization of predictive models. The effectiveness of the approach is demonstrated through extensive testing against real-world data, showcasing its ability to accurately forecast belt failures and enable proactive maintenance strategies. The results obtained from the testing phase reveal a high level of accuracy in predicting belt failures, with the developed models consistently outperforming traditional methods. The incorporation of LSTM networks and swarm intelligence algorithms led to a significant improvement in predictive capabilities, allowing for the early detection of degradation patterns and timely intervention. By harnessing the power of data-driven predictive analytics, the research offers a promising pathway towards enhancing operational efficiency and minimizing unplanned downtime in industrial settings. This study not only contributes to the field of predictive maintenance but also underscores the transformative potential of advanced monitoring technologies in optimizing asset reliability and performance.

A Machine Learning–Based Predictive Modeling for Optimizing the Critical Useful Life of Aeroengines: A Field Maintenance Perspective

2025-06-19

Shaktiyavesh Nandan Pratap Singh , Rohitashwa Shringi , Manish Chaturvedi +1 more | SAE International Journal of Aerospace

<div>Establishing critical useful life plays a central role to determine aeroengine health status including aeroengine parameter changes from adverse material conditions or metal fatigue. The useful life assessment serves to … <div>Establishing critical useful life plays a central role to determine aeroengine health status including aeroengine parameter changes from adverse material conditions or metal fatigue. The useful life assessment serves to support maintenance teams by enabling predictive maintenance followed by part replacement or conditions improvement. The proposed research works to improve the ability of turbofan aeroengine useful life estimation while targeting practical deployment during maintenance operations at field locations. A field maintenance–oriented ensemble bagged regression model for aeroengines represents the proposed method within this research. The present study reaches an error index of 7.06 with 98.95% model fitness when applying it to critical useful life training data. The projected model received its validation through experiments on test and field datasets. Field tests revealed that among 25 machine learning models the proposed model delivered optimal results since its error index was determined at 10.5337 with 97.60% accuracy compared to prior research findings. This study delivers an optimal solution, which enables aviation maintenance crew and techno managers to achieve effective critical useful life evaluation and decision-making for maintenance needs. This research provides essential guidance to industries under maintenance and repair operations for the reassessment of field-based critical parameters identification.</div>

Peak Detection and Segmented Least Squares Denoising for Bearing Fault Signals Under Variable-Speed Conditions

2025-06-19

Ching‐Ming Lai , Xiaobo Chen , Zexian Wei | Sensing and Imaging

A Spectral Interpretable Bearing Fault Diagnosis Framework Powered by Large Language Models

2025-06-19

Pham Thai Bao , Wenjun Yi , Yue Zhu +2 more | Sensors

Most existing fault diagnosis methods, although capable of extracting interpretable features such as attention-weighted fault-related frequencies, remain essentially black-box models that provide only classification results without transparent reasoning or diagnostic … Most existing fault diagnosis methods, although capable of extracting interpretable features such as attention-weighted fault-related frequencies, remain essentially black-box models that provide only classification results without transparent reasoning or diagnostic justification, limiting users' ability to understand and trust diagnostic outcomes. In this work, we present a novel, interpretable fault diagnosis framework that integrates spectral feature extraction with large language models (LLMs). Vibration signals are first transformed into spectral representations using Hilbert- and Fourier-based encoders to highlight key frequencies and amplitudes. A channel attention-augmented convolutional neural network provides an initial fault type prediction. Subsequently, structured information-including operating conditions, spectral features, and CNN outputs-is fed into a fine-tuned enhanced LLM, which delivers both an accurate diagnosis and a transparent reasoning process. Experiments demonstrate that our framework achieves high diagnostic performance while substantially improving interpretability, making advanced fault diagnosis accessible to non-expert users in industrial settings.

Lift-off identification in gas foil bearings through vibration signal analysis using a convolutional neural network

2025-06-19

Leonardo Gusmão , Marian Sarrazin , Majid Ahmadzadeh +4 more | Journal of the Brazilian Society of Mechanical Sciences and Engineering

A vibration mapped RGB-GADF images driven semi-supervised fault diagnosis method for helical gear

2025-06-19

Hongwei Fan , Qingshan Li , Xuhui Zhang | Measurement Science and Technology

Abstract Aiming at the problems of small number of labeled data and low utilization rate of unlabeled data in mechanical fault diagnosis, a vibration mapped RGB-Gramian angular difference field (RGB-GADF) … Abstract Aiming at the problems of small number of labeled data and low utilization rate of unlabeled data in mechanical fault diagnosis, a vibration mapped RGB-Gramian angular difference field (RGB-GADF) images driven semi-supervised fault diagnosis method for helical gear is proposed. Firstly, the 1D vibration signal collected by one three-channel acceleration sensor is subjected to piecewise aggregation approximation (PAA) to obtain three GADF images. Based on the characteristics of RGB images, three single-channel GADF images are fused into one RGB-GADF image to enhance the operation state characterization of helical gear. Then, based on the FixMatch model, the attention of the model to unlabeled data is increased, so a new multi-attention FixMatch (MA-FixMatch) semi-supervised model is constructed. Next, the weight parameters of the teacher model are subjected to exponential moving average (EMA) to improve the quality and stability of pseudo labels. The final MA-FixMatch with EMA semi-supervised model is obtained. Afterwards, based on inverted triangular channel distribution-ConvNeXt (ITCD-ConvNeXt), an improved ConvNeXt feature extraction model using adaptive maximum pooling (AMP-ConvNeXt) is proposed. The stacking times and the number of input channels of each ConvNeXt Block are finely designed. The data with three label rates are studied under four combined conditions of speed and load. The results show that the semi-supervised fault diagnosis method proposed has the fault diagnosis rate of 99.6% and above on the data sets under four working conditions when the label rate reaches the threshold.

AI-Driven Predictive Maintenance for Electrical Machines and Systems

2025-06-19

| IJIREEICE

Multi-Fault Identification of Rolling Bearings Using VMD and Optimized MCKD

2025-06-19

D Wang , Yimin Wei , Xiang Shi | Engineering Research Express

Abstract Aiming at the challenge of identifying multiple faults in rolling bearings caused by the interrelation and cross-interference of collected vibration signals coupled with environmental noise interference - which leads … Abstract Aiming at the challenge of identifying multiple faults in rolling bearings caused by the interrelation and cross-interference of collected vibration signals coupled with environmental noise interference - which leads to overlapping multi-fault characteristic information and difficulty in fault type determination. This paper proposes a multi-fault identification method based on the combination of Variational Mode Decomposition (VMD) and parameteroptimized Maximum Correlated Kurtosis Deconvolution (MCKD). Firstly, the VMD method is employed for signal processing, where the kurtosis criterion is applied to select optimal&#xD;IMF components for vibration signal reconstruction. Subsequently, an adaptive function is constructed to determine the optimal parameter combination for MCKD, enabling separation of reconstructed signals to extract individual fault signals. Characteristic parameters are then extracted to form feature vector sets. Then, the Support Vector Machines (SVM) method is utilized for fault feature recognition and classification. Finally, the proposed method is validated through designed multi-fault injection experiments on elevator compensation sheave bearings. Experimental results demonstrate that the method effectively separates multiple fault signals under environmental noise and achieves accurate identification of specific faults in compensation sheave bearings, with a fault recognition rate reaching 97.8%.&#xD;This research provides a valuable reference for multi-fault diagnosis in bearing systems, offering technical insights for condition monitoring and predictive maintenance in rotating machinery.&#xD;

Enhanced gear fault diagnosis via heterodyne downconversion: Theoretical verification and optimized ultrasonic signal acquisition

2025-06-19

Jingchao Zhang , Shaoqun Zhang , Yixue Dong +4 more | Measurement

A High-precision method for detecting rolling bearing faultis in unmanned aerial vehicle based on improved 1DCNN-Informer model

2025-06-18

Shuangbao Ma , Songjie Shi , Yapeng Zhang +1 more | Measurement

Rolling Bearing Fault Diagnosis Based on SCNN and Optimized HKELM

2025-06-18

Yulin Wang , Xianjun Du | Mathematics

The issue of insufficient multi-scale feature extraction and difficulty in accurately classifying fault features in rolling bearing fault diagnosis is addressed by proposing a novel diagnostic method that integrates stochastic … The issue of insufficient multi-scale feature extraction and difficulty in accurately classifying fault features in rolling bearing fault diagnosis is addressed by proposing a novel diagnostic method that integrates stochastic convolutional neural networks (SCNNs) and a hybrid kernel extreme learning machine (HKELM). First, the convolutional layers of the CNN were designed as multi-branch parallel layers to extract richer features. A stochastic pooling layer, based on a Bernoulli distribution, was introduced to retain more spatial feature information while ensuring feature diversity. This approach enabled the adaptive extraction, dimensionality reduction, and elimination of redundant information from the vibration signal features of rolling bearings. Subsequently, an HKELM classifier with multiple kernel functions was constructed. Key parameters of the HKELM were dynamically adjusted using a novel optimization algorithm, significantly enhancing fault diagnosis accuracy and system stability. Experimental validation was performed using bearing data from Paderborn University. A comparative study with traditional diagnostic methods demonstrated that the proposed model excelled in both fault classification accuracy and adaptability across operating conditions. Experimental results showed a fault classification accuracy exceeding 99%, confirming the practical value of the method.

Enhanced diagnosis of bearing and gear faults using Hilbert-Huang transform, singular value decomposition, and supervised learning methods

2025-06-18

Abdel wahhab Lourari , Bilal El Yousfi , Ahmed Bouzar Essaidi | The International Journal of Advanced Manufacturing Technology

Research on Power Signal Processing and Feature Extraction Algorithm Based on Time-Frequency Analysis

2025-06-18

Guanghua Yang , Rui Li , Xiangyu Lu +2 more | Research Square (Research Square)

<title>Abstract</title> Power signal processing is a specialized domain within signal processing that focuses on the analysis, interpretation, and manipulation of signals in electrical power systems. In modern smart grids, Power … <title>Abstract</title> Power signal processing is a specialized domain within signal processing that focuses on the analysis, interpretation, and manipulation of signals in electrical power systems. In modern smart grids, Power Quality Disturbances (PQDs) can result in considerable operational disruptions and financial losses for energy stakeholders. Accurate and timely identification of these disturbances is critical to maintaining grid reliability, efficiency, and energy stability. To overcome these challenges, the research proposes a comprehensive framework for PQD identification by leveraging advanced power signal processing techniques and time-frequency-based feature extraction. A Short-Time Fourier Transform fused Efficient Natural Gradient Boosting (STFT-ENGB) model is introduced for robust recognition of power quality disturbances with energy grid applications. To improve computational efficiency and decrease redundant data collection, a signal-piloted gain device is employed. This device continuously monitors power signals and initiates data acquisition only when abnormalities or potential disturbances are detected. The Z-score normalization is a preprocessing technique for reducing noise. The STFT is utilized to extract discriminative, time-localized features from the power signals, effectively characterizing voltage fluctuations and transient energy anomalies. These extracted features are subsequently used to train and evaluate the ENGB classifier. The proposed STFT-ENGB approach achieves high accuracy (98.75%). Experimental results demonstrate that the proposed framework achieves high classification accuracy while significantly reducing data volume and computational load. The reduction in processing overhead and latency underscores the system's suitability for real-time smart grid applications. The proposed approach offers a promising solution for real-time power signal monitoring in smart grid environments, facilitating intelligent fault diagnosis and improving the overall resilience and responsiveness of modern electrical infrastructure.

Differential out-of-distribution error guidance for unknown bearing fault diagnosis with conditional diffusion model

2025-06-18

Yuting Zhang , Boyuan Yang , Zixu Zhao | Engineering Applications of Artificial Intelligence

Enhancing marine shaft generator reliability through intelligent fault diagnosis of gearbox bearings via improved Bidirectional LSTM

2025-06-18

Yaqiong Lv , Yu Liu , Shijie Li +2 more | Ocean Engineering