Engineering › Control and Systems Engineering

Fault Detection and Control Systems

Works Count: 133855

Wikipedia

Description

This cluster of papers focuses on the application of various data-driven and statistical techniques for process fault detection and diagnosis in industrial settings. It covers topics such as process monitoring, fault isolation, soft sensors, model-based diagnosis, and the use of machine learning in analyzing and improving industrial processes.

Keywords

Process Monitoring; Fault Detection; Data-Driven Techniques; Statistical Analysis; Soft Sensors; Model-Based Diagnosis; Industrial Processes; Multivariate Statistical Methods; Fault Isolation; Machine Learning

Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy

1990-05-01

Paul M. Frank

Robust Model-Based Fault Diagnosis for Dynamic Systems

1999-01-01

J. Chen , Ron J. Patton

Signal detection theory and ROC analysis

1975-01-01

James P. Egan

Diagnosis and Fault-Tolerant Control

2003-01-01

Mogens Blanke , Michel Kinnaert , Jan Lunze +1 more

Estimation with Quadratic Loss

1992-01-01

William James , Charles Stein

View PDF Chat

Fault Detection and Diagnosis in Engineering Systems

2017-11-22

Janos J. Gertler

Introduction to fault detection and diagnosis discrete linear systems random variables parameter estimation fundamentals analytical redundancy concepts parity equation implementation of residual generators design for structured residuals design for directional … Introduction to fault detection and diagnosis discrete linear systems random variables parameter estimation fundamentals analytical redundancy concepts parity equation implementation of residual generators design for structured residuals design for directional residuals residual generation for parametric faults robustness in residual generation statistical testing of residuals model identification for the diagnosis of additive faults diagnosing multiplicative faults by parameter estimation.

A Survey of Fault Diagnosis and Fault-Tolerant Techniques—Part I: Fault Diagnosis With Model-Based and Signal-Based Approaches

2015-03-27

Zhiwei Gao , Carlo Cecati , Steven X. Ding

With the ever increase of complexity and expense of industrial systems, there is less tolerance for performance degradation, productivity decrease and safety hazards, which greatly stimulates to detect and identify … With the ever increase of complexity and expense of industrial systems, there is less tolerance for performance degradation, productivity decrease and safety hazards, which greatly stimulates to detect and identify any kinds of potential abnormalities and faults as early as possible, and implement realtime fault-tolerant operation for minimizing performance degradation and avoiding dangerous situations.During the last four decades, fruitful results were reported about fault diagnosis and fault-tolerant control methods and their applications in a variety of engineering systems.The three-part survey paper aims to give a comprehensive review for real-time fault diagnosis and fault tolerant control with particular attention on the results reported in the last decade.In the first-part review, fault diagnosis approaches and their applications are reviewed comprehensively from model-based and signal-based perspectives, respectively. Index Terms-Analytical redundancy

View PDF Chat

Fault-Diagnosis Systems

2005-12-26

Rolf Isermann

Probability, Random Variables, and Stochastic Processes.

1984-12-01

Julia Abrahams , A. Papoulis

Part 1 Probability and Random Variables 1 The Meaning of Probability 2 The Axioms of Probability 3 Repeated Trials 4 The Concept of a Random Variable 5 Functions of One … Part 1 Probability and Random Variables 1 The Meaning of Probability 2 The Axioms of Probability 3 Repeated Trials 4 The Concept of a Random Variable 5 Functions of One Random Variable 6 Two Random Variables 7 Sequences of Random Variables 8 Statistics Part 2 Stochastic Processes 9 General Concepts 10 Random Walk and Other Applications 11 Spectral Representation 12 Spectral Estimation 13 Mean Square Estimation 14 Entropy 15 Markov Chains 16 Markov Processes and Queueing Theory

View PDF Chat

Data-driven Soft Sensors in the process industry

2009-01-21

Petr Kadlec , Bogdan Gabryś , Sibylle Strandt

View PDF Chat

Monitoring batch processes using multiway principal component analysis

1994-08-01

Paul Nomikos , John F. MacGregor

Abstract Multivariate statistical procedures for monitoring the progress of batch processes are developed. The only information needed to exploit the procedures is a historical database of past successful batches. Multiway … Abstract Multivariate statistical procedures for monitoring the progress of batch processes are developed. The only information needed to exploit the procedures is a historical database of past successful batches. Multiway principal component analysis is used to extract the information in the multivariate trajectory data by projecting them onto low‐dimensional spaces defined by the latent variables or principal components. This leads to simple monitoring charts, consistent with the philosophy of statistical process control, which are capable of tracking the progress of new batch runs and detecting the occurrence of observable upsets. The approach is contrasted with other approaches which use theoretical or knowledge‐based models, and its potential is illustrated using a detailed simulation study of a semibatch reactor for the production of styrene‐butadiene latex.

Process fault detection based on modeling and estimation methods—A survey

1984-07-01

Rolf Isermann

Distribution of Residual Autocorrelations in Autoregressive-Integrated Moving Average Time Series Models

1970-12-01

George E. P. Box , David A. Pierce

Abstract Many statistical models, and in particular autoregressive—moving average time series models, can be regarded as means of transforming the data to white noise, that is, to an uncorrected sequence … Abstract Many statistical models, and in particular autoregressive—moving average time series models, can be regarded as means of transforming the data to white noise, that is, to an uncorrected sequence of errors. If the parameters are known exactly, this random sequence can be computed directly from the observations; when this calculation is made with estimates substituted for the true parameter values, the resulting sequence is referred to as the "residuals," which can be regarded as estimates of the errors. If the appropriate model has been chosen, there will be zero autocorrelation in the errors. In checking adequacy of fit it is therefore logical to study the sample autocorrelation function of the residuals. For large samples the residuals from a correctly fitted model resemble very closely the true errors of the process; however, care is needed in interpreting the serial correlations of the residuals. It is shown here that the residual autocorrelations are to a close approximation representable as a singular linear transformation of the autocorrelations of the errors so that they possess a singular normal distribution. Failing to allow for this results in a tendency to overlook evidence of lack of fit. Tests of fit and diagnostic checks are devised which take these facts into account.

The theory of the estimation of test reliability

1937-09-01

G. Frederic Kuder , M. W. Richardson

Detection of Abrupt Changes: Theory and Application

1994-08-01

Kurt S. Riedel

This book is downloadable from http://www.irisa.fr/sisthem/kniga/. Many monitoring problems can be stated as the problem of detecting a change in the parameters of a static or dynamic stochastic system. The … This book is downloadable from http://www.irisa.fr/sisthem/kniga/. Many monitoring problems can be stated as the problem of detecting a change in the parameters of a static or dynamic stochastic system. The main goal of this book is to describe a unified framework for the design and the performance analysis of the algorithms for solving these change detection problems. Also the book contains the key mathematical background necessary for this purpose. Finally links with the analytical redundancy approach to fault detection in linear systems are established. We call abrupt change any change in the parameters of the system that occurs either instantaneously or at least very fast with respect to the sampling period of the measurements. Abrupt changes by no means refer to changes with large magnitude; on the contrary, in most applications the main problem is to detect small changes. Moreover, in some applications, the early warning of small - and not necessarily fast - changes is of crucial interest in order to avoid the economic or even catastrophic consequences that can result from an accumulation of such small changes. For example, small faults arising in the sensors of a navigation system can result, through the underlying integration, in serious errors in the estimated position of the plane. Another example is the early warning of small deviations from the normal operating conditions of an industrial process. The early detection of slight changes in the state of the process allows to plan in a more adequate manner the periods during which the process should be inspected and possibly repaired, and thus to reduce the exploitation costs.

Modeling by shortest data description

1978-09-01

J. Rissanen

Parameter Estimation in Engineering and Science

1979-04-01

José Tiago de Fonseca Oliveira , James V. Beck , Kenneth J. Arnold

Estimation of the probability of an event as a function of several independent variables

1967-01-01

Strother H. Walker , David B. Duncan

Estimation of the probability of an event as a function of several independent variables Get access STROTHER H. WALKER, STROTHER H. WALKER Johns Hopkins University Search for other works by … Estimation of the probability of an event as a function of several independent variables Get access STROTHER H. WALKER, STROTHER H. WALKER Johns Hopkins University Search for other works by this author on: Oxford Academic Google Scholar DAVID B. DUNCAN DAVID B. DUNCAN Johns Hopkins University Search for other works by this author on: Oxford Academic Google Scholar Biometrika, Volume 54, Issue 1-2, June 1967, Pages 167–179, https://doi.org/10.1093/biomet/54.1-2.167 Published: 01 June 1967 Article history Received: 01 June 1966 Revision received: 01 January 1967 Published: 01 June 1967

Optimum Settings for Automatic Controllers

1993-06-01

Jens Ziegler , Nancy B. Nichols

In this paper, the three principal control effects found in present controllers are examined and practical names and units of measurement are proposed for each effect. Corresponding units are proposed … In this paper, the three principal control effects found in present controllers are examined and practical names and units of measurement are proposed for each effect. Corresponding units are proposed for a classification of industrial processes in terms of the two principal characteristics affecting their controllability. Formulas are given which enable the controller settings to be determined from the experimental or calculated values of the lag and unit reaction rate of the process to be controlled. These units form the basis of a quick method for adjusting a controller on the job. The effect of varying each controller setting is shown in a series of chart records. It is believed that the conceptions of control presented in this paper will be of assistance in the adjustment of existing controller applications and in the design of new installations.

Observers for multivariable systems

1966-04-01

David G. Luenberger

Often in control design it is necessary to construct estimates of state variables which are not available by direct measurement. If a system is linear, its state vector can be … Often in control design it is necessary to construct estimates of state variables which are not available by direct measurement. If a system is linear, its state vector can be approximately reconstructed by building an observer which is itself a linear system driven by the available outputs and inputs of the original system. The state vector of an <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</tex> th order system with <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</tex> independent outputs can be reconstructed with an observer of order <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n-m</tex> . In this paper it is shown that the design of an observer for a system with <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</tex> outputs can be reduced to the design of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</tex> separate observers for single-output subsystems. This result is a consequence of a special canonical form developed in the paper for multiple-output systems. In the special case of reconstruction of a single linear functional of the unknown state vector, it is shown that a great reduction in observer complexity is often possible. Finally, the application of observers to control design is investigated. It is shown that an observer's estimate of the system state vector can be used in place of the actual state vector in linear or nonlinear feedback designs without loss of stability.

The Analysis of Time Series: An Introduction

1991-08-01

David A. Dickey , Chris Chatfield

Simple descriptive techniques probability models for time series estimation in the time domain forecasting stationary processes in the frequency domain spectral analysis bivariate processes linear systems state-space models and the … Simple descriptive techniques probability models for time series estimation in the time domain forecasting stationary processes in the frequency domain spectral analysis bivariate processes linear systems state-space models and the Kalman filter non-linear models multivariate time series modelling some other topics.

Probabilistic Models for Some Intelligence and Attainment Tests

1961-12-01

George Rasch

A review of process fault detection and diagnosis

2003-03-01

Venkat Venkatasubramanian , Raghunathan Rengaswamy , Surya N. Kavuri

A review of process fault detection and diagnosis

2003-03-01

Venkat Venkatasubramanian , Raghunathan Rengaswamy , Kewen Yin +1 more

Bibliographical review on reconfigurable fault-tolerant control systems

2008-11-12

Youmin Zhang , Jin Jiang

A new look at the statistical model identification

1974-12-01

Hirotugu Akaike

The history of the development of statistical hypothesis testing in time series analysis is reviewed briefly and it is pointed out that the hypothesis testing procedure is not adequately defined … The history of the development of statistical hypothesis testing in time series analysis is reviewed briefly and it is pointed out that the hypothesis testing procedure is not adequately defined as the procedure for statistical model identification. The classical maximum likelihood estimation procedure is reviewed and a new estimate minimum information theoretical criterion (AIC) estimate (MAICE) which is designed for the purpose of statistical identification is introduced. When there are several competing models the MAICE is defined by the model and the maximum likelihood estimates of the parameters which give the minimum of AIC defined by AIC = (-2)log-(maximum likelihood) + 2(number of independently adjusted parameters within the model). MAICE provides a versatile procedure for statistical model identification which is free from the ambiguities inherent in the application of conventional hypothesis testing procedure. The practical utility of MAICE in time series analysis is demonstrated with some numerical examples.

View PDF Chat

A review of process fault detection and diagnosis

2003-03-01

Venkat Venkatasubramanian , Raghunathan Rengaswamy , Surya N. Kavuri +1 more

Generalized harmonic analysis

1930-01-01

Norbert Wiener

View PDF Chat

A Review on Basic Data-Driven Approaches for Industrial Process Monitoring

2014-01-31

Shen Yin , Steven X. Ding , Xiaochen Xie +1 more

Recently, to ensure the reliability and safety of modern large-scale industrial processes, data-driven methods have been receiving considerably increasing attention, particularly for the purpose of process monitoring. However, great challenges … Recently, to ensure the reliability and safety of modern large-scale industrial processes, data-driven methods have been receiving considerably increasing attention, particularly for the purpose of process monitoring. However, great challenges are also met under different real operating conditions by using the basic data-driven methods. In this paper, widely applied data-driven methodologies suggested in the literature for process monitoring and fault diagnosis are surveyed from the application point of view. The major task of this paper is to sketch a basic data-driven design framework with necessary modifications under various industrial operating conditions, aiming to offer a reference for industrial process monitoring on large-scale industrial processes.

An Introduction to Signal Detection and Estimation

1988-01-01

H. Vincent Poor

View PDF Chat

A survey of design methods for failure detection in dynamic systems

1976-11-01

Alan S. Willsky

View PDF Chat

Statistical process monitoring: basics and beyond

2003-08-01

S. Joe Qin

Abstract This paper provides an overview and analysis of statistical process monitoring methods for fault detection, identification and reconstruction. Several fault detection indices in the literature are analyzed and unified. … Abstract This paper provides an overview and analysis of statistical process monitoring methods for fault detection, identification and reconstruction. Several fault detection indices in the literature are analyzed and unified. Fault reconstruction for both sensor and process faults is presented which extends the traditional missing value replacement method. Fault diagnosis methods that have appeared recently are reviewed. The reconstruction‐based approach and the contribution‐based approach are analyzed and compared with simulation and industrial examples. The complementary nature of the reconstruction‐ and contribution‐based approaches is highlighted. An industrial example of polyester film process monitoring is given to demonstrate the power of the contribution‐ and reconstruction‐based approaches in a hierarchical monitoring framework. Finally we demonstrate that the reconstruction‐based framework provides a convenient way for fault analysis, including fault detectability, reconstructability and identifiability conditions, resolving many theoretical issues in process monitoring. Additional topics are summarized at the end of the paper for future investigation. Copyright © 2003 John Wiley & Sons, Ltd.

Multivariate calibration

1990-01-01

David Steele

Nonlinear Regression

1989-02-15

George A. F. Seber , C. Wild

Data analysis: a Bayesian tutorial

1997-06-01

1. The Basics 2. Parameter Estimation I 3. Parameter Estimation II 4. Model Selection 5. Assigning Probabilities 6. Non-parametric Estimation 7. Experimental Design 8. Least-Squares Extensions 9. Nested Sampling 10. … 1. The Basics 2. Parameter Estimation I 3. Parameter Estimation II 4. Model Selection 5. Assigning Probabilities 6. Non-parametric Estimation 7. Experimental Design 8. Least-Squares Extensions 9. Nested Sampling 10. Quantification Appendices Bibliography

View PDF Chat

System identification

1990-07-01

Jan G. De Gooijer

Optimum Settings for Automatic Controllers

1942-11-01

Jens Ziegler , Nancy B. Nichols

Abstract In this paper, the three principal control effects found in present controllers are examined and practical names and units of measurement are proposed for each effect. Corresponding units are … Abstract In this paper, the three principal control effects found in present controllers are examined and practical names and units of measurement are proposed for each effect. Corresponding units are proposed for a classification of industrial processes in terms of the two principal characteristics affecting their controllability. Formulas are given which enable the controller settings to be determined from the experimental or calculated values of the lag and unit reaction rate of the process to be controlled. These units form the basis of a quick method for adjusting a controller on the job. The effect of varying each controller setting is shown in a series of chart records. It is believed that the conceptions of control presented in this paper will be of assistance in the adjustment of existing controller applications and in the design of new installations.

An Algorithm for Least-Squares Estimation of Nonlinear Parameters

1963-01-01

Donald W. Marquardt

A survey of design methods for failure detection in dynamic systems

1977-01-01

View PDF Chat

An Introduction to Signal Detection and Estimation

1994-01-01

H. Vincent Poor

View PDF Chat

Time Series Analysis by State Space Methods

2012-05-03

J. Durbin , Siem Jan Koopman

Abstract This book presents a comprehensive treatment of the state space approach to time series analysis. The distinguishing feature of state space time series models is that observations are regarded … Abstract This book presents a comprehensive treatment of the state space approach to time series analysis. The distinguishing feature of state space time series models is that observations are regarded as being made up of distinct components such as trend, seasonal, regression elements and disturbance elements, each of which is modelled separately. The techniques that emerge from this approach are very flexible. Part I presents a full treatment of the construction and analysis of linear Gaussian state space models. The methods are based on the Kalman filter and are appropriate for a wide range of problems in practical time series analysis. The analysis can be carried out from both classical and Bayesian perspectives. Part I then presents illustrations to real series and exercises are provided for a selection of chapters. Part II discusses approximate and exact approaches for handling broad classes of non-Gaussian and nonlinear state space models. Approximate methods include the extended Kalman filter and the more recently developed unscented Kalman filter. The book shows that exact treatments become feasible when simulation-based methods such as importance sampling and particle filtering are adopted. Bayesian treatments based on simulation methods are also explored.

View PDF Chat

Distribution of Residual Autocorrelations in Autoregressive-Integrated Moving Average Time Series Models

1970-12-01

George E. P. Box , David A. Pierce

Principal Component Analysis

2001-01-01

Leo H. Chiang , Evan L. Russell , Richard D. Braatz

By projecting the data into a lower-dimensional space that accurately characterizes the state of the process, dimensionality reduction techniques can greatly simplify and improve process monitoring procedures. Principal component analysis … By projecting the data into a lower-dimensional space that accurately characterizes the state of the process, dimensionality reduction techniques can greatly simplify and improve process monitoring procedures. Principal component analysis (PCA) is such a dimensionality reduction technique. It produces a lower-dimensional representation in a way that preserves the correlation structure between the process variables, and is optimal in terms of capturing the variability in the data.

Probabilistic Models for some Intelligence and Attainment Tests.

1982-03-01

Leroy Wolins , Benjamin D. Wright , Georg Rasch

Statistics for Long-Memory Processes.

1996-09-01

Donald B. Percival , Jan Beran

A New Look at the Statistical Model Identification

1974-01-01

Hirotugu Akaike

Disentangling the Time-Frequency Nexus of Oil, Uncertainties, and Saudi Equities: A Wavelet Local Multiple Correlation Approach

2025-06-25

Hela Ben Hamida , Chaker Aloui | International Journal of Energy Economics and Policy

This paper examines the combined and separate effects of geopolitical risk, economic policy uncertainty, and oil prices on the stock market within a multivariate time-frequency framework, focusing on Saudi Arabia … This paper examines the combined and separate effects of geopolitical risk, economic policy uncertainty, and oil prices on the stock market within a multivariate time-frequency framework, focusing on Saudi Arabia as an oil-rich country. We implement the wavelet local multiple correlation approach using monthly data from January 2000 to December 2024. Our results reveal that oil prices, geopolitical risk, and economic uncertainty are key drivers of Saudi market behavior. The joint and individual effects vary significantly across time scales and frequencies. Increasing uncertainty surrounding economic policies and rising geopolitical tensions in the region have intensified the impact of oil price movements on the Saudi market. These findings have several implications for portfolio managers, foreign investors, and policymakers. When analyzing and forecasting stock returns, portfolio managers should consider oil prices, geopolitical risk, and changes in economic policy uncertainty.

Development of an intelligent moving horizon estimator integrated with fault diagnosis for automated model maintenance

2025-06-24

Giriraj Bagla , Sachin C. Patwardhan , Mani Bhushan | Journal of Process Control

Fault Diagnosis of Aero‐Engine Gas Path System Under Time‐varying Operating Condition

2025-06-24

Shijie Zhang , Jiawen Hu , Lei Wang | Quality and Reliability Engineering International

ABSTRACT An aero‐engine usually works in time‐varying operating condition. The coupling effect between gas path fault mode and operating condition makes the characteristics of fault mode vary with the operating … ABSTRACT An aero‐engine usually works in time‐varying operating condition. The coupling effect between gas path fault mode and operating condition makes the characteristics of fault mode vary with the operating condition. It increases the difficulty of fault diagnosis of gas path system. Moreover, class imbalance commonly exists between normal data and fault mode data. To address these challenges, we propose a multi‐stage semi‐supervised fault diagnosis method for gas path system, considering time‐varying operating condition and class imbalance. At the first stage, a multilayer perceptron (MLP) is constructed to identify the operating condition based on altitude, Mach number, fuel flow, and high and low‐pressure rotor speed. At the second stage, an auxiliary classifier Wasserstein generative adversarial network with gradient penalty (ACWGAN‐GP) model is developed to create fault samples during the self‐training process. All the data are divided into three categories, that is, pressure, speed, and temperature data, which are used to train fault diagnosis mode, respectively. The Dempster–Shafer evidence theory is employed for the information fusion at the decision level. The effectiveness of our proposed method is validated by data generated by a gas turbine simulation program.

Integrated Cascade Control and Gaussian Process Regression–Based Fault Detection for Roll-to-Roll Textile Systems

2025-06-24

Ahmed Neaz , Eun Ha Lee , Mohamed Ali Noman +2 more | Machines

Roll-to-roll (R2R) manufacturing processes demand precise control of web or yarn velocity and tension, alongside robust mechanisms for handling system failures. This paper presents an integrated approach combining high-performance control … Roll-to-roll (R2R) manufacturing processes demand precise control of web or yarn velocity and tension, alongside robust mechanisms for handling system failures. This paper presents an integrated approach combining high-performance control with reliable fault detection for an experimental R2R system. A model-based cascade control strategy is designed, incorporating system identification, radius compensation for varying roll diameters, and a Kalman filter to mitigate load sensor noise, ensuring accurate regulation of yarn velocity and tension under normal operating conditions. In parallel, a data-driven fault detection layer uses Gaussian Process Regression (GPR) models, trained offline on healthy operating data, to predict yarn tension and motor speeds. During operation, discrepancies between measured and GPR-predicted values that exceed predefined thresholds trigger an immediate shutdown of the system, preventing material loss and equipment damage. Experimental trials demonstrate tension regulation within ±0.02 N and velocity errors below ±5 rad/s across varying roll diameters, while yarn-break and motor-fault scenarios are detected within a single sampling interval (<100 milliseconds) with zero false alarms. This study validates the integrated system’s capability to enhance both the operational precision and resilience of R2R processes against critical failures.

Development and Performance Evaluation of a Fault-tolerant Control and Diagnosis System for a Quadcopter-type CanSat

2025-06-24

Hyeonok Lim , Hao Yang , Yongseon Lee +2 more | Journal of Institute of Control Robotics and Systems

Extraction of Physical Parameters of RRab Variables Using Neural Network Based Interpolator

2025-06-24

Nitesh Kumar , Harinder P. Singh , O. Yu. Malkov +4 more | Universe

Determining the physical parameters of pulsating variable stars such as RR Lyrae is essential for understanding their internal structure, pulsation mechanisms, and evolutionary state. In this study, we present a … Determining the physical parameters of pulsating variable stars such as RR Lyrae is essential for understanding their internal structure, pulsation mechanisms, and evolutionary state. In this study, we present a machine learning framework that uses feedforward artificial neural networks (ANNs) to infer stellar parameters—mass (M), luminosity (log(L/L⊙)), effective temperature (log(Teff)), and metallicity (Z)—directly from Transiting Exoplanet Survey Satellite (TESS) light curves. The network is trained on a synthetic grid of RRab light curves generated from hydrodynamical pulsation models spanning a broad range of physical parameters. We validate the model using synthetic self-inversion tests and demonstrate that the ANN accurately recovers the input parameters with minimal bias. We then apply the trained model to RRab stars observed by the TESS. The observed light curves are phase-folded, corrected for extinction, and passed through the ANN to derive physical parameters. Based on these results, we construct an empirical period–luminosity–metallicity (PLZ) relation: log(L/L⊙) = (1.458 ± 0.028) log(P/days) + (–0.068 ± 0.007) [Fe/H] + (2.040 ± 0.007). This work shows that ANN-based light-curve inversion offers an alternative method for extracting stellar parameters from single-band photometry. The approach can be extended to other classes of pulsators such as Cepheids and Miras.

Integral Approach-Based Sensitive Protection of Autotransformers for Turn-to-Turn Faults

2025-06-23

Krzysztof Solak , Waldemar Rebizant , Frank Mieske | Energies

Current differential protection, using either phase currents or negative-sequence components, is commonly applied for the sensitive protection of power transformers. However, this method proves insufficient for autotransformers, particularly when their … Current differential protection, using either phase currents or negative-sequence components, is commonly applied for the sensitive protection of power transformers. However, this method proves insufficient for autotransformers, particularly when their tertiary winding is fully loaded, as demonstrated in this paper. To address this limitation, the authors’ previously proposed negative-sequence integral approach for power transformers has been adapted and evaluated for three-winding autotransformers. The results show that this integral protection offers significantly higher sensitivity than current differential schemes while maintaining security during external faults with current transformer saturation.

Observer compensation‐based model predictive fault‐tolerant control for industrial processes: A high‐order fully actuated system‐method

2025-06-23

Pengbin Zhang , Hongrui Wang , Limin Wang +1 more | The Canadian Journal of Chemical Engineering

Abstract This paper proposes a fault‐tolerant predictive tracking control strategy for the industrial process based on a high‐order fully actuated (HOFA) system method. First, a novel system representation method is … Abstract This paper proposes a fault‐tolerant predictive tracking control strategy for the industrial process based on a high‐order fully actuated (HOFA) system method. First, a novel system representation method is employed to model the industrial process as a HOFA system. Subsequently, a fault‐compensated HOFA predictive fault‐tolerant control scheme is introduced, which includes two components: HOFA feedback stabilization and HOFA model predictive tracking control. Within this framework, an incremental predictive model is developed to replace the reduced‐order prediction model by employing a Diophantine equation. The cost function, which incorporates tracking performance, is subsequently minimized using multi‐step output prediction. Additionally, sufficient conditions for the stability and tracking performance of the closed‐loop HOFA system are derived. The advantage of this approach lies in its ability to reduce system dimensionality while effectively eliminating the impact of faults on system stability through the introduction of an observer‐based compensation concept. This ensures stable operation under fault conditions, or even operation unaffected by faults. Finally, the effectiveness and reliability of the proposed method are validated through a case study involving a nonlinear reactor.

Dynamically scaling spatio‐temporal semi‐supervised adaptive networks based soft sensor for industrial process

2025-06-23

Guo Xiao-ping , Peiqi Wu , Yuan Li | The Canadian Journal of Chemical Engineering

Abstract Aiming at the question of information loss between layers when mining spatiotemporal features of process data and whether pseudo‐labels are generated for unlabelled data, this paper proposes the dynamically … Abstract Aiming at the question of information loss between layers when mining spatiotemporal features of process data and whether pseudo‐labels are generated for unlabelled data, this paper proposes the dynamically scaling spatio‐temporal semi‐supervised adaptive networks based soft sensor for industrial process (DSST‐SSAN). In order to extract the local temporal correlation features and decrease the information loss between layers, the dynamic scaled spatio‐temporal feature module is constructed, the local prediction models between the current input and the hidden layer features are built in each hidden layer of the long short‐term memory (LSTM) network respectively, the prediction deviations of multiple local models are calculated and the dynamic scaled factors are constructed to update the corresponding hidden layer features. The spatial features are extracted in parallel using graph attention network (GAT), and the spatio‐temporal features are obtained by fusion to establish a soft sensor model. To address the lack of modelling labelling data, a semi‐supervised thresholding mechanism is proposed to filter the pseudo‐labelled data for adaptive data accumulation. The threshold is constructed using the likelihood root mean square of the root mean square error (RMSE) and mean absolute error (MAE) of the labelled data, which can determine whether the unlabelled data need to generate pseudo‐labels and perform modelling data accumulation and thus update the model. The effectiveness of the proposed method is confirmed by simulation experiments on two industrial cases, debutane tower and sulphur recovery.

Trend Boundary Minima Optimized Empirical Wavelet Transform Method Applied to Vibration Signal Feature Extraction for Shipboard Atomic Gravimeter

2025-06-23

Jinxiu Ma , Jhih-Heng Yan , Wenbin Gong +3 more | Physica Scripta

Abstract The shipboard atomic interferometric gravimeter is a high-precision gravity measurement instrument applied broadly in geophysics, ocean exploration, inertial navigation, and other precision measurement physics fields. However, environmental vibration noise … Abstract The shipboard atomic interferometric gravimeter is a high-precision gravity measurement instrument applied broadly in geophysics, ocean exploration, inertial navigation, and other precision measurement physics fields. However, environmental vibration noise has been one of the most serious factors limiting its performance. Based on the above, this paper developed an empirical wavelet transform technique. It optimizes the minimum value of the trend boundary and utilizes it to extract features from vibration signals of shipboard atomic gravimeters. The boundary of the segmented spectrum is determined by calculating the minimum value of the trend component, and the key spectral negentropy is employed to filter each initial frequency band to extract the frequency band containing vibration information. The left and right demarcations of the extracted frequency bands are adopted as the ultimate boundaries for reconstruction, after which the components containing vibration information can be obtained. This method improves how the empirical wavelet transforms complexly segments the boundary and reduces the problem of too many invalid components. Validation of the vibration interference signals from simulated signals and shipboard atomic gravimeters in dynamic environments showed that our method could accurately decompose the signal components and improve the decomposition efficiency. It provides a theoretical basis for the design of the active vibration isolation system of shipboard atomic gravimeters.&#xD;

Fault diagnosis based on <i>convolutional autoencoders</i> combined with multivariate information fusion

2025-06-23

Hongchao Wang , Jianxin Jiang , Yu Li +3 more | Journal of Vibration and Control

A single type of sensor signal cannot fully represent the operational status of mechanical equipment, leading to incomplete state characterization and inaccurate diagnostics. This paper proposes an innovative fault diagnosis … A single type of sensor signal cannot fully represent the operational status of mechanical equipment, leading to incomplete state characterization and inaccurate diagnostics. This paper proposes an innovative fault diagnosis method based on Convolutional AutoEncoders combined with multivariate information fusion to accurately identify the overall health status of bearings by analyzing various sensor data. Our approach leverages the Convolutional AutoEncoders to effectively integrate heterogeneous sensor data from multiple sources, including vibration and sound signals, with data augmentation and normalization techniques for preprocessing, thereby improving the model’s generalization capability and accuracy. Furthermore, the integration of K- means clustering and a Sparse Attention mechanism enables precise recognition of critical fault features. The model’s effectiveness is validated through comprehensive performance evaluation using confusion matrices and visualization techniques. Experimental results demonstrate that our method achieves high accuracy and robustness in fault diagnosis tasks, offering a significant advancement in intelligent maintenance and fault prediction of rolling bearings by addressing the limitations of traditional methods.

On Calibration in Multi-Distribution Learning

2025-06-23

Rajeev Verma , Volker Fischer , Eric Nalisnick

View PDF Chat

Fault Identification Model Using Convolutional Neural Networks with Transformer Architecture

2025-06-23

Yongxin Fan , Y. Dang , Yangming Guo | Sensors

With the advancement of industrial manufacturing and the shift toward high automation, machines have increasingly taken over many production tasks, greatly improving efficiency and reducing human labor. However, this also … With the advancement of industrial manufacturing and the shift toward high automation, machines have increasingly taken over many production tasks, greatly improving efficiency and reducing human labor. However, this also introduces new challenges, particularly the inability of machines to autonomously detect and diagnose faults. Such undetected issues may cause unexpected breakdowns, interrupting critical operations, leading to economic losses and potential safety hazards. To address this, the present study proposes a novel hybrid deep learning framework that integrates Convolutional Neural Networks (CNN) for feature extraction with Transformer architecture for temporal modeling. The model is validated using NASA’s CMAPSS dataset, a widely used benchmark that includes multi-sensor data and Remaining Useful Life (RUL) labels from aeroengines. By learning from time-series sensor data, the framework achieves accurate RUL predictions and early fault detection. Experimental results show that the model attains over 97% accuracy under both single and multiple operating conditions, highlighting its robustness and adaptability. These findings suggest the framework’s potential in developing intelligent maintenance systems and contribute to the field of Prognostics and Health Management (PHM), enabling more reliable, efficient, and self-monitoring industrial systems.

Predictive Uncertainty Estimation of SOC with Ensemble Algorithms and Bayesian Optimization

2025-06-23

Hoan Nguyen Xuan , Tran Van Sang , Van‐Manh Pham +5 more | Eurasian Soil Science

Definitions and comprehensive assessment of fault isolability in expert-based diagnostic systems

2025-06-23

Jan Maciej Kościelny , Anna Sztyber | Mechanical Systems and Signal Processing

State-of-the-Art Methodologies for Self-Fault Detection, Diagnosis and Evaluation (FDDE) in Residential Heat Pumps

2025-06-23

Francesco Pelella , Adelso Flaviano Passarelli , Belén Llopis-Mengual +3 more | Energies

The European Union’s 2050 targets for decarbonization and electrification are promoting the widespread integration of heat pumps for space heating, cooling, and domestic hot water in buildings. However, their energy … The European Union’s 2050 targets for decarbonization and electrification are promoting the widespread integration of heat pumps for space heating, cooling, and domestic hot water in buildings. However, their energy and environmental performance can be significantly compromised by soft faults, such as refrigerant leakage or heat exchanger fouling, which may reduce system efficiency by up to 25%, even with maintenance intervals every two years. As a result, the implementation of self-fault detection, diagnosis, and evaluation (FDDE) tools based on operational data has become increasingly important. The complexity and added value of these tools grow as they progress from simple fault detection to quantitative fault evaluation, enabling more accurate and timely maintenance strategies. Direct fault measurements are often unfeasible due to spatial, economic, or intrusiveness constraints, thus requiring indirect methods based on low-cost and accessible measurements. In such cases, overlapping fault symptoms may create diagnostic ambiguities. Moreover, the accuracy of FDDE approaches depends on the type and number of sensors deployed, which must be balanced against cost considerations. This paper provides a comprehensive review of current FDDE methodologies for heat pumps, drawing insights from the academic literature, patent databases, and commercial products. Finally, the role of artificial intelligence in enhancing fault evaluation capabilities is discussed, along with emerging challenges and future research directions.

Predicting Marine Fuels with Unusual Wax Appearance Temperatures Using One-Class Support Vector Machines

2025-06-23

Njideka Chima-Amaeshi , Chris O’Malley , Mark J. Willis | Journal of Marine Science and Application

Estimation of Dynamic Error Parameters in a Measurement Chain Based on the Spectrum of Input Quantities

2025-06-23

Marian Kampik , Łukasz Dróżdż , Jerzy Roj | Applied Sciences

This paper presents a method for estimating the parameters of the dynamic error signal in a measurement chain. The method is based on knowledge of the transmittance of subsequent elements … This paper presents a method for estimating the parameters of the dynamic error signal in a measurement chain. The method is based on knowledge of the transmittance of subsequent elements in the chain and analysis of the spectrum of the processed signal. The proposed approach allows for determining the parts of uncertainty budget of the measurement chain related with dynamic errors, considering the currently processed signal and the calculation of the expanded uncertainty associated with the dynamic error signal. The paper describes the proposed error model, the algorithm for estimating the error signal parameters, and detail measurement and simulation experiments conducted to verify the effectiveness of the proposed method.

Knowledge-Graph-Driven Fault Diagnosis Methods for Intelligent Production Lines

2025-06-23

Yanjun Chen , Min Zhou , Meizhou Zhang +1 more | Sensors

In order to enhance the management and application of fault knowledge within intelligent production lines, thereby increasing the efficiency of fault diagnosis and ensuring the stable and reliable operation of … In order to enhance the management and application of fault knowledge within intelligent production lines, thereby increasing the efficiency of fault diagnosis and ensuring the stable and reliable operation of these systems, we propose a fault diagnosis methodology that leverages knowledge graphs. First, we designed an ontology model for fault knowledge by integrating textual features from various components of the production line with expert insights. Second, we employed the ALBERT–BiLSTM–Attention–CRF model to achieve named entity and relationship recognition for faults in intelligent production lines. The introduction of the ALBERT model resulted in a 7.3% improvement in the F1 score compared to the BiLSTM–CRF model. Additionally, incorporating the attention mechanism in relationship extraction led to a 7.37% increase in the F1 score. Finally, we utilized the Neo4j graph database to facilitate the storage and visualization of fault knowledge, validating the effectiveness of our proposed method through a case study on fault diagnosis in CNC machining centers. The research findings indicate that this method excels in recognizing textual entities and relationships related to faults in intelligent production lines, effectively leveraging prior knowledge of faults across various components and elucidating their causes. This approach provides maintenance personnel with an intuitive tool for fault diagnosis and decision support, thereby enhancing diagnostic accuracy and efficiency.

A neural network-based fault detection and isolation method for a class of unknown nonlinear systems with application to the tandem cold rolling process

2025-06-23

Yinyin Tang , Xiaojian Li | International Journal of Systems Science

A Neural Network Integrated Accelerated Failure Time-Based Mixture Cure Model

2025-06-22

Wisdom Aselisewine , Suvra Pal | Statistics and Computing

A Combined Approach for Machine Rare Failure Detection and Process Monitoring using Machine Learning and Multivariate Control charts

2025-06-22

Nadia Bahria , Imen Harbaoui Dridi , Dorsaf Daldoul +1 more | European J of Industrial Engineering

Approximate Hypothesis Testing

2025-06-22

Nicolas Le Gouic , Robert Graczyk , Stefan Moser

View PDF Chat

Transient parameter prediction and fault diagnosis for nuclear power plants based on machine learning

2025-06-22

Yanyu Tang , Tao Liu , Yinlin Chang +2 more | Journal of Nuclear Science and Technology

Fault Diagnosis in Gears using Vibration Analysis

2025-06-21

Prof. Mandar Padhye | INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT

In gearboxes, load fluctuations on the gearbox and gear defects are two major sources of vibration. Further, at times, measurement of vibration in the gearbox is not easy because of … In gearboxes, load fluctuations on the gearbox and gear defects are two major sources of vibration. Further, at times, measurement of vibration in the gearbox is not easy because of the inaccessibility in mounting the vibration transducers. For detecting different type of gear tooth faults an experimental data is taken from single stage gearbox set up. Vibration analysis techniques are used for detection of fault in gear system, fluctuation in gear load. A method for detecting the evolution of gear faults based on time-amplitude analysis through LabVIEW. By comparing Signals of defective condition with healthy condition through vibration analyzer in which, analysis is carried out with the signal to trace of vibration. The validation is done successfully by taking input signal from accelerometer to LabVIEW program. It is for calculating effective statistical parameters in defective condition for time & amplitude domain analysis. The actual position in angle of rotation for one tooth missing in gearbox is also investigated by using LabVIEW program. It is also helpful tool for health monitoring of gears in different conditions. Key Words: Gearbox, Vibration Analysis, Accelerometer

Large Models for Machine Monitoring and Fault Diagnostics: Opportunities, Challenges and Future Direction

2025-06-21

Xuefeng Chen , Yaguo Lei , Yan‐Fu Li +7 more | Journal of Dynamics Monitoring and Diagnostics

As a critical technology for industrial system reliability and safety, machine monitoring and fault diagnostics has advanced transformatively with Large Language Models (LLMs). This paper reviews LLM based monitoring and … As a critical technology for industrial system reliability and safety, machine monitoring and fault diagnostics has advanced transformatively with Large Language Models (LLMs). This paper reviews LLM based monitoring and diagnostics methodologies, categorizing them into in-context learning, fine tuning, retrieval augmented generation, multimodal learning, and time series approaches, analyzing advances in diagnostics and decision support. It identifies bottlenecks like limited industrial data and edge deployment issues, proposing a three stage roadmap to highlight LLMs’ potential in shaping adaptive, interpretable PHM frameworks.

Two-Stage Noise Processing Based on Diffusion Model Integrated With Counterfactual Feature Optimization for Fault Detection

2025-06-20

Zheng Wei , S.W.K. Fu , Hao Pan +2 more | Engineering Research Express

Abstract In industrial production systems, rapid and accurate fault diagnosis is crucial for enhancing productivity, ensuring safety, and reducing the risk of accidents. However, since fault data is generally imbalanced, … Abstract In industrial production systems, rapid and accurate fault diagnosis is crucial for enhancing productivity, ensuring safety, and reducing the risk of accidents. However, since fault data is generally imbalanced, existing sampling methods are typically sensitive to noisy data and prone to generating noisy data. Meanwhile, the high dimensionality of fault data further significantly weakens fault diagnosis performance. To solve the above problems, this paper proposes an improved hybrid sampling method based on diffusion model with two-stage noise processing combined with counterfactual feature optimization for fault diagnosis(CITL-PM-CITL-CE): Firstly, we introduced a confidence evaluation mechanism to optimize the&#xD;Tomek Links method and proposed a data-cleaning approach named CITL. Based on CITL and the diffusion model, a hybrid sampling method (CITL-PM-CITL) with a two-stage noise processing mechanism is designed to create a balanced dataset and reduce noisy data.In industrial production systems, rapid and accurate fault diagnosis is crucial for enhancing productivity, ensuring safety, and reducing the risk of accidents. However, since fault data is generally imbalanced, existing sampling methods are typically sensitive to noisy data and prone to generating noisy data. Meanwhile, the high dimensionality of fault data further significantly weakens fault diagnosis performance. To solve the above problems, this paper proposes an improved hybrid sampling method based on diffusion model with two-stage noise processing combined with counterfactual feature optimization for fault diagnosis(CITL-PM-CITL-CE): Firstly, we introduced a confidence evaluation mechanism to optimize the Tomek Links method and proposed a data-cleaning approach named CITL. Based on CITL and the diffusion model, a hybrid sampling method (CITL-PM-CITL) with a two-stage noise processing mechanism is designed to create a balanced dataset and reduce noisy data. Secondly, to eliminate redundant features and improve data quality, a feature optimization method based on counterfactual explanations is employed for dimensionality reduction. Finally, fault diagnosis is performed on the optimized dataset.

Uncertainty quantification of vector nozzle mechanism through data driven approach

2025-06-20

Xiaoyu Wang , Jianxin Ma , Hai Feng Hu +4 more | International Journal of Computational Methods

Alternative observer-based compensator design for robust asymptotic disturbance rejection in view of input saturation

2025-06-20

Peter Hippe , Günter Roppenecker | at - Automatisierungstechnik

Abstract A new design of observer-based compensators for robust asymptotic rejection of persistent disturbances is presented. A systematic method to prevent controller windup caused by input saturation is the observer … Abstract A new design of observer-based compensators for robust asymptotic rejection of persistent disturbances is presented. A systematic method to prevent controller windup caused by input saturation is the observer technique, i.e., driving the observer by the constrained plant input. When using the internal model principle this technique does not stabilize the compensator during saturation. Therefore, several additional measures have been developed to overcome this problem. The approach presented here follows a completely different path. It starts with a compensator of sufficient order, which is first designed for pole placement. By subsequently modifying the feedback of the observer states and, if necessary, of the system outputs, the conditions for a robust disturbance rejection are satisfied. Thus, the observer technique directly assures windup prevention.

Advancing remote handling capabilities in the nuclear industry with AI-based surrogate models for robotic technologies

2025-06-20

Akhtar Zeb , Petteri Kokkonen , Mikko Tahkola +2 more | Fusion Engineering and Design

Improved African Vulture Optimization Algorithm for Optimizing Nonlinear Regression in Wind-Tunnel-Test Temperature Prediction

2025-06-20

Lester Shen , Xumei Cui , Biling Wang +2 more | Processes

The thermal data of the hypersonic wind tunnel field accurately reflect the aerodynamic performance and key parameters of the aircraft model. However, the prediction of the temperature in hypersonic wind … The thermal data of the hypersonic wind tunnel field accurately reflect the aerodynamic performance and key parameters of the aircraft model. However, the prediction of the temperature in hypersonic wind tunnels has problems such as a large delay, nonlinearity and multivariable coupling. In order to reduce the influence brought by temperature changes and improve the accuracy of temperature prediction in the field control of hypersonic wind tunnels, this paper first combines kernel principal component analysis (KPCA) with phase space reconstruction to preprocess the temperature data set of wind tunnel tests, and the processed data set is used as the input of the temperature-prediction model. Secondly, support vector regression is applied to the construction of the temperature prediction model for the hypersonic wind-tunnel temperature field. Meanwhile, aiming at the problem of difficult parameter-combination selection in support vector regression machines, an Improved African Vulture Optimization Algorithm (IAVOA) based on adaptive chaotic mapping and local search enhancement is proposed to conduct combination optimization of parameters in support vector regression. The improved African Vulture Optimization Algorithm (AVOA) proposed in this paper was compared and analyzed with the traditional AVOA, PSO (Particle Swarm Optimization Algorithm) and GWO (Grey Wolf Optimizer) algorithms through 10 basic test functions, and the superiority of the improved AVOA algorithm proposed in this paper in optimizing the parameters of the support vector regression machine was verified in the actual temperature data in wind-tunnel field control.

Robust broad learning system with parametrized variational mode decomposition for schizophrenia diagnosis

2025-06-19

Sebamai Parija , Mrutyunjaya Sahani , Susanta Kumar Rout | Engineering Applications of Artificial Intelligence

Research, application, and challenges of causal inference in industrial fault diagnosis: A survey

2025-06-19

Bo Li , Qiang Li , Tingqi Du +7 more | Engineering Applications of Artificial Intelligence

Presenting an architecture for a vehicle health monitoring center based on connected vehicles

2025-06-19

Seyed Majid Safi , Mahnaz Rafie , Masood Shahverdi +1 more | Research Square (Research Square)

<title>Abstract</title> Today, with the progress of the automotive industry and its ancillary industries, as well as the progress of the communication and telecommunications industries, and as a result of the … <title>Abstract</title> Today, with the progress of the automotive industry and its ancillary industries, as well as the progress of the communication and telecommunications industries, and as a result of the growth and development of ITS, a new approach has emerged in automotive companies and their accessory manufacturers to provide service to vehicles in the event of breakdowns and problems. In the meantime, a special method based on receiving information from the vehicle with the help of the OBD II device has become more prominent. In most existing methods, the goal is to transfer the vehicle data collected from the sensors and other parts of the vehicle by the vehicle ECU to a server or application program using OBD II in order to use this data to detect vehicle defects. In most of the research and methods presented, the focus has been on one or a few parameters in the ECU, for example, working on parameters that indicate correct fuel consumption so that if there is a defect in the vehicle and its polluting properties, the defect can be fixed to help protect the environment. In this article, the goal is to present an architecture for a vehicle health monitoring center based on connected vehicles. This project aims to provide a monitoring center to take steps in diagnosing vehicle defects and ensure the health of the vehicles connected to this center. In this regard, an application under the Android operating system has been developed, so that after connecting the OBD II device to the vehicle, it connects to it using Bluetooth and transfers the data that this device reads from the ECU to the user's mobile phone and, while storing it in the phone, sends it to the monitoring center server, where the data is analyzed and with its help, possible vehicle damage is detected and action is taken to fix it. Our main goal is to design an architecture for the monitoring center. After evaluating its efficiency in comparison with existing methods, the proposed method was shown to be more complete in terms of quality than all of them, and its implementation was also determined to be easier and more cost-effective. Also, in the quantitative evaluation of the data obtained from testing the proposed method on the Peugeot 206 car, interesting results were obtained from the data continuity of the parameters and the relationships between them, which can be used to introduce the appropriate model of vehicle behavior. In addition to introducing the appropriate model in the behavior of a perfect vehicle with respect to the health of the tested vehicle, a series of relationships were presented that were obtained after analyzing the data received from the vehicle.

Fault Diagnosis and Identification of Abnormal Variables Based on Center Nearest Neighbor Reconstruction Theory

2025-06-19

Guozhu Wang , Ruizhe Zhou , Fei Li +2 more | Mathematics

Fault diagnosis and identification are important goals in ensuring the safe production of industrial processes. This article proposes a data reconstruction method based on Center Nearest Neighbor (CNN) theory for … Fault diagnosis and identification are important goals in ensuring the safe production of industrial processes. This article proposes a data reconstruction method based on Center Nearest Neighbor (CNN) theory for fault diagnosis and abnormal variable identification. Firstly, the k-nearest neighbor (k-NN) method is used to monitor the process and determine whether there is a fault. Secondly, when there is a fault, a high-precision CNN reconstruction algorithm is used to reconstruct each variable and calculate the reconstructed control index. The variable that reduces the control index the most is replaced with the reconstructed variable in sequence, and the iteration is carried out until the control index is within the control range, and all abnormal variables are finally determined. The accuracy of the CNN reconstruction method was verified through a numerical example. Additionally, it was confirmed that the method is not only suitable for fault diagnosis of a single sensor but also can be used sensor faults that occur simultaneously or propagate due to variable correlation. Finally, the effectiveness and applicability of the proposed method were validated through the penicillin fermentation process.

Non‐Invasive Diagnosis of Chronic Myocardial Infarction via Composite In‐Silico‐Human Data Learning

2025-06-19

Rana Raza Mehdi , Nikhil Kadivar , Tanmay Mukherjee +5 more | PubMed

Abstract Myocardial infarction (MI) continues to be a leading cause of death worldwide. The precise quantification of infarcted tissue is crucial to diagnosis, therapeutic management, and post‐MI care. Late gadolinium … Abstract Myocardial infarction (MI) continues to be a leading cause of death worldwide. The precise quantification of infarcted tissue is crucial to diagnosis, therapeutic management, and post‐MI care. Late gadolinium enhancement‐cardiac magnetic resonance (LGE‐CMR) is regarded as the gold standard for precise infarct tissue localization in MI patients. A fundamental limitation of LGE‐CMR is the invasive intravenous introduction of gadolinium‐based contrast agents that present potential high‐risk toxicity, particularly for individuals with underlying chronic kidney diseases. Herein, a completely non‐invasive methodology is developed to identify the location and extent of an infarct region in the left ventricle via a machine learning (ML) model using only cardiac strains as inputs. In this approach, the remarkable performance of a multi‐fidelity ML model is demonstrated, which combines rodent‐based in‐silico‐generated training data (low‐fidelity) with very limited patient‐specific human data (high‐fidelity) in predicting LGE ground truth. The results offer a new paradigm for developing feasible prognostic tools by augmenting synthetic simulation‐based data with very small amounts of in vivo human data. More broadly, the proposed approach can significantly assist with addressing biomedical challenges in healthcare where human data are limited.

Sensor fault detection based on L∞ interval observer for uncertain continuous-time switched linear systems

2025-06-19

Haifa Ethabet , Leila Dadi , Mohamed Aoun +1 more | Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering

In this paper, we address the challenge of designing an interval Fault Detection (FD) method for continuous-time Switched Linear Systems (SLS) in the Unknown But Bounded Error (UBBE) context. The … In this paper, we address the challenge of designing an interval Fault Detection (FD) method for continuous-time Switched Linear Systems (SLS) in the Unknown But Bounded Error (UBBE) context. The considered systems are subject to unknown but bounded disturbances (state and output disturbances) in predefined intervals. A novel technique is developed to construct residual framers using interval observer with <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" overflow="scroll"> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>L</mml:mi> </mml:mrow> <mml:mrow> <mml:mi>∞</mml:mi> </mml:mrow> </mml:msub> </mml:mrow> </mml:math> criterion. The proposed approach is used to supply more degrees of design freedom and to achieve accurate FD results. The design conditions of the proposed FD interval observer are provided in terms of Linear Matrix Inequalities (LMIs) adopting a common quadratic Lyapunov function, under an arbitrary switching signal. Furthermore, a fault detection decision is proposed to indicate the presence of faults using interval analysis. The performances of the proposed approach is highlighted on illustrative examples and comparative studies.

A Data-Driven Monitoring System for a Prescriptive Maintenance Approach: Supporting Reinforcement Learning Strategies

2025-06-19

Joaquín Ordieres‐Meré , Antonio Sánchez-Herguedas , Ángel Isidro Mena Nieto | Applied Sciences

The aim of this study was to evaluate machine learning algorithms’ capacity to improve prescriptive maintenance. A pumping system consisting of two hydraulic pumps with an electric motor from a … The aim of this study was to evaluate machine learning algorithms’ capacity to improve prescriptive maintenance. A pumping system consisting of two hydraulic pumps with an electric motor from a Spanish petrochemical company was used as a case study. Sensors were used to record data on the variables, with the target variable being the bearing temperature of the electric motor. Several regression models and a neural network time series model were tested to model the system variables. A bearing temperature sensitivity analysis was conducted based on the coefficients obtained from the optimization of the regression model. To fully exploit the capabilities of these techniques for application in this field, we designed a reference framework intended to foster model deployment in an industrial context by promoting the self-monitoring and updating of the models when required. The impact on decision-making processes is explored using reinforcement learning in the context of this framework.