This paper presents a novel approach to detect and diagnose faults in the dynamic part of a class of stochastic systems . the Such a group of systems are subjected to a set of crisp inputs but the outputs considered a...This paper presents a novel approach to detect and diagnose faults in the dynamic part of a class of stochastic systems . the Such a group of systems are subjected to a set of crisp inputs but the outputs considered are the measurable probability density functions (PDFs) of the system output, rather than the system output alone. A new approximation model is developed for the output probability density functions so that the dynamic part of the system is decoupled from the output probability density functions. A nonlinear adaptive observer is constructed to detect and diagnose the fault in the dynamic part of the system. Conver-gency analysis is performed for the error dynamics raised from the fault detection and diagnosis phase and an applicability study on the detection and diagnosis of the unexpected changes in the 2D grammage distributions in a paper forming process is included.展开更多
Fault detection in industrial robot drive systems is a critical aspect of ensuring operational reliability and efficiency.To address the challenge of balancing accuracy and robustness in existing fault detection metho...Fault detection in industrial robot drive systems is a critical aspect of ensuring operational reliability and efficiency.To address the challenge of balancing accuracy and robustness in existing fault detection methods,this paper proposes an enhanced fault detection method based on the unscented Kalman filter(UKF).A comprehensive mathematical model of the brushless DC motor drive system is developed to provide a theoretical foundation for the design of subsequent fault detection methods.The conventional UKF estimation process is detailed,and its limitations in balancing estimation accuracy and robustness are addressed by introducing a dynamic,time-varying boundary layer.To further enhance detection performance,the method incorporates residual analysis using improved z-score and signal-tonoise ratio(SNR)metrics.Numerical simulations under both fault-free and faulty conditions demonstrate that the proposed approach achieves lower root mean square error(RMSE)in fault-free scenarios and provides reliable fault detection.These results highlight the potential of the proposed method to enhance the reliability and robustness of fault detection in industrial robot drive systems.展开更多
To accurately diagnosemisfire faults in automotive engines,we propose a Channel Attention Convolutional Model,specifically the Squeeze-and-Excitation Networks(SENET),for classifying engine vibration signals and precis...To accurately diagnosemisfire faults in automotive engines,we propose a Channel Attention Convolutional Model,specifically the Squeeze-and-Excitation Networks(SENET),for classifying engine vibration signals and precisely pinpointing misfire faults.In the experiment,we established a total of 11 distinct states,encompassing the engine’s normal state,single-cylinder misfire faults,and dual-cylinder misfire faults for different cylinders.Data collection was facilitated by a highly sensitive acceleration signal collector with a high sampling rate of 20,840Hz.The collected data were methodically divided into training and testing sets based on different experimental groups to ensure generalization and prevent overlap between the two sets.The results revealed that,with a vibration acceleration sequence of 1000 time steps(approximately 50 ms)as input,the SENET model achieved a misfire fault detection accuracy of 99.8%.For comparison,we also trained and tested several commonly used models,including Long Short-Term Memory(LSTM),Transformer,and Multi-Scale Residual Networks(MSRESNET),yielding accuracy rates of 84%,79%,and 95%,respectively.This underscores the superior accuracy of the SENET model in detecting engine misfire faults compared to other models.Furthermore,the F1 scores for each type of recognition in the SENET model surpassed 0.98,outperforming the baseline models.Our analysis indicated that the misclassified samples in the LSTM and Transformer models’predictions were primarily due to intra-class misidentifications between single-cylinder and dual-cylinder misfire scenarios.To delve deeper,we conducted a visual analysis of the features extracted by the LSTM and SENET models using T-distributed Stochastic Neighbor Embedding(T-SNE)technology.The findings revealed that,in the LSTMmodel,data points of the same type tended to cluster together with significant overlap.Conversely,in the SENET model,data points of various types were more widely and evenly dispersed,demonstrating its effectiveness in distinguishing between different fault types.展开更多
A Wireless Sensor Network(WSN)comprises a series of spatially distributed autonomous devices,each equipped with sophisticated sensors.These sensors play a crucial role in monitoring diverse environmental conditions su...A Wireless Sensor Network(WSN)comprises a series of spatially distributed autonomous devices,each equipped with sophisticated sensors.These sensors play a crucial role in monitoring diverse environmental conditions such as light intensity,air pressure,temperature,humidity,wind,etc.These sensors are generally deployed in harsh and hostile conditions;hence they suffer from different kinds of faults.However,identifying faults in WSN data remains a complex task,as existing fault detection methods,including centralized,distributed,and hybrid approaches,rely on the spatio⁃temporal correlation among sensor nodes.Moreover,existing techniques predominantly leverage classification⁃based machine learning methods to discern the fault state within WSN.In this paper,we propose a regression⁃based bagging method to detect the faults in the network.The proposed bagging method is consisted of GRU(Gated Recurrent Unit)and Prophet model.Bagging allows weak learners to combine efforts to outperform a strong learner,hence it is appropriate to use in WSN.The proposed bagging method was first trained at the base station,then they were deployed at each SN(Sensor Node).Most of the common faults in WSN,such as transient,intermittent and permanent faults,were considered.The validity of the proposed scheme was tested using a trusted online published dataset.Using experimental studies,compared to the latest state⁃of⁃the⁃art machine learning models,the effectiveness of the proposed model is shown for fault detection.Performance evaluation in terms of false positive rate,accuracy,and false alarm rate shows the efficiency of the proposed algorithm.展开更多
Accurately evaluating the safety status of lithium-ion battery systems in electric vehicles is imperative due to the challenges in effectively predicting potential battery failure risks under stochastic profiles.Compl...Accurately evaluating the safety status of lithium-ion battery systems in electric vehicles is imperative due to the challenges in effectively predicting potential battery failure risks under stochastic profiles.Complex battery fault mechanisms and limited poor-quality data collection impede fault detection for battery systems under real-world conditions.This paper proposes a novel graph-guided fault detection method designed to recognize concealed anomalies in realistic data.Graphs guided by physical relationships are constructed for learning the dynamic evolution of physical quantities under normal conditions and their potential change characteristics in fault scenarios.An ensemble Graph Sample and Aggregate Network model are developed to tackle sample distribution imbalances and non-uniformity battery system specifications across vehicles.Failure risk probabilities for diverse battery charging and discharging segments are derived.An ablation study verifies the necessity of ensemble learning in addressing imbalanced datasets.Analysis of 102,095 segments across 86 vehicles with different battery material systems,battery capacities,and numbers of cells and temperature sensors confirms the robustness and generalization of the proposed method,yielding a recall of 98.37%.By introducing the graph,spatio-temporal global fault characteristics of battery systems are automatically extracted.The coupling relationship and evolution of physical quantities under both normal and faulty states are established,effectively uncovering fault information hidden in collected battery data without observable anomalies.The safety state of battery systems is reflected in terms of failure risk probability,providing reliable data support for battery system maintenance.展开更多
During the sizing process,yarn congestion fault occurs at the reed teeth of a sizing machine.At present,the yarn congestion fault is generally handled by manual detection.The sizing production line operates on a large...During the sizing process,yarn congestion fault occurs at the reed teeth of a sizing machine.At present,the yarn congestion fault is generally handled by manual detection.The sizing production line operates on a large scale and runs continuously.Untimely handling of the yarn congestion fault causes a large amount of yarn waste.In this research,a machine vision-based algorithm for yarn congestion fault detection is developed.Through the analysis of the congestion fault and interference contour characteristics,the basic idea of image phase subtraction to identify the congestion fault is determined.To address the interference information appearing after image phase subtraction,the image pre-processing methods of Canny edge extraction and mean filtering are employed.According to the fault size and location characteristics,the fault contour detection algorithm based on inter-frame difference is designed.To mitigate the camera vibration interference,the anti-vibration interference algorithm based on affine transformation is studied,and the fault detection algorithm for the total yarn congestion fault is determined.The detection of 20 sets of field data is carried out,and the detection rate reaches 90%.This fault detection algorithm realizes the automatic detection of yarn congestion fault of sizing machine with certain real-time performance and accuracy.展开更多
In modern industrial applications,ensuring the reliability of mechanical fittings is critical for maintaining operational safety and efficiency,particularly in power grid systems where split pins serve a pivotal role ...In modern industrial applications,ensuring the reliability of mechanical fittings is critical for maintaining operational safety and efficiency,particularly in power grid systems where split pins serve a pivotal role despite being susceptible to environmental degradation and failure.Existing UAV-based inspection systems are hampered by a low representation of split pin elements and complex backgrounds,leading to challenges in accurate fault detection and timely maintenance.To address this pressing issue,our study proposes an innovative fault detection method for split pins.The approach employs a three-step process:first,cropping operations are used to accurately isolate the fittings containing split pins;second,super-resolution reconstruction is applied to enhance image clarity and detail;and finally,an improved YOLOv8 network,augmented with inner-shape IoU and local window attention mechanisms,is utilized to refine local feature extraction and annotation accuracy.Experimental evaluations on a split pin defect dataset demonstrate robust performance,achieving an accuracy rate of 72.1%and a mean average precision(mAP)of 67.7%,thereby validating the method’s effectiveness under challenging conditions.The proposed approach contributes to the field by specifically targeting the challenges associated with split pin detection in UAV-based inspections,offering a practically applicable and reliably precise method.展开更多
Seismic data plays a pivotal role in fault detection,offering critical insights into subsurface structures and seismic hazards.Understanding fault detection from seismic data is essential for mitigating seismic risks ...Seismic data plays a pivotal role in fault detection,offering critical insights into subsurface structures and seismic hazards.Understanding fault detection from seismic data is essential for mitigating seismic risks and guiding land-use plans.This paper presents a comprehensive review of existing methodologies for fault detection,focusing on the application of Machine Learning(ML)and Deep Learning(DL)techniques to enhance accuracy and efficiency.Various ML and DL approaches are analyzed with respect to fault segmentation,adaptive learning,and fault detection models.These techniques,benchmarked against established seismic datasets,reveal significant improvements over classical methods in terms of accuracy and computational efficiency.Additionally,this review highlights emerging trends,including hybrid model applications and the integration of real-time data processing for seismic fault detection.By providing a detailed comparative analysis of current methodologies,this review aims to guide future research and foster advancements in the effectiveness and reliability of seismic studies.Ultimately,the study seeks to bridge the gap between theoretical investigations and practical implementations in fault detection.展开更多
1.Background In the chemical industry,process plants-commonly referred to as plantwide systems-typically consist of many process units(unit operations).Driven by the considerable economic efficiency offered by complex...1.Background In the chemical industry,process plants-commonly referred to as plantwide systems-typically consist of many process units(unit operations).Driven by the considerable economic efficiency offered by complex and interactive process designs,modern plantwide systems are becoming increasingly sophisticated.The operation of these processes is typically characterized by the complexity of individual units(subsystems)and the intricate interactions between geographically distributed units through networks of material and energy flows,as well as control loops[1].展开更多
Three-phase grid-connected inverters(GCIs)are essential components in distributed generation systems,where the accuracy of current measurement circuits is fundamental for reliable closed-loop operation.Nevertheless,th...Three-phase grid-connected inverters(GCIs)are essential components in distributed generation systems,where the accuracy of current measurement circuits is fundamental for reliable closed-loop operation.Nevertheless,the presence of a DC offset in the measured current can disrupt the regulation of grid currents and significantly degrade system performance.In this work,a fault-tolerant control approach is introduced to counteract the impact of such offset faults through a dedicated current compensation mechanism.The proposed solution is built around two main stages:(i)detecting and isolating DC offset faults that may appear in one or multiple phases of the measured grid currents,and(ii)estimating the fault magnitude and reconstructing the corrected current signal.The offset magnitude is obtained analytically by examining the grid current projected onto the synchronous d-axis at the grid angular frequency,eliminating the need for any additional sensing hardware.Simulation and experimental investigations conducted under several fault scenarios confirm the robustness of the proposed strategy and highlight significant improvements in detection speed and diagnostic accuracy.展开更多
Permanent-magnet synchronous machines(PMSMs)are widely used in robotics,rail transportation,and electric vehicles owing to their high power density,high efficiency,and high power factor.However,PMSMs often operate in ...Permanent-magnet synchronous machines(PMSMs)are widely used in robotics,rail transportation,and electric vehicles owing to their high power density,high efficiency,and high power factor.However,PMSMs often operate in harsh environments,where critical components such as windings and permanent magnets(PMs)are susceptible to failures.These faults can lead to a significant degradation in performance,posing substantial challenges to the reliable operation of PMSMs.This paper presents a comprehensive review of common fault types in PMSMs,along with their corresponding fault diagnosis and fault-tolerant control strategies.The underlying mechanisms of typical faults are systematically analyzed,followed by a detailed comparison of various diagnostic and fault-tolerant control methods to evaluate their respective advantages and limitations.Finally,the review concludes by identifying key research gaps in PMSM fault diagnosis and fault-tolerant control,while proposing potential future directions for advancing this field.展开更多
Kernel-based slow feature analysis(SFA)methods have been successfully applied in the industrial process fault detection field.However,kernel-based SFA methods have high computational complexity as dealing with nonline...Kernel-based slow feature analysis(SFA)methods have been successfully applied in the industrial process fault detection field.However,kernel-based SFA methods have high computational complexity as dealing with nonlinearity,leading to delays in detecting time-varying data features.Additionally,the uncertain kernel function and kernel parameters limit the ability of the extracted features to express process characteristics,resulting in poor fault detection performance.To alleviate the above problems,a novel randomized auto-regressive dynamic slow feature analysis(RRDSFA)method is proposed to simultaneously monitor the operating point deviations and process dynamic faults,enabling real-time monitoring of data features in industrial processes.Firstly,the proposed Random Fourier mappingbased method achieves more effective nonlinear transformation,contrasting with the current kernelbased RDSFA algorithm that may lead to significant computational complexity.Secondly,a randomized RDSFA model is developed to extract nonlinear dynamic slow features.Furthermore,a Bayesian inference-based overall fault monitoring model including all RRDSFA sub-models is developed to overcome the randomness of random Fourier mapping.Finally,the superiority and effectiveness of the proposed monitoring method are demonstrated through a numerical case and a simulation of continuous stirred tank reactor.展开更多
In the field of gear fault detection,the symmetrized dot pattern(SDP)technique,combined with a convolutional neural network(CNN),is widely used to classify various types of defects.The SDP-CNN combination is used to t...In the field of gear fault detection,the symmetrized dot pattern(SDP)technique,combined with a convolutional neural network(CNN),is widely used to classify various types of defects.The SDP-CNN combination is used to transform vibration signals and simplify the defect classification process under stationary operating conditions.This work aims to enhance the SDP-CNN combination for detecting incipient defects in gear under variable working conditions.The vibration signals are filtered by Vold-Kalman Filter Multi-Order Tracking to highlight fault characteristics under variable working conditions.Subsequently,the signals are SDP-transformed and are then classified by optimized CNN.The new pipeline has been validated on an experimental dataset and compared with the classical one by developing both two-and multi-class CNNs.The results showed the applicability of the new pipeline in terms of percentage accuracy and ROC curve compared to the classical approach.Finally,the proposed pipeline was compared with other ML literature techniques using the same dataset.展开更多
Fault sensing in wind turbine(WT)generator bearings is essential for ensuring reliability and holding down maintenance costs.Feeding raw sensor data to machine learning(ML)model often overlooks the enveloping interdep...Fault sensing in wind turbine(WT)generator bearings is essential for ensuring reliability and holding down maintenance costs.Feeding raw sensor data to machine learning(ML)model often overlooks the enveloping interdependencies between system elements.This study proposes a new hybrid method that combines the domain knowledge via knowledge graphs(KGs)and the traditional feature-based data.Incorporation of contextual relationships through construction of graph embedding methods,such as Node2Vec,can capture meaningful information,such as the relationships among key parameters(e.g.wind speed,rotor Revolutions Per Minute(RPM),and temperature)in the enriched feature representations.These node embeddings,when augmented with the original data,can be used to allow the model to learn and generalize better.As shown in results achieved on experimental data,the augmented ML model(with KG)is much better at predicting with the help of accuracy and error measure compared to traditional ML methods.Paired t-test analysis proves the statistical validity of this improvement.Moreover,graph-based feature importance increases the interpretability of the model and helps to uncover the structurally significant variables that are otherwise ignored by the common methods.The approach provides an excellent,knowledge-guided manner through which intelligent fault detection can be executed on WT systems.展开更多
As modern power systems grow in complexity,accurate and efficient fault detection has become increasingly important.While many existing reviews focus on a single modality,this paper presents a comprehensive survey fro...As modern power systems grow in complexity,accurate and efficient fault detection has become increasingly important.While many existing reviews focus on a single modality,this paper presents a comprehensive survey from a dual-modality perspective-infrared imaging and voiceprint analysis-two complementary,non-contact techniques that capture different fault characteristics.Infrared imaging excels at detecting thermal anomalies,while voiceprint signals provide insight into mechanical vibrations and internal discharge phenomena.We review both traditional signal processing and deep learning-based approaches for each modality,categorized by key processing stages such as feature extraction and classification.The paper highlights how these modalities address distinct fault types and how they may be fused to improve robustness and accuracy.Representative datasets are summarized,and practical challenges such as noise interference,limited fault samples,and deployment constraints are discussed.By offering a cross-modal,comparative analysis,this work aims to bridge fragmented research and guide future development in intelligent fault detection systems.The review concludes with research trends including multimodal fusion,lightweight models,and self-supervised learning.展开更多
This research aims to address the challenges of fault detection and isolation(FDI)in digital grids,focusing on improving the reliability and stability of power systems.Traditional fault detection techniques,such as ru...This research aims to address the challenges of fault detection and isolation(FDI)in digital grids,focusing on improving the reliability and stability of power systems.Traditional fault detection techniques,such as rule-based fuzzy systems and conventional FDI methods,often struggle with the dynamic nature of modern grids,resulting in delays and inaccuracies in fault classification.To overcome these limitations,this study introduces a Hybrid NeuroFuzzy Fault Detection Model that combines the adaptive learning capabilities of neural networks with the reasoning strength of fuzzy logic.The model’s performance was evaluated through extensive simulations on the IEEE 33-bus test system,considering various fault scenarios,including line-to-ground faults(LGF),three-phase short circuits(3PSC),and harmonic distortions(HD).The quantitative results show that the model achieves 97.2%accuracy,a false negative rate(FNR)of 1.9%,and a false positive rate(FPR)of 2.3%,demonstrating its high precision in fault diagnosis.The qualitative analysis further highlights the model’s adaptability and its potential for seamless integration into smart grids,micro grids,and renewable energy systems.By dynamically refining fuzzy inference rules,the model enhances fault detection efficiency without compromising computational feasibility.These findings contribute to the development of more resilient and adaptive fault management systems,paving the way for advanced smart grid technologies.展开更多
The snapshot Fault Detection(FD)algorithm of Advanced Receiver Autonomous Integrity Monitoring(ARAIM)necessitates the allocation of continuity and integrity risk requirements from the operational exposure time level t...The snapshot Fault Detection(FD)algorithm of Advanced Receiver Autonomous Integrity Monitoring(ARAIM)necessitates the allocation of continuity and integrity risk requirements from the operational exposure time level to the single epoch level.Current studies primarily focus on finding a conservative Number of Effective Samples(NES)as a risk mapping factor.However,considering that the NES varies with the observation environment and the type of the fault mode,applying a fixed NES can constrain the performance of the algorithm.To address this issue,the continuity and integrity risks over the operational exposure time are analyzed and bounded based on all epochs within the exposure time.A more adaptable method for continuity and integrity budget allocation over the operational exposure time is presented,capable of monitoring the continuity and integrity risks over the recent operational exposure time in real time,and dynamically adjusting the allocation values based on the current observation environment.Simulation results demonstrate that,compared with the allocation method based on a fixed NES,ARAIM based on the proposed allocation method exhibits superior performance in terms of the availability.At an FD execution frequency equal to the required Time-To-Alert(TTA),the dual-constellation H-ARAIM provides 100%of the global coverage with 99.5%availability of the RNP 0.1 service,and the dual-constellation V-ARAIM provides 86.38%of the global coverage with 99.5%availability of the LPV-200 service.展开更多
The aircraft braking system is critical to ensure the safe take-off and landing of the aircraft.However,the braking system is often exposed to high temperatures and strong vibration working environments,which makes th...The aircraft braking system is critical to ensure the safe take-off and landing of the aircraft.However,the braking system is often exposed to high temperatures and strong vibration working environments,which makes the sensor prone to failure.Sensor failure has the potential to compromise aircraft safety.In order to improve the safety of the aircraft braking system,a fault detection and fault-tolerant control(FDFTC)strategy for the aircraft brake pressure sensor is designed.Firstly,a model based on a bidirectional long short-term memory(Bi-LSTM)network is constructed to estimate the brake pressure.Then,the residual sequence is obtained by comparing the measured pressure with the estimated pressure.On this basis,the improved sequential probability ratio test(SPRT)method based on mathematical statistics is applied to analyze the residual sequence to detect the fault.Finally,simulation and hardware-in-the-loop(HIL)testing results indicate that the proposed FDFTC strategy can detect sensor faults in time and efficiently complete braking when faults occur.Hence,the proposed FDFTC strategy can effectively deal with the faults of the aircraft brake pressure sensor,which is of great significance to improve the reliability and safety of the aircraft.展开更多
This research focuses on detecting faults in flight vehicles with unstable subsystems operating asynchronously.By accounting for asynchronous switching,a switched model is established,and filters for fault detection(F...This research focuses on detecting faults in flight vehicles with unstable subsystems operating asynchronously.By accounting for asynchronous switching,a switched model is established,and filters for fault detection(FD)in unstable subsystems are developed.The FD challenge is then transformed into an H∞filtering issue.Utilizing the multiple discontinuous Lyapunov function(MDLF)approach and the mode-dependent average dwell time(MDADT)method,sufficient conditions are derived to ensure stability during both fast and slow switching.Furthermore,the existence and solutions for FD filters are provided through linear matrix inequalities(LMIs).The simulation outcomes demonstrated the excellent performance of the developed method in studied cases.展开更多
Test selection design(TSD)is an important technique for improving product maintainability,reliability and reducing lifecycle costs.In recent years,although some researchers have addressed the design problem of test se...Test selection design(TSD)is an important technique for improving product maintainability,reliability and reducing lifecycle costs.In recent years,although some researchers have addressed the design problem of test selection,the correlation between test outcomes has not been sufficiently considered in test metrics modeling.This study proposes a new approach that combines copula and D-Vine copula to address the correlation issue in TSD.First,the copula is utilized to model FIR on the joint distribution.Furthermore,the D-Vine copula is applied to model the FDR and FAR.Then,a particle swarm optimization is employed to select the optimal testing scheme.Finally,the efficacy of the proposed method is validated through experimentation on a negative feedback circuit.展开更多
文摘This paper presents a novel approach to detect and diagnose faults in the dynamic part of a class of stochastic systems . the Such a group of systems are subjected to a set of crisp inputs but the outputs considered are the measurable probability density functions (PDFs) of the system output, rather than the system output alone. A new approximation model is developed for the output probability density functions so that the dynamic part of the system is decoupled from the output probability density functions. A nonlinear adaptive observer is constructed to detect and diagnose the fault in the dynamic part of the system. Conver-gency analysis is performed for the error dynamics raised from the fault detection and diagnosis phase and an applicability study on the detection and diagnosis of the unexpected changes in the 2D grammage distributions in a paper forming process is included.
基金Supported by the Natural Science Foundation of the Higher Education Institutions of Jiangsu Province(22KJB520012)the Research Project on Higher Education Reform in Jiangsu Province(2023JSJG781)the College Student Innovation and Entrepreneurship Training Program Project(202313571008Z)。
文摘Fault detection in industrial robot drive systems is a critical aspect of ensuring operational reliability and efficiency.To address the challenge of balancing accuracy and robustness in existing fault detection methods,this paper proposes an enhanced fault detection method based on the unscented Kalman filter(UKF).A comprehensive mathematical model of the brushless DC motor drive system is developed to provide a theoretical foundation for the design of subsequent fault detection methods.The conventional UKF estimation process is detailed,and its limitations in balancing estimation accuracy and robustness are addressed by introducing a dynamic,time-varying boundary layer.To further enhance detection performance,the method incorporates residual analysis using improved z-score and signal-tonoise ratio(SNR)metrics.Numerical simulations under both fault-free and faulty conditions demonstrate that the proposed approach achieves lower root mean square error(RMSE)in fault-free scenarios and provides reliable fault detection.These results highlight the potential of the proposed method to enhance the reliability and robustness of fault detection in industrial robot drive systems.
基金Yongxian Huang supported by Projects of Guangzhou Science and Technology Plan(2023A04J0409)。
文摘To accurately diagnosemisfire faults in automotive engines,we propose a Channel Attention Convolutional Model,specifically the Squeeze-and-Excitation Networks(SENET),for classifying engine vibration signals and precisely pinpointing misfire faults.In the experiment,we established a total of 11 distinct states,encompassing the engine’s normal state,single-cylinder misfire faults,and dual-cylinder misfire faults for different cylinders.Data collection was facilitated by a highly sensitive acceleration signal collector with a high sampling rate of 20,840Hz.The collected data were methodically divided into training and testing sets based on different experimental groups to ensure generalization and prevent overlap between the two sets.The results revealed that,with a vibration acceleration sequence of 1000 time steps(approximately 50 ms)as input,the SENET model achieved a misfire fault detection accuracy of 99.8%.For comparison,we also trained and tested several commonly used models,including Long Short-Term Memory(LSTM),Transformer,and Multi-Scale Residual Networks(MSRESNET),yielding accuracy rates of 84%,79%,and 95%,respectively.This underscores the superior accuracy of the SENET model in detecting engine misfire faults compared to other models.Furthermore,the F1 scores for each type of recognition in the SENET model surpassed 0.98,outperforming the baseline models.Our analysis indicated that the misclassified samples in the LSTM and Transformer models’predictions were primarily due to intra-class misidentifications between single-cylinder and dual-cylinder misfire scenarios.To delve deeper,we conducted a visual analysis of the features extracted by the LSTM and SENET models using T-distributed Stochastic Neighbor Embedding(T-SNE)technology.The findings revealed that,in the LSTMmodel,data points of the same type tended to cluster together with significant overlap.Conversely,in the SENET model,data points of various types were more widely and evenly dispersed,demonstrating its effectiveness in distinguishing between different fault types.
文摘A Wireless Sensor Network(WSN)comprises a series of spatially distributed autonomous devices,each equipped with sophisticated sensors.These sensors play a crucial role in monitoring diverse environmental conditions such as light intensity,air pressure,temperature,humidity,wind,etc.These sensors are generally deployed in harsh and hostile conditions;hence they suffer from different kinds of faults.However,identifying faults in WSN data remains a complex task,as existing fault detection methods,including centralized,distributed,and hybrid approaches,rely on the spatio⁃temporal correlation among sensor nodes.Moreover,existing techniques predominantly leverage classification⁃based machine learning methods to discern the fault state within WSN.In this paper,we propose a regression⁃based bagging method to detect the faults in the network.The proposed bagging method is consisted of GRU(Gated Recurrent Unit)and Prophet model.Bagging allows weak learners to combine efforts to outperform a strong learner,hence it is appropriate to use in WSN.The proposed bagging method was first trained at the base station,then they were deployed at each SN(Sensor Node).Most of the common faults in WSN,such as transient,intermittent and permanent faults,were considered.The validity of the proposed scheme was tested using a trusted online published dataset.Using experimental studies,compared to the latest state⁃of⁃the⁃art machine learning models,the effectiveness of the proposed model is shown for fault detection.Performance evaluation in terms of false positive rate,accuracy,and false alarm rate shows the efficiency of the proposed algorithm.
基金funded by the National Natural Science Foundation of China(Grant No.52222708)。
文摘Accurately evaluating the safety status of lithium-ion battery systems in electric vehicles is imperative due to the challenges in effectively predicting potential battery failure risks under stochastic profiles.Complex battery fault mechanisms and limited poor-quality data collection impede fault detection for battery systems under real-world conditions.This paper proposes a novel graph-guided fault detection method designed to recognize concealed anomalies in realistic data.Graphs guided by physical relationships are constructed for learning the dynamic evolution of physical quantities under normal conditions and their potential change characteristics in fault scenarios.An ensemble Graph Sample and Aggregate Network model are developed to tackle sample distribution imbalances and non-uniformity battery system specifications across vehicles.Failure risk probabilities for diverse battery charging and discharging segments are derived.An ablation study verifies the necessity of ensemble learning in addressing imbalanced datasets.Analysis of 102,095 segments across 86 vehicles with different battery material systems,battery capacities,and numbers of cells and temperature sensors confirms the robustness and generalization of the proposed method,yielding a recall of 98.37%.By introducing the graph,spatio-temporal global fault characteristics of battery systems are automatically extracted.The coupling relationship and evolution of physical quantities under both normal and faulty states are established,effectively uncovering fault information hidden in collected battery data without observable anomalies.The safety state of battery systems is reflected in terms of failure risk probability,providing reliable data support for battery system maintenance.
基金National Key Research and Development Program of China(No.2017YFB1304001)。
文摘During the sizing process,yarn congestion fault occurs at the reed teeth of a sizing machine.At present,the yarn congestion fault is generally handled by manual detection.The sizing production line operates on a large scale and runs continuously.Untimely handling of the yarn congestion fault causes a large amount of yarn waste.In this research,a machine vision-based algorithm for yarn congestion fault detection is developed.Through the analysis of the congestion fault and interference contour characteristics,the basic idea of image phase subtraction to identify the congestion fault is determined.To address the interference information appearing after image phase subtraction,the image pre-processing methods of Canny edge extraction and mean filtering are employed.According to the fault size and location characteristics,the fault contour detection algorithm based on inter-frame difference is designed.To mitigate the camera vibration interference,the anti-vibration interference algorithm based on affine transformation is studied,and the fault detection algorithm for the total yarn congestion fault is determined.The detection of 20 sets of field data is carried out,and the detection rate reaches 90%.This fault detection algorithm realizes the automatic detection of yarn congestion fault of sizing machine with certain real-time performance and accuracy.
基金Fundamental Research Funds for the Central Universities(2023MS134)。
文摘In modern industrial applications,ensuring the reliability of mechanical fittings is critical for maintaining operational safety and efficiency,particularly in power grid systems where split pins serve a pivotal role despite being susceptible to environmental degradation and failure.Existing UAV-based inspection systems are hampered by a low representation of split pin elements and complex backgrounds,leading to challenges in accurate fault detection and timely maintenance.To address this pressing issue,our study proposes an innovative fault detection method for split pins.The approach employs a three-step process:first,cropping operations are used to accurately isolate the fittings containing split pins;second,super-resolution reconstruction is applied to enhance image clarity and detail;and finally,an improved YOLOv8 network,augmented with inner-shape IoU and local window attention mechanisms,is utilized to refine local feature extraction and annotation accuracy.Experimental evaluations on a split pin defect dataset demonstrate robust performance,achieving an accuracy rate of 72.1%and a mean average precision(mAP)of 67.7%,thereby validating the method’s effectiveness under challenging conditions.The proposed approach contributes to the field by specifically targeting the challenges associated with split pin detection in UAV-based inspections,offering a practically applicable and reliably precise method.
文摘Seismic data plays a pivotal role in fault detection,offering critical insights into subsurface structures and seismic hazards.Understanding fault detection from seismic data is essential for mitigating seismic risks and guiding land-use plans.This paper presents a comprehensive review of existing methodologies for fault detection,focusing on the application of Machine Learning(ML)and Deep Learning(DL)techniques to enhance accuracy and efficiency.Various ML and DL approaches are analyzed with respect to fault segmentation,adaptive learning,and fault detection models.These techniques,benchmarked against established seismic datasets,reveal significant improvements over classical methods in terms of accuracy and computational efficiency.Additionally,this review highlights emerging trends,including hybrid model applications and the integration of real-time data processing for seismic fault detection.By providing a detailed comparative analysis of current methodologies,this review aims to guide future research and foster advancements in the effectiveness and reliability of seismic studies.Ultimately,the study seeks to bridge the gap between theoretical investigations and practical implementations in fault detection.
基金the National Natural Science Foundation of China(NSFC)(62103283)the Australia Research Council’s Discovery Pro-jects Scheme(DP220100355).
文摘1.Background In the chemical industry,process plants-commonly referred to as plantwide systems-typically consist of many process units(unit operations).Driven by the considerable economic efficiency offered by complex and interactive process designs,modern plantwide systems are becoming increasingly sophisticated.The operation of these processes is typically characterized by the complexity of individual units(subsystems)and the intricate interactions between geographically distributed units through networks of material and energy flows,as well as control loops[1].
文摘Three-phase grid-connected inverters(GCIs)are essential components in distributed generation systems,where the accuracy of current measurement circuits is fundamental for reliable closed-loop operation.Nevertheless,the presence of a DC offset in the measured current can disrupt the regulation of grid currents and significantly degrade system performance.In this work,a fault-tolerant control approach is introduced to counteract the impact of such offset faults through a dedicated current compensation mechanism.The proposed solution is built around two main stages:(i)detecting and isolating DC offset faults that may appear in one or multiple phases of the measured grid currents,and(ii)estimating the fault magnitude and reconstructing the corrected current signal.The offset magnitude is obtained analytically by examining the grid current projected onto the synchronous d-axis at the grid angular frequency,eliminating the need for any additional sensing hardware.Simulation and experimental investigations conducted under several fault scenarios confirm the robustness of the proposed strategy and highlight significant improvements in detection speed and diagnostic accuracy.
基金supported by National Natural Science Foundation of China under Project 52437003 and 52421004in part by the National Key R&D Program of China under Project 2023YFB3406000in part by Heilongjiang Provincial Natural Science Foundation under Project YQ2022E029.
文摘Permanent-magnet synchronous machines(PMSMs)are widely used in robotics,rail transportation,and electric vehicles owing to their high power density,high efficiency,and high power factor.However,PMSMs often operate in harsh environments,where critical components such as windings and permanent magnets(PMs)are susceptible to failures.These faults can lead to a significant degradation in performance,posing substantial challenges to the reliable operation of PMSMs.This paper presents a comprehensive review of common fault types in PMSMs,along with their corresponding fault diagnosis and fault-tolerant control strategies.The underlying mechanisms of typical faults are systematically analyzed,followed by a detailed comparison of various diagnostic and fault-tolerant control methods to evaluate their respective advantages and limitations.Finally,the review concludes by identifying key research gaps in PMSM fault diagnosis and fault-tolerant control,while proposing potential future directions for advancing this field.
基金supported by the Program of National Natural Science Foundation of China(U23A20329,62163036)Youth Academic and Technical Leaders Reserve Talent Training project(202105AC160094)Industrial Innovation Talent Special Project of Xingdian Talent Support Program(XDYC-CYCX-2022-0010).
文摘Kernel-based slow feature analysis(SFA)methods have been successfully applied in the industrial process fault detection field.However,kernel-based SFA methods have high computational complexity as dealing with nonlinearity,leading to delays in detecting time-varying data features.Additionally,the uncertain kernel function and kernel parameters limit the ability of the extracted features to express process characteristics,resulting in poor fault detection performance.To alleviate the above problems,a novel randomized auto-regressive dynamic slow feature analysis(RRDSFA)method is proposed to simultaneously monitor the operating point deviations and process dynamic faults,enabling real-time monitoring of data features in industrial processes.Firstly,the proposed Random Fourier mappingbased method achieves more effective nonlinear transformation,contrasting with the current kernelbased RDSFA algorithm that may lead to significant computational complexity.Secondly,a randomized RDSFA model is developed to extract nonlinear dynamic slow features.Furthermore,a Bayesian inference-based overall fault monitoring model including all RRDSFA sub-models is developed to overcome the randomness of random Fourier mapping.Finally,the superiority and effectiveness of the proposed monitoring method are demonstrated through a numerical case and a simulation of continuous stirred tank reactor.
文摘In the field of gear fault detection,the symmetrized dot pattern(SDP)technique,combined with a convolutional neural network(CNN),is widely used to classify various types of defects.The SDP-CNN combination is used to transform vibration signals and simplify the defect classification process under stationary operating conditions.This work aims to enhance the SDP-CNN combination for detecting incipient defects in gear under variable working conditions.The vibration signals are filtered by Vold-Kalman Filter Multi-Order Tracking to highlight fault characteristics under variable working conditions.Subsequently,the signals are SDP-transformed and are then classified by optimized CNN.The new pipeline has been validated on an experimental dataset and compared with the classical one by developing both two-and multi-class CNNs.The results showed the applicability of the new pipeline in terms of percentage accuracy and ROC curve compared to the classical approach.Finally,the proposed pipeline was compared with other ML literature techniques using the same dataset.
文摘Fault sensing in wind turbine(WT)generator bearings is essential for ensuring reliability and holding down maintenance costs.Feeding raw sensor data to machine learning(ML)model often overlooks the enveloping interdependencies between system elements.This study proposes a new hybrid method that combines the domain knowledge via knowledge graphs(KGs)and the traditional feature-based data.Incorporation of contextual relationships through construction of graph embedding methods,such as Node2Vec,can capture meaningful information,such as the relationships among key parameters(e.g.wind speed,rotor Revolutions Per Minute(RPM),and temperature)in the enriched feature representations.These node embeddings,when augmented with the original data,can be used to allow the model to learn and generalize better.As shown in results achieved on experimental data,the augmented ML model(with KG)is much better at predicting with the help of accuracy and error measure compared to traditional ML methods.Paired t-test analysis proves the statistical validity of this improvement.Moreover,graph-based feature importance increases the interpretability of the model and helps to uncover the structurally significant variables that are otherwise ignored by the common methods.The approach provides an excellent,knowledge-guided manner through which intelligent fault detection can be executed on WT systems.
基金supported by Science and Technology Project of State Grid Corporation of China(52094024003D).
文摘As modern power systems grow in complexity,accurate and efficient fault detection has become increasingly important.While many existing reviews focus on a single modality,this paper presents a comprehensive survey from a dual-modality perspective-infrared imaging and voiceprint analysis-two complementary,non-contact techniques that capture different fault characteristics.Infrared imaging excels at detecting thermal anomalies,while voiceprint signals provide insight into mechanical vibrations and internal discharge phenomena.We review both traditional signal processing and deep learning-based approaches for each modality,categorized by key processing stages such as feature extraction and classification.The paper highlights how these modalities address distinct fault types and how they may be fused to improve robustness and accuracy.Representative datasets are summarized,and practical challenges such as noise interference,limited fault samples,and deployment constraints are discussed.By offering a cross-modal,comparative analysis,this work aims to bridge fragmented research and guide future development in intelligent fault detection systems.The review concludes with research trends including multimodal fusion,lightweight models,and self-supervised learning.
文摘This research aims to address the challenges of fault detection and isolation(FDI)in digital grids,focusing on improving the reliability and stability of power systems.Traditional fault detection techniques,such as rule-based fuzzy systems and conventional FDI methods,often struggle with the dynamic nature of modern grids,resulting in delays and inaccuracies in fault classification.To overcome these limitations,this study introduces a Hybrid NeuroFuzzy Fault Detection Model that combines the adaptive learning capabilities of neural networks with the reasoning strength of fuzzy logic.The model’s performance was evaluated through extensive simulations on the IEEE 33-bus test system,considering various fault scenarios,including line-to-ground faults(LGF),three-phase short circuits(3PSC),and harmonic distortions(HD).The quantitative results show that the model achieves 97.2%accuracy,a false negative rate(FNR)of 1.9%,and a false positive rate(FPR)of 2.3%,demonstrating its high precision in fault diagnosis.The qualitative analysis further highlights the model’s adaptability and its potential for seamless integration into smart grids,micro grids,and renewable energy systems.By dynamically refining fuzzy inference rules,the model enhances fault detection efficiency without compromising computational feasibility.These findings contribute to the development of more resilient and adaptive fault management systems,paving the way for advanced smart grid technologies.
基金supported by the National Key Research and Development Program of China(No.2023YFB4302804)the National Natural Science Foundation of China(Nos.U2233217,62371029,62471023,62301016,and 62101015)。
文摘The snapshot Fault Detection(FD)algorithm of Advanced Receiver Autonomous Integrity Monitoring(ARAIM)necessitates the allocation of continuity and integrity risk requirements from the operational exposure time level to the single epoch level.Current studies primarily focus on finding a conservative Number of Effective Samples(NES)as a risk mapping factor.However,considering that the NES varies with the observation environment and the type of the fault mode,applying a fixed NES can constrain the performance of the algorithm.To address this issue,the continuity and integrity risks over the operational exposure time are analyzed and bounded based on all epochs within the exposure time.A more adaptable method for continuity and integrity budget allocation over the operational exposure time is presented,capable of monitoring the continuity and integrity risks over the recent operational exposure time in real time,and dynamically adjusting the allocation values based on the current observation environment.Simulation results demonstrate that,compared with the allocation method based on a fixed NES,ARAIM based on the proposed allocation method exhibits superior performance in terms of the availability.At an FD execution frequency equal to the required Time-To-Alert(TTA),the dual-constellation H-ARAIM provides 100%of the global coverage with 99.5%availability of the RNP 0.1 service,and the dual-constellation V-ARAIM provides 86.38%of the global coverage with 99.5%availability of the LPV-200 service.
基金Supported by National Natural Science Foundation of China(Grant No.52205045)National Key Research and Development Program of China(Grant No.2021YFB2011300)+2 种基金Aeronautical Science Foundation of China(Grant No.2022Z029051001)Zhejiang Provincial Natural Science Foundation of China(Grant No.LZ24E050006)Research Fund of State Key Laboratory of Mechanics and Control for Aerospace Structures(Nanjing University of Aeronautics and Astronautics)(Grant No.MCAS-E-0224G01).
文摘The aircraft braking system is critical to ensure the safe take-off and landing of the aircraft.However,the braking system is often exposed to high temperatures and strong vibration working environments,which makes the sensor prone to failure.Sensor failure has the potential to compromise aircraft safety.In order to improve the safety of the aircraft braking system,a fault detection and fault-tolerant control(FDFTC)strategy for the aircraft brake pressure sensor is designed.Firstly,a model based on a bidirectional long short-term memory(Bi-LSTM)network is constructed to estimate the brake pressure.Then,the residual sequence is obtained by comparing the measured pressure with the estimated pressure.On this basis,the improved sequential probability ratio test(SPRT)method based on mathematical statistics is applied to analyze the residual sequence to detect the fault.Finally,simulation and hardware-in-the-loop(HIL)testing results indicate that the proposed FDFTC strategy can detect sensor faults in time and efficiently complete braking when faults occur.Hence,the proposed FDFTC strategy can effectively deal with the faults of the aircraft brake pressure sensor,which is of great significance to improve the reliability and safety of the aircraft.
基金the National Natural Science Foundation of China(Grant Nos.62303380,62176214,62101590,62003268)the Aeronautical Science Foundation of China(Grant No.201907053001).
文摘This research focuses on detecting faults in flight vehicles with unstable subsystems operating asynchronously.By accounting for asynchronous switching,a switched model is established,and filters for fault detection(FD)in unstable subsystems are developed.The FD challenge is then transformed into an H∞filtering issue.Utilizing the multiple discontinuous Lyapunov function(MDLF)approach and the mode-dependent average dwell time(MDADT)method,sufficient conditions are derived to ensure stability during both fast and slow switching.Furthermore,the existence and solutions for FD filters are provided through linear matrix inequalities(LMIs).The simulation outcomes demonstrated the excellent performance of the developed method in studied cases.
基金supported by the National Natural Science Foundation of China(No.62303293,62303414)the China Postdoctoral Science Foundation(No.2023M732176,2023M741821)the Zhejiang Province Postdoctoral Selected Foundation(No.ZJ2023143).
文摘Test selection design(TSD)is an important technique for improving product maintainability,reliability and reducing lifecycle costs.In recent years,although some researchers have addressed the design problem of test selection,the correlation between test outcomes has not been sufficiently considered in test metrics modeling.This study proposes a new approach that combines copula and D-Vine copula to address the correlation issue in TSD.First,the copula is utilized to model FIR on the joint distribution.Furthermore,the D-Vine copula is applied to model the FDR and FAR.Then,a particle swarm optimization is employed to select the optimal testing scheme.Finally,the efficacy of the proposed method is validated through experimentation on a negative feedback circuit.
