Computer-empowered detection of possible faults for Heating,Ventilation and Air-Conditioning(HVAC)subsystems,e.g.,chillers,is one of the most important applications in Artificial Intelligence(AI)integrated Internet of...Computer-empowered detection of possible faults for Heating,Ventilation and Air-Conditioning(HVAC)subsystems,e.g.,chillers,is one of the most important applications in Artificial Intelligence(AI)integrated Internet of Things(IoT).The cyber-physical system greatly enhances the safety and security of the working facilities,reducing time,saving energy and protecting humans’health.Under the current trends of smart building design and energy management optimization,Automated Fault Detection and Diagnosis(AFDD)of chillers integrated with IoT is highly demanded.Recent studies show that standard machine learning techniques,such as Principal Component Analysis(PCA),Support Vector Machine(SVM)and tree-structure-based algorithms,are useful in capturing various chiller faults with high accuracy rates.With the fast development of deep learning technology,Convolutional Neural Networks(CNNs)have been widely and successfully applied to various fields.However,for chiller AFDD,few existing works are adopting CNN and its extensions in the feature extraction and classification processes.In this study,we propose to perform chiller FDD using a CNN-based approach.The proposed approach has two distinct advantages over existing machine learning-based chiller AFDD methods.First,the CNN-based approach does not require the feature selection/extraction process.Since CNN is reputable with its feature extraction capability,the feature extraction and classification processes are merged,leading to a more neat AFDD framework compared to traditional approaches.Second,the classification accuracy is significantly improved compared to traditional methods using the CNN-based approach.展开更多
Quantized fault detection for sensor/actuator faults of networked control systems （NCSs） with time delays both in the sensor-to-controller channel and controller-to-actuator channel is concerned in this paper. A fau...Quantized fault detection for sensor/actuator faults of networked control systems （NCSs） with time delays both in the sensor-to-controller channel and controller-to-actuator channel is concerned in this paper. A fault model is set up based on the possible cases of sensor/atuator faults. Then, the model predictive control is used to compensate the time delay. When the sensors and actuators are healthy, an H stability criterion of the state predictive observer is obtained in terms of linear matrix inequality. A new threshold computational method that conforms to the actual situation is proposed. Then, the thresholds of the false alarm rate （FAR） and miss detection rate （MDR） are presented by using our proposed method, which are also compared with the ones given in the existin~ literatures. Finally, some numerical simulations are shown to demonstrate the effectiveness of the proposed method.展开更多
Efficient optical network management poses significant importance in backhaul and access network communicationfor preventing service disruptions and ensuring Quality of Service(QoS)satisfaction.The emerging faultsin o...Efficient optical network management poses significant importance in backhaul and access network communicationfor preventing service disruptions and ensuring Quality of Service(QoS)satisfaction.The emerging faultsin optical networks introduce challenges that can jeopardize the network with a variety of faults.The existingliterature witnessed various partial or inadequate solutions.On the other hand,Machine Learning(ML)hasrevolutionized as a promising technique for fault detection and prevention.Unlike traditional fault managementsystems,this research has three-fold contributions.First,this research leverages the ML and Deep Learning(DL)multi-classification system and evaluates their accuracy in detecting six distinct fault types,including fiber cut,fibereavesdropping,splicing,bad connector,bending,and PC connector.Secondly,this paper assesses the classificationdelay of each classification algorithm.Finally,this work proposes a fiber optics fault prevention algorithm thatdetermines to mitigate the faults accordingly.This work utilized a publicly available fiber optics dataset namedOTDR_Data and applied different ML classifiers,such as Gaussian Naive Bayes(GNB),Logistic Regression(LR),Support Vector Machine(SVM),K-Nearest Neighbor(KNN),Random Forest(RF),and Decision Tree(DT).Moreover,Ensemble Learning(EL)techniques are applied to evaluate the accuracy of various classifiers.In addition,this work evaluated the performance of DL-based Convolutional Neural Network and Long-Short Term Memory(CNN-LSTM)hybrid classifier.The findings reveal that the CNN-LSTM hybrid technique achieved the highestaccuracy of 99%with a delay of 360 s.On the other hand,EL techniques improved the accuracy in detecting fiberoptic faults.Thus,this research comprehensively assesses accuracy and delay metrics for various classifiers andproposes the most efficient attack detection system in fiber optics.展开更多
It is significant to detect the fault type and assess the fault level as early as possible for avoiding catastrophic accidents.Due to diversity and complexity,the compound faults detection of rotating machinery under ...It is significant to detect the fault type and assess the fault level as early as possible for avoiding catastrophic accidents.Due to diversity and complexity,the compound faults detection of rotating machinery under non-stationary operation turns to be a challenging task.Multiwavelet with two or more base functions may match two or more features of compound faults,which may supply a possible solution to compound faults detection.However,the fixed basis functions of multiwavelet transform,which are not related with the vibration signal,may reduce the accuracy of compound faults detection.Moreover,the decomposition results of multiwavelet transform not being own time-invariant is harmful to extract the features of periodical impulses.Furthermore,multiwavelet transform only focuses on the multi-resolution analysis in the low frequency band,and may leave out the useful features of compound faults.To overcome these shortcomings,a novel method called adaptive redundant multiwavelet packet(ARMP) is proposed based on the two-scale similarity transforms.Besides,the relative energy ratio at the characteristic frequency of the concerned component is computed to select the sensitive frequency bands of multiwavelet packet coefficients.The proposed method was used to analyze the compound faults of rolling element bearing.The results showed that the proposed method could enhance the ability of compound faults detection of rotating machinery.展开更多
The current morphological wavelet technologies utilize a fixed filter or a linear decomposition algorithm, which cannot cope with the sudden changes, such as impulses or edges in a signal effectively. This paper pre- ...The current morphological wavelet technologies utilize a fixed filter or a linear decomposition algorithm, which cannot cope with the sudden changes, such as impulses or edges in a signal effectively. This paper pre- sents a novel signal processing scheme, adaptive morpho- logical update lifting wavelet （AMULW）, for rolling element bearing fault detection. In contrast with the widely used morphological wavelet, the filters in AMULW are no longer fixed. Instead, the AMULW adaptively uses a morphological dilation-erosion filter or an average filter as the update lifting filter to modify the approximation signal. Moreover, the nonlinear morphological filter is utilized to substitute the traditional linear filter in AMULW. The effectiveness of the proposed AMULW is evaluated using a simulated vibration signal and experimental vibration sig- nals collected from a bearing test rig. Results show that the proposed method has a superior performance in extracting fault features of defective roiling element bearings.展开更多
With the complexity of integrated circuits is continually increasing, a local defect in circuits may cause multiple faults. The behavior of a digital circuit with a multiple fault may significantly differ from that of...With the complexity of integrated circuits is continually increasing, a local defect in circuits may cause multiple faults. The behavior of a digital circuit with a multiple fault may significantly differ from that of a single fault. A new method for the detection of multiple faults in digital circuits is presented in this paper, the method is based on binary decision diagram （BDD）. First of all, the BDDs for the normal circuit and faulty circuit are built respectively. Secondly, a test BDD is obtained by the XOR operation of the BDDs corresponds to normal circuit and faulty circuit. In the test BDD, each input assignment that leads to the leaf node labeled 1 is a test vector of multiple faults. Therefore, the test set of multiple faults is generated by searching for the type of input assignments in the test BDD. Experimental results on some digital circuits show the feasibility of the approach presented in this paper.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
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
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
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
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
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
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
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
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
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
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
The reliability and efficiency of photovoltaic(PV)systems are essential for sustainable energy produc-tion,requiring accurate fault detection to minimize energy losses.This study proposes a hybrid model integrating Ne...The reliability and efficiency of photovoltaic(PV)systems are essential for sustainable energy produc-tion,requiring accurate fault detection to minimize energy losses.This study proposes a hybrid model integrating Neighborhood Components Analysis(NCA)with a Convolutional Neural Network(CNN)to improve fault detection and diagnosis.Unlike Principal Component Analysis(PCA),which may compromise class relationships during feature extraction,NCA preserves these relationships,enhancing classification performance.The hybrid model combines NCA with CNN,a fundamental deep learning architecture,to enhance fault detection and diagnosis capabilities.The performance of the proposed NCA-CNN model was evaluated against other models.The experimental evaluation demonstrates that the NCA-CNN model outperforms existing methods,achieving 100%fault detection accuracy and 99%fault diagnosis accuracy.These findings underscore the model’s potential in improving PV system reliability and efficiency.展开更多
基金supported by two Ministry of Education(MoE)Singapore Tier 1 research grants under grant numbers R-296-000-208-133 and R-296-000-241-114.
文摘Computer-empowered detection of possible faults for Heating,Ventilation and Air-Conditioning(HVAC)subsystems,e.g.,chillers,is one of the most important applications in Artificial Intelligence(AI)integrated Internet of Things(IoT).The cyber-physical system greatly enhances the safety and security of the working facilities,reducing time,saving energy and protecting humans’health.Under the current trends of smart building design and energy management optimization,Automated Fault Detection and Diagnosis(AFDD)of chillers integrated with IoT is highly demanded.Recent studies show that standard machine learning techniques,such as Principal Component Analysis(PCA),Support Vector Machine(SVM)and tree-structure-based algorithms,are useful in capturing various chiller faults with high accuracy rates.With the fast development of deep learning technology,Convolutional Neural Networks(CNNs)have been widely and successfully applied to various fields.However,for chiller AFDD,few existing works are adopting CNN and its extensions in the feature extraction and classification processes.In this study,we propose to perform chiller FDD using a CNN-based approach.The proposed approach has two distinct advantages over existing machine learning-based chiller AFDD methods.First,the CNN-based approach does not require the feature selection/extraction process.Since CNN is reputable with its feature extraction capability,the feature extraction and classification processes are merged,leading to a more neat AFDD framework compared to traditional approaches.Second,the classification accuracy is significantly improved compared to traditional methods using the CNN-based approach.
基金supported by National Natural Science Foundation of China(No.61074065)Natural Science Foundation of Hebei Province(No.F2012203184)Specialized Research Fund for the Doctoral Program of Higher Education of China(No.20111333120009)
文摘Quantized fault detection for sensor/actuator faults of networked control systems （NCSs） with time delays both in the sensor-to-controller channel and controller-to-actuator channel is concerned in this paper. A fault model is set up based on the possible cases of sensor/atuator faults. Then, the model predictive control is used to compensate the time delay. When the sensors and actuators are healthy, an H stability criterion of the state predictive observer is obtained in terms of linear matrix inequality. A new threshold computational method that conforms to the actual situation is proposed. Then, the thresholds of the false alarm rate （FAR） and miss detection rate （MDR） are presented by using our proposed method, which are also compared with the ones given in the existin~ literatures. Finally, some numerical simulations are shown to demonstrate the effectiveness of the proposed method.
基金in part by the National Natural Science Foundation of China under Grants 62271079,61875239,62127802in part by the Fundamental Research Funds for the Central Universities under Grant 2023PY01+1 种基金in part by the National Key Research and Development Program of China under Grant 2018YFB2200903in part by the Beijing Nova Program with Grant Number Z211100002121138.
文摘Efficient optical network management poses significant importance in backhaul and access network communicationfor preventing service disruptions and ensuring Quality of Service(QoS)satisfaction.The emerging faultsin optical networks introduce challenges that can jeopardize the network with a variety of faults.The existingliterature witnessed various partial or inadequate solutions.On the other hand,Machine Learning(ML)hasrevolutionized as a promising technique for fault detection and prevention.Unlike traditional fault managementsystems,this research has three-fold contributions.First,this research leverages the ML and Deep Learning(DL)multi-classification system and evaluates their accuracy in detecting six distinct fault types,including fiber cut,fibereavesdropping,splicing,bad connector,bending,and PC connector.Secondly,this paper assesses the classificationdelay of each classification algorithm.Finally,this work proposes a fiber optics fault prevention algorithm thatdetermines to mitigate the faults accordingly.This work utilized a publicly available fiber optics dataset namedOTDR_Data and applied different ML classifiers,such as Gaussian Naive Bayes(GNB),Logistic Regression(LR),Support Vector Machine(SVM),K-Nearest Neighbor(KNN),Random Forest(RF),and Decision Tree(DT).Moreover,Ensemble Learning(EL)techniques are applied to evaluate the accuracy of various classifiers.In addition,this work evaluated the performance of DL-based Convolutional Neural Network and Long-Short Term Memory(CNN-LSTM)hybrid classifier.The findings reveal that the CNN-LSTM hybrid technique achieved the highestaccuracy of 99%with a delay of 360 s.On the other hand,EL techniques improved the accuracy in detecting fiberoptic faults.Thus,this research comprehensively assesses accuracy and delay metrics for various classifiers andproposes the most efficient attack detection system in fiber optics.
基金supported by the National Natural Science Foundation of China (Grant Nos. 50975220 and 51035007)the National Basic Research Program of China ("973" Program) (Grant No. 2009CB724405)the Important National Science and Technology Specific Projects (Grant No.2010ZX04014-016)
文摘It is significant to detect the fault type and assess the fault level as early as possible for avoiding catastrophic accidents.Due to diversity and complexity,the compound faults detection of rotating machinery under non-stationary operation turns to be a challenging task.Multiwavelet with two or more base functions may match two or more features of compound faults,which may supply a possible solution to compound faults detection.However,the fixed basis functions of multiwavelet transform,which are not related with the vibration signal,may reduce the accuracy of compound faults detection.Moreover,the decomposition results of multiwavelet transform not being own time-invariant is harmful to extract the features of periodical impulses.Furthermore,multiwavelet transform only focuses on the multi-resolution analysis in the low frequency band,and may leave out the useful features of compound faults.To overcome these shortcomings,a novel method called adaptive redundant multiwavelet packet(ARMP) is proposed based on the two-scale similarity transforms.Besides,the relative energy ratio at the characteristic frequency of the concerned component is computed to select the sensitive frequency bands of multiwavelet packet coefficients.The proposed method was used to analyze the compound faults of rolling element bearing.The results showed that the proposed method could enhance the ability of compound faults detection of rotating machinery.
基金Supported by National Natural Science Foundation of China(51705431,51375078)Natural Sciences and Engineering Research Council of Canada(RGPIN-2015-04897)
文摘The current morphological wavelet technologies utilize a fixed filter or a linear decomposition algorithm, which cannot cope with the sudden changes, such as impulses or edges in a signal effectively. This paper pre- sents a novel signal processing scheme, adaptive morpho- logical update lifting wavelet （AMULW）, for rolling element bearing fault detection. In contrast with the widely used morphological wavelet, the filters in AMULW are no longer fixed. Instead, the AMULW adaptively uses a morphological dilation-erosion filter or an average filter as the update lifting filter to modify the approximation signal. Moreover, the nonlinear morphological filter is utilized to substitute the traditional linear filter in AMULW. The effectiveness of the proposed AMULW is evaluated using a simulated vibration signal and experimental vibration sig- nals collected from a bearing test rig. Results show that the proposed method has a superior performance in extracting fault features of defective roiling element bearings.
基金Supported by the National Natural Science Foun-dation of China (60006002) Natural Science Research Project of Education Department of Guangdong Province of China (02019)
文摘With the complexity of integrated circuits is continually increasing, a local defect in circuits may cause multiple faults. The behavior of a digital circuit with a multiple fault may significantly differ from that of a single fault. A new method for the detection of multiple faults in digital circuits is presented in this paper, the method is based on binary decision diagram （BDD）. First of all, the BDDs for the normal circuit and faulty circuit are built respectively. Secondly, a test BDD is obtained by the XOR operation of the BDDs corresponds to normal circuit and faulty circuit. In the test BDD, each input assignment that leads to the leaf node labeled 1 is a test vector of multiple faults. Therefore, the test set of multiple faults is generated by searching for the type of input assignments in the test BDD. Experimental results on some digital circuits show the feasibility of the approach presented in this paper.
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.
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.
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.
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.
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.
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.
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The reliability and efficiency of photovoltaic(PV)systems are essential for sustainable energy produc-tion,requiring accurate fault detection to minimize energy losses.This study proposes a hybrid model integrating Neighborhood Components Analysis(NCA)with a Convolutional Neural Network(CNN)to improve fault detection and diagnosis.Unlike Principal Component Analysis(PCA),which may compromise class relationships during feature extraction,NCA preserves these relationships,enhancing classification performance.The hybrid model combines NCA with CNN,a fundamental deep learning architecture,to enhance fault detection and diagnosis capabilities.The performance of the proposed NCA-CNN model was evaluated against other models.The experimental evaluation demonstrates that the NCA-CNN model outperforms existing methods,achieving 100%fault detection accuracy and 99%fault diagnosis accuracy.These findings underscore the model’s potential in improving PV system reliability and efficiency.
