The widespread adoption of the Internet of Things (IoT) has transformed various sectors globally, making themmore intelligent and connected. However, this advancement comes with challenges related to the effectiveness...The widespread adoption of the Internet of Things (IoT) has transformed various sectors globally, making themmore intelligent and connected. However, this advancement comes with challenges related to the effectiveness ofIoT devices. These devices, present in offices, homes, industries, and more, need constant monitoring to ensuretheir proper functionality. The success of smart systems relies on their seamless operation and ability to handlefaults. Sensors, crucial components of these systems, gather data and contribute to their functionality. Therefore,sensor faults can compromise the system’s reliability and undermine the trustworthiness of smart environments.To address these concerns, various techniques and algorithms can be employed to enhance the performance ofIoT devices through effective fault detection. This paper conducted a thorough review of the existing literature andconducted a detailed analysis.This analysis effectively links sensor errors with a prominent fault detection techniquecapable of addressing them. This study is innovative because it paves theway for future researchers to explore errorsthat have not yet been tackled by existing fault detection methods. Significant, the paper, also highlights essentialfactors for selecting and adopting fault detection techniques, as well as the characteristics of datasets and theircorresponding recommended techniques. Additionally, the paper presents amethodical overview of fault detectiontechniques employed in smart devices, including themetrics used for evaluation. Furthermore, the paper examinesthe body of academic work related to sensor faults and fault detection techniques within the domain. This reflectsthe growing inclination and scholarly attention of researchers and academicians toward strategies for fault detectionwithin the realm of the Internet of Things.展开更多
Deep learning has emerged in many practical applications,such as image classification,fault diagnosis,and object detection.More recently,convolutional neural networks(CNNs),representative models of deep learning,have ...Deep learning has emerged in many practical applications,such as image classification,fault diagnosis,and object detection.More recently,convolutional neural networks(CNNs),representative models of deep learning,have been used to solve fault detection.However,the current design of CNNs for fault detection of wind turbine blades is highly dependent on domain knowledge and requires a large amount of trial and error.For this reason,an evolutionary YOLOv8 network has been developed to automatically find the network architecture for wind turbine blade-based fault detection.YOLOv8 is a CNN-backed object detection model.Specifically,to reduce the parameter count,we first design an improved FasterNet module based on the Partial Convolution(PConv)operator.Then,to enhance convergence performance,we improve the loss function based on the efficient complete intersection over the union.Based on this,a flexible variable-length encoding is proposed,and the corresponding reproduction operators are designed.Related experimental results confirmthat the proposed approach can achieve better fault detection results and improve by 2.6%in mean precision at 50(mAP50)compared to the existing methods.Additionally,compared to training with the YOLOv8n model,the YOLOBFE model reduces the training parameters by 933,937 and decreases the GFLOPS(Giga Floating Point Operations Per Second)by 1.1.展开更多
Electrolysis tanks are used to smeltmetals based on electrochemical principles,and the short-circuiting of the pole plates in the tanks in the production process will lead to high temperatures,thus affecting normal pr...Electrolysis tanks are used to smeltmetals based on electrochemical principles,and the short-circuiting of the pole plates in the tanks in the production process will lead to high temperatures,thus affecting normal production.Aiming at the problems of time-consuming and poor accuracy of existing infrared methods for high-temperature detection of dense pole plates in electrolysis tanks,an infrared dense pole plate anomalous target detection network YOLOv5-RMF based on You Only Look Once version 5(YOLOv5)is proposed.Firstly,we modified the Real-Time Enhanced Super-Resolution Generative Adversarial Network(Real-ESRGAN)by changing the U-shaped network(U-Net)to Attention U-Net,to preprocess the images;secondly,we propose a new Focus module that introduces the Marr operator,which can provide more boundary information for the network;again,because Complete Intersection over Union(CIOU)cannot accommodate target borders that are increasing and decreasing,replace CIOU with Extended Intersection over Union(EIOU),while the loss function is changed to Focal and Efficient IOU(Focal-EIOU)due to the different difficulty of sample detection.On the homemade dataset,the precision of our method is 94%,the recall is 70.8%,and the map@.5 is 83.6%,which is an improvement of 1.3%in precision,9.7%in recall,and 7%in map@.5 over the original network.The algorithm can meet the needs of electrolysis tank pole plate abnormal temperature detection,which can lay a technical foundation for improving production efficiency and reducing production waste.展开更多
Accurate and reliable fault detection is essential for the safe operation of electric vehicles.Support vector data description(SVDD)has been widely used in the field of fault detection.However,constructing the hypersp...Accurate and reliable fault detection is essential for the safe operation of electric vehicles.Support vector data description(SVDD)has been widely used in the field of fault detection.However,constructing the hypersphere boundary only describes the distribution of unlabeled samples,while the distribution of faulty samples cannot be effectively described and easilymisses detecting faulty data due to the imbalance of sample distribution.Meanwhile,selecting parameters is critical to the detection performance,and empirical parameterization is generally timeconsuming and laborious and may not result in finding the optimal parameters.Therefore,this paper proposes a semi-supervised data-driven method based on which the SVDD algorithm is improved and achieves excellent fault detection performance.By incorporating faulty samples into the underlying SVDD model,training deals better with the problem of missing detection of faulty samples caused by the imbalance in the distribution of abnormal samples,and the hypersphere boundary ismodified to classify the samplesmore accurately.The Bayesian Optimization NSVDD(BO-NSVDD)model was constructed to quickly and accurately optimize hyperparameter combinations.In the experiments,electric vehicle operation data with four common fault types are used to evaluate the performance with other five models,and the results show that the BO-NSVDD model presents superior detection performance for each type of fault data,especially in the imperceptible early and minor faults,which has seen very obvious advantages.Finally,the strong robustness of the proposed method is verified by adding different intensities of noise in the dataset.展开更多
Fault diagnosis of traction systems is important for the safety operation of high-speed trains.Long-term operation of the trains will degrade the performance of systems,which decreases the fault detection accuracy.To ...Fault diagnosis of traction systems is important for the safety operation of high-speed trains.Long-term operation of the trains will degrade the performance of systems,which decreases the fault detection accuracy.To solve this problem,this paper proposes a fault detection method developed by a Generalized Autoencoder(GAE)for systems with performance degradation.The advantage of this method is that it can accurately detect faults when the traction system of high-speed trains is affected by performance degradation.Regardless of the probability distribution,it can handle any data,and the GAE has extremely high sensitivity in anomaly detection.Finally,the effectiveness of this method is verified through the Traction Drive Control System(TDCS)platform.At different performance degradation levels,our method’s experimental results are superior to traditional methods.展开更多
This paper examines the progression and advancements in fault detection techniques for photovoltaic (PV) panels, a target for optimizing the efficiency and longevity of solar energy systems. As the adoption of PV tech...This paper examines the progression and advancements in fault detection techniques for photovoltaic (PV) panels, a target for optimizing the efficiency and longevity of solar energy systems. As the adoption of PV technology grows, the need for effective fault detection strategies becomes increasingly paramount to maximize energy output and minimize operational downtimes of solar power systems. These approaches include the use of machine learning and deep learning methodologies to be able to detect the identified faults in PV technology. Here, we delve into how machine learning models, specifically kernel-based extreme learning machines and support vector machines, trained on current-voltage characteristic (I-V curve) data, provide information on fault identification. We explore deep learning approaches by taking models like EfficientNet-B0, which looks at infrared images of solar panels to detect subtle defects not visible to the human eye. We highlight the utilization of advanced image processing techniques and algorithms to exploit aerial imagery data, from Unmanned Aerial Vehicles (UAVs), for inspecting large solar installations. Some other techniques like DeepLabV3 , Feature Pyramid Networks (FPN), and U-Net will be detailed as such tools enable effective segmentation and anomaly detection in aerial panel images. Finally, we discuss implications of these technologies on labor costs, fault detection precision, and sustainability of PV installations.展开更多
The in-core self-powered neutron detector(SPND)acts as a key measuring device for the monitoring of parameters and evaluation of the operating conditions of nuclear reactors.Prompt detection and tolerance of faulty SP...The in-core self-powered neutron detector(SPND)acts as a key measuring device for the monitoring of parameters and evaluation of the operating conditions of nuclear reactors.Prompt detection and tolerance of faulty SPNDs are indispensable for reliable reactor management.To completely extract the correlated state information of SPNDs,we constructed a twin model based on a generalized regression neural network(GRNN)that represents the common relationships among overall signals.Faulty SPNDs were determined because of the functional concordance of the twin model and real monitoring sys-tems,which calculated the error probability distribution between the model outputs and real values.Fault detection follows a tolerance phase to reinforce the stability of the twin model in the case of massive failures.A weighted K-nearest neighbor model was employed to reasonably reconstruct the values of the faulty signals and guarantee data purity.The experimental evaluation of the proposed method showed promising results,with excellent output consistency and high detection accuracy for both single-and multiple-point faulty SPNDs.For unexpected excessive failures,the proposed tolerance approach can efficiently repair fault behaviors and enhance the prediction performance of the twin model.展开更多
The complex working conditions and nonlinear characteristics of the motor drive control system of industrial robots make it difficult to detect faults.In this paper,a deep learning-based observer,which combines the co...The complex working conditions and nonlinear characteristics of the motor drive control system of industrial robots make it difficult to detect faults.In this paper,a deep learning-based observer,which combines the convolutional neural network(CNN)and the long short-term memory network(LSTM),is employed to approximate the nonlinear driving control system.CNN layers are introduced to extract dynamic features of the data,whereas LSTM layers perform time-sequential prediction of the target system.In terms of application,normal samples are fed into the observer to build an offline prediction model for the target system.The trained CNN-LSTM-based observer is then deployed along with the target system to estimate the system outputs.Online fault detection can be realized by analyzing the residuals.Finally,an application of the proposed fault detection method to a brushless DC motor drive system is given to verify the effectiveness of the proposed scheme.Simulation results indicate the impressive fault detection capability of the presented method for driving control systems of industrial robots.展开更多
Expert knowledge is the key to modeling milling fault detection systems based on the belief rule base.The construction of an initial expert knowledge base seriously affects the accuracy and interpretability of the mil...Expert knowledge is the key to modeling milling fault detection systems based on the belief rule base.The construction of an initial expert knowledge base seriously affects the accuracy and interpretability of the milling fault detection model.However,due to the complexity of the milling system structure and the uncertainty of the milling failure index,it is often impossible to construct model expert knowledge effectively.Therefore,a milling system fault detection method based on fault tree analysis and hierarchical BRB(FTBRB)is proposed.Firstly,the proposed method uses a fault tree and hierarchical BRB modeling.Through fault tree analysis(FTA),the logical correspondence between FTA and BRB is sorted out.This can effectively embed the FTA mechanism into the BRB expert knowledge base.The hierarchical BRB model is used to solve the problem of excessive indexes and avoid combinatorial explosion.Secondly,evidence reasoning(ER)is used to ensure the transparency of the model reasoning process.Thirdly,the projection covariance matrix adaptation evolutionary strategies(P-CMA-ES)is used to optimize the model.Finally,this paper verifies the validity model and the method’s feasibility techniques for milling data sets.展开更多
This work presents a novel wavelet-based denoising technique for improving the signal-to-noise ratio(SNR)of nonsteady vibration signals in hardware redundant systems.The proposed method utilizes the relationship betwe...This work presents a novel wavelet-based denoising technique for improving the signal-to-noise ratio(SNR)of nonsteady vibration signals in hardware redundant systems.The proposed method utilizes the relationship between redundant hardware components to effectively separate fault-related components from the vibration signature,thus enhancing fault detection accuracy.The study evaluates the proposed technique on two mechanically identical subsystems that are simultaneously controlled under the same speed and load inputs,with and without the proposed denoising step.The results demonstrate an increase in detection accuracy when incorporating the proposed denoising method into a fault detection system designed for hardware redundant machinery.This work is original in its application of a new method for improving performance when using residual analysis for fault detection in hardware redundant machinery configurations.Moreover,the proposed methodology is applicable to nonstationary equipment that experiences changes in both speed and load.展开更多
Considering packet losses, time-varying delay, and parameter uncertainty in the switched fuzzy system, this paper designs a robust fault detection filter at any switching rate and analyzes the H∞ performance of the s...Considering packet losses, time-varying delay, and parameter uncertainty in the switched fuzzy system, this paper designs a robust fault detection filter at any switching rate and analyzes the H∞ performance of the system. Firstly, the Takagi-Sugeno(T-S) fuzzy model is used to establish a global fuzzy model for the uncertain nonlinear time-delay switched system,and the packet loss process is modeled as a mathematical model satisfying Bernoulli distribution. Secondly, through the average dwell time method and multiple Lyapunov functions, the exponentially stable condition of the nonlinear network switched system is given. Finally, specific parameters of the robust fault detection filter can be obtained by solving linear matrix inequalities(LMIs). The effectiveness of the method is verified by simulation results.展开更多
Railway turnout is one of the critical equipment of Switch&Crossing(S&C)Systems in railway,related to the train’s safety and operation efficiency.With the advancement of intelligent sensors,data-driven fault ...Railway turnout is one of the critical equipment of Switch&Crossing(S&C)Systems in railway,related to the train’s safety and operation efficiency.With the advancement of intelligent sensors,data-driven fault detection technology for railway turnout has become an important research topic.However,little research in the literature has investigated the capability of data-driven fault detection technology for metro railway turnout.This paper presents a convolutional autoencoder-based fault detection method for the metro railway turnout considering human field inspection scenarios.First,the one-dimensional original time-series signal is converted into a twodimensional image by data pre-processing and 2D representation.Next,a binary classification model based on the convolutional autoencoder is developed to implement fault detection.The profile and structure information can be captured by processing data as images.The performance of our method is evaluated and tested on real-world operational current data in themetro stations.Experimental results show that the proposedmethod achieves better performance,especially in terms of error rate and specificity,and is robust in practical engineering applications.展开更多
Wireless Sensor Networks(WSNs)gather data in physical environments,which is some type.These ubiquitous sensors face several challenges responsible for corrupting them(mostly sensor failure and intrusions in external a...Wireless Sensor Networks(WSNs)gather data in physical environments,which is some type.These ubiquitous sensors face several challenges responsible for corrupting them(mostly sensor failure and intrusions in external agents).WSNs were disposed to error,and effectual fault detection techniques are utilized for detecting faults from WSNs in a timely approach.Machine learning(ML)was extremely utilized for detecting faults in WSNs.Therefore,this study proposes a billiards optimization algorithm with modified deep learning for fault detection(BIOMDL-FD)in WSN.The BIOMDLFD technique mainly concentrates on identifying sensor faults to enhance network efficiency.To do so,the presented BIOMDL-FD technique uses the attention-based bidirectional long short-term memory(ABLSTM)method for fault detection.In the ABLSTM model,the attention mechanism enables us to learn the relationships between the inputs and modify the probability to give more attention to essential features.At the same time,the BIO algorithm is employed for optimal hyperparameter tuning of the ABLSTM model,which is stimulated by billiard games,showing the novelty of the work.Experimental analyses are made to affirm the enhanced fault detection outcomes of the BIOMDL-FD technique.Detailed simulation results demonstrate the improvement of the BIOMDL-FD technique over other models with a maximum classification accuracy of 99.37%.展开更多
Aiming at the fact that the rotor winding inter-turn weak faults can hardly be detected due to the strong electromagnetic coupling effect in the excitation system,an interval observer based on current residual is desi...Aiming at the fact that the rotor winding inter-turn weak faults can hardly be detected due to the strong electromagnetic coupling effect in the excitation system,an interval observer based on current residual is designed.Firstly,the mechanism of the inter-turn short circuit of the rotor winding in the excitation system is modeled under the premise of stable working conditions,and electromagnetic decoupling and system simplification are carried out through Park Transform.An interval observer is designed based on the current residual in the two-phase coordinate system,and the sensitive and stable conditions of the observer is preset.The fault diagnosis process based on the interval observer is formulated,and the observer gain matrix is convexly optimized by linear matrix inequality.The numerical simulation and experimental results show that the inter-turn short circuit weak fault is hardly detected directly through the current signal,but the fault is quickly and accurately diagnosed through the residual internal observer.Compared with the traditional fault diagnosis method based on excitation current,the diagnosis speed and accuracy are greatly improved,and the probability of misdiagnosis also decreases.This method provides a theoretical basis for weak fault identification of excitation systems,and is of great significance for the operation and maintenance of excitation systems.展开更多
With the development of the technology of the Internet of Things,more and more operational data can be collected from air conditioning systems.Unfortunately,the most of existing air conditioning controllers mainly pro...With the development of the technology of the Internet of Things,more and more operational data can be collected from air conditioning systems.Unfortunately,the most of existing air conditioning controllers mainly provide controlling functions more than storing,processing or computing the measured data.This study develops an online fault detection configuration on the equipment side of air conditioning systems to realize these functions.Modbus communication is served to collect real-time operational data.The calculating programs are embedded to identify whether the measured signals exceed their limits or not,and to detect if sensor reading is frozen and other faults in relation to the operational performance are generated or not.The online fault detection configuration is tested on an actual variable-air-volume(VAV)air handling unit(AHU).The results show that the time ratio of fault detection exceeds 95.00%,which means that the configuration exhibits an acceptable fault detection effect.展开更多
ADC distribution network is an effective solution for increasing renewable energy utilization with distinct benefits,such as high efficiency and easy control.However,a sudden increase in the current after the occurren...ADC distribution network is an effective solution for increasing renewable energy utilization with distinct benefits,such as high efficiency and easy control.However,a sudden increase in the current after the occurrence of faults in the network may adversely affect network stability.This study proposes an artificial neural network(ANN)-based fault detection and protection method for DC distribution networks.The ANN is applied to a classifier for different faults ontheDC line.The backpropagationneuralnetwork is used to predict the line current,and the fault detection threshold is obtained on the basis of the difference between the predicted current and the actual current.The proposed method only uses local signals,with no requirement of a strict communication link.Simulation experiments are conducted for the proposed algorithm on a two-terminal DC distribution network modeled in the PSCAD/EMTDC and developed on the MATLAB platform.The results confirm that the proposed method can accurately detect and classify line faults within a few milliseconds and is not affected by fault locations,fault resistance,noise,and communication delay.展开更多
Rolling element bearings are commonly used in rotary mechanical and electrical equipment. According to investigation, more than half of rotating machinery defects are related to bearing faults. However, reliable beari...Rolling element bearings are commonly used in rotary mechanical and electrical equipment. According to investigation, more than half of rotating machinery defects are related to bearing faults. However, reliable bearing fault detection still remains a challenging task, especially in industrial applications. The objective of this work is to propose an adaptive variational mode decomposition (AVMD) technique for non-stationary signal analysis and bearing fault detection. The AVMD includes several steps in processing: 1) Signal characteristics are analyzed to determine the signal center frequency and the related parameters. 2) The ensemble-kurtosis index is suggested to decompose the target signal and select the most representative intrinsic mode functions (IMFs). 3) The envelope spectrum analysis is performed using the selected IMFs to identify the characteristic features for bearing fault detection. The effectiveness of the proposed AVMD technique is examined by experimental tests under different bearing conditions, with the comparison of other related bearing fault techniques.展开更多
In order to overcome the defects of the existing technology that the detection of ceramic electric kiln faults takes a long time and costs a lot,an electric kiln control and fault detection device was designed.The wor...In order to overcome the defects of the existing technology that the detection of ceramic electric kiln faults takes a long time and costs a lot,an electric kiln control and fault detection device was designed.The working process of the device includes detection module,control module,start⁃stop module and switch module.The detection module detects the resistance circuit and sends a fault signal to the control module.The control module generates stop signal and fault information according to the fault signal,and starts the electric kiln when the fault signal is not received within the preset time.The start⁃stop module can monitor the internal temperature of the electric kiln and control the closing status of the switch module.The switch module is used to control the connection status of AC power and each resistance circuit in the kiln.Based on the 5G DTU or 5G module,the control module could send the information to mobile terminal under the ultra⁃reliable and low⁃latency communication(uRLLC)technical characteristics of 5G communication.展开更多
By analyzing the average percent of faults detected （APFD） metric and its variant versions, which are widely utilized as metrics to evaluate the fault detection efficiency of the test suite, this paper points out so...By analyzing the average percent of faults detected （APFD） metric and its variant versions, which are widely utilized as metrics to evaluate the fault detection efficiency of the test suite, this paper points out some limitations of the APFD series metrics. These limitations include APFD series metrics having inaccurate physical explanations and being unable to precisely describe the process of fault detection. To avoid the limitations of existing metrics, this paper proposes two improved metrics for evaluating fault detection efficiency of a test suite, including relative-APFD and relative-APFDc. The proposed metrics refer to both the speed of fault detection and the constraint of the testing source. The case study shows that the two proposed metrics can provide much more precise descriptions of the fault detection process and the fault detection efficiency of the test suite.展开更多
Online fault detection is one of the key technologies to improve the performance of cloud systems. The current data of cloud systems is to be monitored, collected and used to reflect their state. Its use can potential...Online fault detection is one of the key technologies to improve the performance of cloud systems. The current data of cloud systems is to be monitored, collected and used to reflect their state. Its use can potentially help cloud managers take some timely measures before fault occurrence in clouds. Because of the complex structure and dynamic change characteristics of the clouds, existing fault detection methods suffer from the problems of low efficiency and low accuracy. In order to solve them, this work proposes an online detection model based on asystematic parameter-search method called SVM-Grid, whose construction is based on a support vector machine(SVM). SVM-Grid is used to optimize parameters in SVM. Proper attributes of a cloud system's running data are selected by using Pearson correlation and principal component analysis for the model. Strategies of predicting cloud faults and updating fault sample databases are proposed to optimize the model and improve its performance.In comparison with some representative existing methods, the proposed model can achieve more efficient and accurate fault detection for cloud systems.展开更多
文摘The widespread adoption of the Internet of Things (IoT) has transformed various sectors globally, making themmore intelligent and connected. However, this advancement comes with challenges related to the effectiveness ofIoT devices. These devices, present in offices, homes, industries, and more, need constant monitoring to ensuretheir proper functionality. The success of smart systems relies on their seamless operation and ability to handlefaults. Sensors, crucial components of these systems, gather data and contribute to their functionality. Therefore,sensor faults can compromise the system’s reliability and undermine the trustworthiness of smart environments.To address these concerns, various techniques and algorithms can be employed to enhance the performance ofIoT devices through effective fault detection. This paper conducted a thorough review of the existing literature andconducted a detailed analysis.This analysis effectively links sensor errors with a prominent fault detection techniquecapable of addressing them. This study is innovative because it paves theway for future researchers to explore errorsthat have not yet been tackled by existing fault detection methods. Significant, the paper, also highlights essentialfactors for selecting and adopting fault detection techniques, as well as the characteristics of datasets and theircorresponding recommended techniques. Additionally, the paper presents amethodical overview of fault detectiontechniques employed in smart devices, including themetrics used for evaluation. Furthermore, the paper examinesthe body of academic work related to sensor faults and fault detection techniques within the domain. This reflectsthe growing inclination and scholarly attention of researchers and academicians toward strategies for fault detectionwithin the realm of the Internet of Things.
基金supported by the Liaoning Province Applied Basic Research Program Project of China(Grant:2023JH2/101300065)the Liaoning Province Science and Technology Plan Joint Fund(2023-MSLH-221).
文摘Deep learning has emerged in many practical applications,such as image classification,fault diagnosis,and object detection.More recently,convolutional neural networks(CNNs),representative models of deep learning,have been used to solve fault detection.However,the current design of CNNs for fault detection of wind turbine blades is highly dependent on domain knowledge and requires a large amount of trial and error.For this reason,an evolutionary YOLOv8 network has been developed to automatically find the network architecture for wind turbine blade-based fault detection.YOLOv8 is a CNN-backed object detection model.Specifically,to reduce the parameter count,we first design an improved FasterNet module based on the Partial Convolution(PConv)operator.Then,to enhance convergence performance,we improve the loss function based on the efficient complete intersection over the union.Based on this,a flexible variable-length encoding is proposed,and the corresponding reproduction operators are designed.Related experimental results confirmthat the proposed approach can achieve better fault detection results and improve by 2.6%in mean precision at 50(mAP50)compared to the existing methods.Additionally,compared to training with the YOLOv8n model,the YOLOBFE model reduces the training parameters by 933,937 and decreases the GFLOPS(Giga Floating Point Operations Per Second)by 1.1.
文摘Electrolysis tanks are used to smeltmetals based on electrochemical principles,and the short-circuiting of the pole plates in the tanks in the production process will lead to high temperatures,thus affecting normal production.Aiming at the problems of time-consuming and poor accuracy of existing infrared methods for high-temperature detection of dense pole plates in electrolysis tanks,an infrared dense pole plate anomalous target detection network YOLOv5-RMF based on You Only Look Once version 5(YOLOv5)is proposed.Firstly,we modified the Real-Time Enhanced Super-Resolution Generative Adversarial Network(Real-ESRGAN)by changing the U-shaped network(U-Net)to Attention U-Net,to preprocess the images;secondly,we propose a new Focus module that introduces the Marr operator,which can provide more boundary information for the network;again,because Complete Intersection over Union(CIOU)cannot accommodate target borders that are increasing and decreasing,replace CIOU with Extended Intersection over Union(EIOU),while the loss function is changed to Focal and Efficient IOU(Focal-EIOU)due to the different difficulty of sample detection.On the homemade dataset,the precision of our method is 94%,the recall is 70.8%,and the map@.5 is 83.6%,which is an improvement of 1.3%in precision,9.7%in recall,and 7%in map@.5 over the original network.The algorithm can meet the needs of electrolysis tank pole plate abnormal temperature detection,which can lay a technical foundation for improving production efficiency and reducing production waste.
基金supported partially by NationalNatural Science Foundation of China(NSFC)(No.U21A20146)Collaborative Innovation Project of Anhui Universities(No.GXXT-2020-070)+8 种基金Cooperation Project of Anhui Future Technology Research Institute and Enterprise(No.2023qyhz32)Development of a New Dynamic Life Prediction Technology for Energy Storage Batteries(No.KH10003598)Opening Project of Key Laboratory of Electric Drive and Control of Anhui Province(No.DQKJ202304)Anhui Provincial Department of Education New Era Education Quality Project(No.2023dshwyx019)Special Fund for Collaborative Innovation between Anhui Polytechnic University and Jiujiang District(No.2022cyxtb10)Key Research and Development Program of Wuhu City(No.2022yf42)Open Research Fund of Anhui Key Laboratory of Detection Technology and Energy Saving Devices(No.JCKJ2021B06)Anhui Provincial Graduate Student Innovation and Entrepreneurship Practice Project(No.2022cxcysj123)Key Scientific Research Project for Anhui Universities(No.2022AH050981).
文摘Accurate and reliable fault detection is essential for the safe operation of electric vehicles.Support vector data description(SVDD)has been widely used in the field of fault detection.However,constructing the hypersphere boundary only describes the distribution of unlabeled samples,while the distribution of faulty samples cannot be effectively described and easilymisses detecting faulty data due to the imbalance of sample distribution.Meanwhile,selecting parameters is critical to the detection performance,and empirical parameterization is generally timeconsuming and laborious and may not result in finding the optimal parameters.Therefore,this paper proposes a semi-supervised data-driven method based on which the SVDD algorithm is improved and achieves excellent fault detection performance.By incorporating faulty samples into the underlying SVDD model,training deals better with the problem of missing detection of faulty samples caused by the imbalance in the distribution of abnormal samples,and the hypersphere boundary ismodified to classify the samplesmore accurately.The Bayesian Optimization NSVDD(BO-NSVDD)model was constructed to quickly and accurately optimize hyperparameter combinations.In the experiments,electric vehicle operation data with four common fault types are used to evaluate the performance with other five models,and the results show that the BO-NSVDD model presents superior detection performance for each type of fault data,especially in the imperceptible early and minor faults,which has seen very obvious advantages.Finally,the strong robustness of the proposed method is verified by adding different intensities of noise in the dataset.
基金supported by the National Natural Science Foundation of China(Grant Nos.U20A20186 and 62372063).
文摘Fault diagnosis of traction systems is important for the safety operation of high-speed trains.Long-term operation of the trains will degrade the performance of systems,which decreases the fault detection accuracy.To solve this problem,this paper proposes a fault detection method developed by a Generalized Autoencoder(GAE)for systems with performance degradation.The advantage of this method is that it can accurately detect faults when the traction system of high-speed trains is affected by performance degradation.Regardless of the probability distribution,it can handle any data,and the GAE has extremely high sensitivity in anomaly detection.Finally,the effectiveness of this method is verified through the Traction Drive Control System(TDCS)platform.At different performance degradation levels,our method’s experimental results are superior to traditional methods.
文摘This paper examines the progression and advancements in fault detection techniques for photovoltaic (PV) panels, a target for optimizing the efficiency and longevity of solar energy systems. As the adoption of PV technology grows, the need for effective fault detection strategies becomes increasingly paramount to maximize energy output and minimize operational downtimes of solar power systems. These approaches include the use of machine learning and deep learning methodologies to be able to detect the identified faults in PV technology. Here, we delve into how machine learning models, specifically kernel-based extreme learning machines and support vector machines, trained on current-voltage characteristic (I-V curve) data, provide information on fault identification. We explore deep learning approaches by taking models like EfficientNet-B0, which looks at infrared images of solar panels to detect subtle defects not visible to the human eye. We highlight the utilization of advanced image processing techniques and algorithms to exploit aerial imagery data, from Unmanned Aerial Vehicles (UAVs), for inspecting large solar installations. Some other techniques like DeepLabV3 , Feature Pyramid Networks (FPN), and U-Net will be detailed as such tools enable effective segmentation and anomaly detection in aerial panel images. Finally, we discuss implications of these technologies on labor costs, fault detection precision, and sustainability of PV installations.
基金supported by the Natural Science Foundation of Fujian Province,China(No.2022J01566).
文摘The in-core self-powered neutron detector(SPND)acts as a key measuring device for the monitoring of parameters and evaluation of the operating conditions of nuclear reactors.Prompt detection and tolerance of faulty SPNDs are indispensable for reliable reactor management.To completely extract the correlated state information of SPNDs,we constructed a twin model based on a generalized regression neural network(GRNN)that represents the common relationships among overall signals.Faulty SPNDs were determined because of the functional concordance of the twin model and real monitoring sys-tems,which calculated the error probability distribution between the model outputs and real values.Fault detection follows a tolerance phase to reinforce the stability of the twin model in the case of massive failures.A weighted K-nearest neighbor model was employed to reasonably reconstruct the values of the faulty signals and guarantee data purity.The experimental evaluation of the proposed method showed promising results,with excellent output consistency and high detection accuracy for both single-and multiple-point faulty SPNDs.For unexpected excessive failures,the proposed tolerance approach can efficiently repair fault behaviors and enhance the prediction performance of the twin model.
基金supported in part by the Natural Science Foundation of the Jiangsu Higher Education Institutions of China under Grant 21KJA470007。
文摘The complex working conditions and nonlinear characteristics of the motor drive control system of industrial robots make it difficult to detect faults.In this paper,a deep learning-based observer,which combines the convolutional neural network(CNN)and the long short-term memory network(LSTM),is employed to approximate the nonlinear driving control system.CNN layers are introduced to extract dynamic features of the data,whereas LSTM layers perform time-sequential prediction of the target system.In terms of application,normal samples are fed into the observer to build an offline prediction model for the target system.The trained CNN-LSTM-based observer is then deployed along with the target system to estimate the system outputs.Online fault detection can be realized by analyzing the residuals.Finally,an application of the proposed fault detection method to a brushless DC motor drive system is given to verify the effectiveness of the proposed scheme.Simulation results indicate the impressive fault detection capability of the presented method for driving control systems of industrial robots.
基金This work was supported in part by the Natural Science Foundation of China under Grant 62203461 and Grant 62203365in part by the Postdoctoral Science Foundation of China under Grant No.2020M683736+3 种基金in part by the Teaching reform project of higher education in Heilongjiang Province under Grant Nos.SJGY20210456 and SJGY20210457in part by the Natural Science Foundation of Heilongjiang Province of China under Grant No.LH2021F038in part by the graduate academic innovation project of Harbin Normal University under Grant Nos.HSDSSCX2022-17,HSDSSCX2022-18 andHSDSSCX2022-19in part by the Foreign Expert Project of Heilongjiang Province under Grant No.GZ20220131.
文摘Expert knowledge is the key to modeling milling fault detection systems based on the belief rule base.The construction of an initial expert knowledge base seriously affects the accuracy and interpretability of the milling fault detection model.However,due to the complexity of the milling system structure and the uncertainty of the milling failure index,it is often impossible to construct model expert knowledge effectively.Therefore,a milling system fault detection method based on fault tree analysis and hierarchical BRB(FTBRB)is proposed.Firstly,the proposed method uses a fault tree and hierarchical BRB modeling.Through fault tree analysis(FTA),the logical correspondence between FTA and BRB is sorted out.This can effectively embed the FTA mechanism into the BRB expert knowledge base.The hierarchical BRB model is used to solve the problem of excessive indexes and avoid combinatorial explosion.Secondly,evidence reasoning(ER)is used to ensure the transparency of the model reasoning process.Thirdly,the projection covariance matrix adaptation evolutionary strategies(P-CMA-ES)is used to optimize the model.Finally,this paper verifies the validity model and the method’s feasibility techniques for milling data sets.
文摘This work presents a novel wavelet-based denoising technique for improving the signal-to-noise ratio(SNR)of nonsteady vibration signals in hardware redundant systems.The proposed method utilizes the relationship between redundant hardware components to effectively separate fault-related components from the vibration signature,thus enhancing fault detection accuracy.The study evaluates the proposed technique on two mechanically identical subsystems that are simultaneously controlled under the same speed and load inputs,with and without the proposed denoising step.The results demonstrate an increase in detection accuracy when incorporating the proposed denoising method into a fault detection system designed for hardware redundant machinery.This work is original in its application of a new method for improving performance when using residual analysis for fault detection in hardware redundant machinery configurations.Moreover,the proposed methodology is applicable to nonstationary equipment that experiences changes in both speed and load.
基金supported by the National Natural Science Foundation of China (61471323)。
文摘Considering packet losses, time-varying delay, and parameter uncertainty in the switched fuzzy system, this paper designs a robust fault detection filter at any switching rate and analyzes the H∞ performance of the system. Firstly, the Takagi-Sugeno(T-S) fuzzy model is used to establish a global fuzzy model for the uncertain nonlinear time-delay switched system,and the packet loss process is modeled as a mathematical model satisfying Bernoulli distribution. Secondly, through the average dwell time method and multiple Lyapunov functions, the exponentially stable condition of the nonlinear network switched system is given. Finally, specific parameters of the robust fault detection filter can be obtained by solving linear matrix inequalities(LMIs). The effectiveness of the method is verified by simulation results.
基金supported in part by the National Natural Science Foundation of China under Grant U1734211.
文摘Railway turnout is one of the critical equipment of Switch&Crossing(S&C)Systems in railway,related to the train’s safety and operation efficiency.With the advancement of intelligent sensors,data-driven fault detection technology for railway turnout has become an important research topic.However,little research in the literature has investigated the capability of data-driven fault detection technology for metro railway turnout.This paper presents a convolutional autoencoder-based fault detection method for the metro railway turnout considering human field inspection scenarios.First,the one-dimensional original time-series signal is converted into a twodimensional image by data pre-processing and 2D representation.Next,a binary classification model based on the convolutional autoencoder is developed to implement fault detection.The profile and structure information can be captured by processing data as images.The performance of our method is evaluated and tested on real-world operational current data in themetro stations.Experimental results show that the proposedmethod achieves better performance,especially in terms of error rate and specificity,and is robust in practical engineering applications.
文摘Wireless Sensor Networks(WSNs)gather data in physical environments,which is some type.These ubiquitous sensors face several challenges responsible for corrupting them(mostly sensor failure and intrusions in external agents).WSNs were disposed to error,and effectual fault detection techniques are utilized for detecting faults from WSNs in a timely approach.Machine learning(ML)was extremely utilized for detecting faults in WSNs.Therefore,this study proposes a billiards optimization algorithm with modified deep learning for fault detection(BIOMDL-FD)in WSN.The BIOMDLFD technique mainly concentrates on identifying sensor faults to enhance network efficiency.To do so,the presented BIOMDL-FD technique uses the attention-based bidirectional long short-term memory(ABLSTM)method for fault detection.In the ABLSTM model,the attention mechanism enables us to learn the relationships between the inputs and modify the probability to give more attention to essential features.At the same time,the BIO algorithm is employed for optimal hyperparameter tuning of the ABLSTM model,which is stimulated by billiard games,showing the novelty of the work.Experimental analyses are made to affirm the enhanced fault detection outcomes of the BIOMDL-FD technique.Detailed simulation results demonstrate the improvement of the BIOMDL-FD technique over other models with a maximum classification accuracy of 99.37%.
基金supports from National Science Foundation of China(Grant No.51777121).
文摘Aiming at the fact that the rotor winding inter-turn weak faults can hardly be detected due to the strong electromagnetic coupling effect in the excitation system,an interval observer based on current residual is designed.Firstly,the mechanism of the inter-turn short circuit of the rotor winding in the excitation system is modeled under the premise of stable working conditions,and electromagnetic decoupling and system simplification are carried out through Park Transform.An interval observer is designed based on the current residual in the two-phase coordinate system,and the sensitive and stable conditions of the observer is preset.The fault diagnosis process based on the interval observer is formulated,and the observer gain matrix is convexly optimized by linear matrix inequality.The numerical simulation and experimental results show that the inter-turn short circuit weak fault is hardly detected directly through the current signal,but the fault is quickly and accurately diagnosed through the residual internal observer.Compared with the traditional fault diagnosis method based on excitation current,the diagnosis speed and accuracy are greatly improved,and the probability of misdiagnosis also decreases.This method provides a theoretical basis for weak fault identification of excitation systems,and is of great significance for the operation and maintenance of excitation systems.
基金Research Project of China Ship Development and Design Center,Wuhan,China。
文摘With the development of the technology of the Internet of Things,more and more operational data can be collected from air conditioning systems.Unfortunately,the most of existing air conditioning controllers mainly provide controlling functions more than storing,processing or computing the measured data.This study develops an online fault detection configuration on the equipment side of air conditioning systems to realize these functions.Modbus communication is served to collect real-time operational data.The calculating programs are embedded to identify whether the measured signals exceed their limits or not,and to detect if sensor reading is frozen and other faults in relation to the operational performance are generated or not.The online fault detection configuration is tested on an actual variable-air-volume(VAV)air handling unit(AHU).The results show that the time ratio of fault detection exceeds 95.00%,which means that the configuration exhibits an acceptable fault detection effect.
基金supported by Key Natural Science Research Projects of Colleges and Universities in Anhui Province(No.2022AH051831).
文摘ADC distribution network is an effective solution for increasing renewable energy utilization with distinct benefits,such as high efficiency and easy control.However,a sudden increase in the current after the occurrence of faults in the network may adversely affect network stability.This study proposes an artificial neural network(ANN)-based fault detection and protection method for DC distribution networks.The ANN is applied to a classifier for different faults ontheDC line.The backpropagationneuralnetwork is used to predict the line current,and the fault detection threshold is obtained on the basis of the difference between the predicted current and the actual current.The proposed method only uses local signals,with no requirement of a strict communication link.Simulation experiments are conducted for the proposed algorithm on a two-terminal DC distribution network modeled in the PSCAD/EMTDC and developed on the MATLAB platform.The results confirm that the proposed method can accurately detect and classify line faults within a few milliseconds and is not affected by fault locations,fault resistance,noise,and communication delay.
文摘Rolling element bearings are commonly used in rotary mechanical and electrical equipment. According to investigation, more than half of rotating machinery defects are related to bearing faults. However, reliable bearing fault detection still remains a challenging task, especially in industrial applications. The objective of this work is to propose an adaptive variational mode decomposition (AVMD) technique for non-stationary signal analysis and bearing fault detection. The AVMD includes several steps in processing: 1) Signal characteristics are analyzed to determine the signal center frequency and the related parameters. 2) The ensemble-kurtosis index is suggested to decompose the target signal and select the most representative intrinsic mode functions (IMFs). 3) The envelope spectrum analysis is performed using the selected IMFs to identify the characteristic features for bearing fault detection. The effectiveness of the proposed AVMD technique is examined by experimental tests under different bearing conditions, with the comparison of other related bearing fault techniques.
文摘In order to overcome the defects of the existing technology that the detection of ceramic electric kiln faults takes a long time and costs a lot,an electric kiln control and fault detection device was designed.The working process of the device includes detection module,control module,start⁃stop module and switch module.The detection module detects the resistance circuit and sends a fault signal to the control module.The control module generates stop signal and fault information according to the fault signal,and starts the electric kiln when the fault signal is not received within the preset time.The start⁃stop module can monitor the internal temperature of the electric kiln and control the closing status of the switch module.The switch module is used to control the connection status of AC power and each resistance circuit in the kiln.Based on the 5G DTU or 5G module,the control module could send the information to mobile terminal under the ultra⁃reliable and low⁃latency communication(uRLLC)technical characteristics of 5G communication.
基金The National Natural Science Foundation of China(No.61300054)the Natural Science Foundation of Jiangsu Province(No.BK2011190,BK20130879)+1 种基金the Natural Science Foundation of Higher Education Institutions of Jiangsu Province(No.13KJB520018)the Science Foundation of Nanjing University of Posts&Telecommunications(No.NY212023)
文摘By analyzing the average percent of faults detected （APFD） metric and its variant versions, which are widely utilized as metrics to evaluate the fault detection efficiency of the test suite, this paper points out some limitations of the APFD series metrics. These limitations include APFD series metrics having inaccurate physical explanations and being unable to precisely describe the process of fault detection. To avoid the limitations of existing metrics, this paper proposes two improved metrics for evaluating fault detection efficiency of a test suite, including relative-APFD and relative-APFDc. The proposed metrics refer to both the speed of fault detection and the constraint of the testing source. The case study shows that the two proposed metrics can provide much more precise descriptions of the fault detection process and the fault detection efficiency of the test suite.
基金supported by the National Natural Science Foundation of China(61472005,61201252)CERNET Innovation Project(NGII20160207)
文摘Online fault detection is one of the key technologies to improve the performance of cloud systems. The current data of cloud systems is to be monitored, collected and used to reflect their state. Its use can potentially help cloud managers take some timely measures before fault occurrence in clouds. Because of the complex structure and dynamic change characteristics of the clouds, existing fault detection methods suffer from the problems of low efficiency and low accuracy. In order to solve them, this work proposes an online detection model based on asystematic parameter-search method called SVM-Grid, whose construction is based on a support vector machine(SVM). SVM-Grid is used to optimize parameters in SVM. Proper attributes of a cloud system's running data are selected by using Pearson correlation and principal component analysis for the model. Strategies of predicting cloud faults and updating fault sample databases are proposed to optimize the model and improve its performance.In comparison with some representative existing methods, the proposed model can achieve more efficient and accurate fault detection for cloud systems.
