Arc grounding faults occur frequently in the power grid with small resistance grounding neutral points.The existing arc fault identification technology only uses the fault line signal characteristics to set the identi...Arc grounding faults occur frequently in the power grid with small resistance grounding neutral points.The existing arc fault identification technology only uses the fault line signal characteristics to set the identification index,which leads to detection failure when the arc zero-off characteristic is short.To solve this problem,this paper presents an arc fault identification method by utilizing integrated signal characteristics of both the fault line and sound lines.Firstly,the waveform characteristics of the fault line and sound lines under an arc grounding fault are studied.After that,the convex hull,gradient product,and correlation coefficient index are used as the basic characteristic parameters to establish fault identification criteria.Then,the logistic regression algorithm is employed to deal with the reference samples,establish the machine discrimination model,and realize the discrimination of fault types.Finally,simulation test results and experimental results verify the accuracy of the proposed method.The comparison analysis shows that the proposed method has higher recognition accuracy,especially when the arc dissipation power is smaller than 2×10^(3) W,the zero-off period is not obvious.In conclusion,the proposed method expands the arc fault identification theory.展开更多
Ahealth monitoring scheme is developed in this work by using hybrid machine learning strategies to iden-tify the fault severity and assess the health status of the aircraft gas turbine engine that is subject to compon...Ahealth monitoring scheme is developed in this work by using hybrid machine learning strategies to iden-tify the fault severity and assess the health status of the aircraft gas turbine engine that is subject to component degrada-tions that are caused by fouling and erosion.The proposed hybrid framework involves integrating both supervised recur-rent neural networks and unsupervised self-organizing maps methodologies,where the former is developed to extract ef-fective features that can be associated with the engine health condition and the latter is constructed for fault severity modeling and tracking of each considered degradation mode.Advantages of our proposed methodology are that it ac-complishes fault identification and health monitoring objectives by only discovering inherent health information that are available in the system I/O data at each operating point.The effectiveness of our approach is validated and justified with engine data under various degradation modes in compressors and turbines.展开更多
Fault management is crucial to pro vi de quality of service grantees for the future networks, and fault identification is an essential part of it. A novel fault identification algorithm is proposed in this paper, wh...Fault management is crucial to pro vi de quality of service grantees for the future networks, and fault identification is an essential part of it. A novel fault identification algorithm is proposed in this paper, which focuses on the anomaly detection of network traffic. Since the fault identification has been achieved using statistical information in mana gement information base, the algorithm is compatible with the existing simple ne twork management protocol framework. The network traffic time series is verified to be non-stationary. By fitting the adaptive autoregressive model, the series is transformed into a multidimensional vector. The training samples and identif iers are acquired from the network simulation. A k-nearest neighbor classif ier identifies the system faults after being trained. The experiment results are consistent with the given fault scenarios, which prove the accuracy of the algo rithm. The identification errors are discussed to illustrate that the novel faul t identification algorithm is adaptive in the fault scenarios with network traff ic change.展开更多
Nowadays, the DC distribution system has been suggested, as a replacement for the AC power distribution system with electric propulsion. This idea signifies a fresh approach of issuing energy for low-voltage installat...Nowadays, the DC distribution system has been suggested, as a replacement for the AC power distribution system with electric propulsion. This idea signifies a fresh approach of issuing energy for low-voltage installations. It can be used for any electrical application up to 20 MW and works at a nominal voltage of 1000 V DC. The DC distribution system is just an extension of the multiple DC links that previously available in all propulsion and thruster drives, which typically comprise more than 80% of the electrical power consumption on electric propulsion vessels. A fault detection and islanding scheme for DC grid connected PV system is presented in this paper. Unlike traditional ac distribution systems, protection has been challenging for dc systems. The goals of this paper are to classify and detect the fault in the PV system as well as DC grid and to isolate the faulted section so that the system keeps operating without disabling the entire system. The results show the measured values of power at PV panel and DC grid side under different fault condition, which indicates the type of fault that occurs in the system.展开更多
A distributed generation system(DG)has several benefits over a traditional centralized power system.However,the protection area in the case of the distributed generator requires special attention as it encounters stab...A distributed generation system(DG)has several benefits over a traditional centralized power system.However,the protection area in the case of the distributed generator requires special attention as it encounters stability loss,failure re-closure,fluctuations in voltage,etc.And thereby,it demands immediate attention in identifying the location&type of a fault without delay especially when occurred in a small,distributed generation system,as it would adversely affect the overall system and its operation.In the past,several methods were proposed for classification and localisation of a fault in a distributed generation system.Many of those methods were accurate in identifying location,but the accuracy in identifying the type of fault was not up to the acceptable mark.The proposed work here uses a shallow artificial neural network(sANN)model for identifying a particular type of fault that could happen in a specific distribution network when used in conjunction with distributed generators.Firstly,a distribution network consisting of two similar distributed generators(DG1 and DG2),one grid,and a 100 Km distribution line is modeled.Thereafter,different voltages and currents corresponding to various faults(line to line,line to ground)at different locations are tabulated,resulting in a matrix of 500×18 inputs.Secondly,the sANN is formulated for identifying the types of faults in the system in which the above-obtained data is used to train,validate,and test the neural network.The overall result shows an unprecedented almost zero percent error in identifying the type of the faults.展开更多
According to the background of the rub impact faults of aerial engines and industrial turbines, two kinds of test rigs, on the base of the dynamics model, are established to study the rub impact faults between rotor...According to the background of the rub impact faults of aerial engines and industrial turbines, two kinds of test rigs, on the base of the dynamics model, are established to study the rub impact faults between rotor and stator with free supports. The orbit of the vibration of rotor displacement is respectively examined on the four impact conditions, which are the normal state with no impact, the early sharp impact statement, the semi sharp impact statement and the terminal blunt impact statement. The route to chaos, appearing with the early sharp impact, is observed for the first time. By analyzing the frequency domain characteristics of the experimental data on four impact conditions, it is testified that the appearance of the sub harmonic vibrations of the order 1/3 and 1/4 is the effective evidence to judge whether or not the blade has initial light rub impact. When there are only the harmonic vibrations of the order of 1/1 and 1/2, the blade stator rub impact faults have become very serious.展开更多
Receiver autonomous integrity monitoring（RAIM） provides integrity monitoring of global positioning system（GPS） for safety-of-life applications.In the process of RAIM, fault identification（FI） enables navigation ...Receiver autonomous integrity monitoring（RAIM） provides integrity monitoring of global positioning system（GPS） for safety-of-life applications.In the process of RAIM, fault identification（FI） enables navigation to continue in the presence of fault measurement.Affected by satellite geometry, the leverage of each measurement in position solution may differ greatly.However, the conventional RAIM FI methods are generally based on maximum likelihood of ranging error for different measurements, thereby causing a major decrease in the probability of correct identification for the fault measurement with high leverage.In this paper, the impact of leverage on the fault identification is analyzed.The leveraged RAIM fault identification（L-RAIM FI） method is proposed with consideration of the difference in leverage for each satellite in view.Furthermore,the theoretical probability of correct identification is derived to evaluate the performance of L-RAIM FI method.The experiments in various typical scenarios demonstrate the effectiveness of L-RAIM FI method over conventional FI methods in the probability of correct identification for the fault with high leverage.展开更多
With the integration of alternative energy and renewables,the issue of stability and resilience of the power network has received considerable attention.The basic necessity for fault diagnosis and isolation is fault i...With the integration of alternative energy and renewables,the issue of stability and resilience of the power network has received considerable attention.The basic necessity for fault diagnosis and isolation is fault identification and location.The conventional intelligent fault identification method needs supervision,manual labelling of characteristics,and requires large amounts of labelled data.To enhance the ability of intelligent methods and get rid of the dependence on a large amount of labelled data,a novel fault identification method based on deep reinforcement learning(DRL),which has not received enough attention in the field of fault identification,is investigated in this paper.The proposed method uses different faults as parameters of the model to expand the scope of fault identification.In addition,the DRL algorithm can intelligently modify the fault parameters according to the observations obtained from the power network environment,rather than requiring manual and mechanical tuning of parameters.The methodology was tested on the IEEE 14 bus for several scenarios and the performance of the proposed method was compared with that of population-based optimization methods and supervised learning methods.The obtained results have confirmed the feasibility and effectiveness of the proposed method.展开更多
Identification and classification of DC faults are considered as fundamentals of DC grid protection.A sudden rise of DC fault current must be identified and classified to immediately operate the corresponding interrup...Identification and classification of DC faults are considered as fundamentals of DC grid protection.A sudden rise of DC fault current must be identified and classified to immediately operate the corresponding interrupting mechanism.In this paper,the Boltzmann machine learning(BML)approach is proposed for identification and classification of DC faults using travelling waves generated at fault point in voltage source converter based high-voltage direct current(VSC-HVDC)transmission system.An unsupervised way of feature extraction is performed on the frequency spectrum of the travelling waves.Binomial class logistic regression(BCLR)classifies the HVDC transmission system into faulty and healthy states.The proposed technique reduces the time for fault identification and classification because of reduced tagged data with few characteristics.Therefore,the faults near or at converter stations are readily identified and classified.The performance of the proposed technique is assessed via simulations developed in MATLAB/Simulink and tested for pre-fault and post-fault data both at VSC1 and VSC2,respectively.Moreover,the proposed technique is supported by analyzing the root mean square error to show practicality and realization with reduced computations.展开更多
The size and complexity of modern equipment require more advanced fault diagnosis techniques. Different from signal analysis based methods, a dynamic model based diagnosis technique can further diagnose the location a...The size and complexity of modern equipment require more advanced fault diagnosis techniques. Different from signal analysis based methods, a dynamic model based diagnosis technique can further diagnose the location and severity of the fault, and detect multiple faults at one time. A model based fault diagnosis method was developed to identify typical faults of rotating machinery. This method can identify mass unbalances, crack locations and sizes, and oil film parameters in rotating machinery by optimization methods and dynamics simulation technique. Numerical and experimental results demonstrate that the method is useful for detecting faults of rotating systems.展开更多
This study combined fault identification with a deep learning algorithm and applied a convolutional neural network(CNN)design based on an improved balanced crossentropy(BCE)loss function to address the low accuracy in...This study combined fault identification with a deep learning algorithm and applied a convolutional neural network(CNN)design based on an improved balanced crossentropy(BCE)loss function to address the low accuracy in the intelligent identification of seismic faults and the slow training speed of convolutional neural networks caused by unbalanced training sample sets.The network structure and optimal hyperparameters were determined by extracting feature maps layer by layer and by analyzing the results of seismic feature extraction.The BCE loss function was used to add the parameter which is the ratio of nonfaults to the total sample sets,thereby changing the loss function to find the reference of the minimum weight parameter and adjusting the ratio of fault to nonfault data.The method overcame the unbalanced number of sample sets and improved the iteration speed.After a brief training,the accuracy could reach more than 95%,and gradient descent was evident.The proposed method was applied to fault identification in an oilfield area.The trained model can predict faults clearly,and the prediction results are basically consistent with an actual case,verifying the effectiveness and adaptability of the method.展开更多
Sequential diagnosis is a very useful strategy for system-level fault identification because of its lower cost of hardware.In this paper,the characterization of sequentially t-diagnosable system is given,and a tmivers...Sequential diagnosis is a very useful strategy for system-level fault identification because of its lower cost of hardware.In this paper,the characterization of sequentially t-diagnosable system is given,and a tmiversal algorithm to seek faulty units in the system is developed.展开更多
The intermittent connection（IC）of the field-bus in networked manufacturing systems is a common but hard troubleshooting network problem,which may result in system level failures or safety issues.However,there is no ...The intermittent connection（IC）of the field-bus in networked manufacturing systems is a common but hard troubleshooting network problem,which may result in system level failures or safety issues.However,there is no online IC location identification method available to detect and locate the position of the problem.To tackle this problem,a novel model based online fault location identification method for localized IC problem is proposed.First,the error event patterns are identified and classified according to different node sources in each error frame.Then generalized zero inflated Poisson process（GZIP）model for each node is established by using time stamped error event sequence.Finally,the location of the IC fault is determined by testing whether the parameters of the fitted stochastic model is statistically significant or not using the confident intervals of the estimated parameters.To illustrate the proposed method,case studies are conducted on a 3-node controller area network（CAN）test-bed,in which IC induced faults are imposed on a network drop cable using computer controlled on-off switches.The experimental results show the parameters of the GZIP model for the problematic node are statistically significant（larger than 0）,and the patterns of the confident intervals of the estimated parameters are directly linked to the problematic node,which agrees with the experimental setup.The proposed online IC location identification method can successfully identify the location of the drop cable on which IC faults occurs on the CAN network.展开更多
Fractal dimensions of a terrain quantitatively describe the self-organizedstructure of the terrain geometry. However, the local topographic variation cannot be illustrated bythe conventional box-counting method. This ...Fractal dimensions of a terrain quantitatively describe the self-organizedstructure of the terrain geometry. However, the local topographic variation cannot be illustrated bythe conventional box-counting method. This paper proposes a successive shift box-counting method,in which the studied object is divided into small sub-objects that are composed of a series of gridsaccording to its characteristic scaling. The terrain fractal dimensions in the grids are calculatedwith the successive shift box-counting method and the scattered points with values of fractaldimensions are obtained. The present research shows that the planar variation of fractal dimensionsis well consistent with fault traces and geological boundaries.展开更多
Fuzzy logic control(FLC)systems have found wide utilization in several industrial applications.This paper proposes a fuzzy logic-based fault detection and identification method for open-circuit switch fault in grid-ti...Fuzzy logic control(FLC)systems have found wide utilization in several industrial applications.This paper proposes a fuzzy logic-based fault detection and identification method for open-circuit switch fault in grid-tied photovoltaic(PV)inverters.Large installations and ambitious plans have been recently achieved for PV systems as clean and renewable power generation sources due to their improved environmental impacts and availability everywhere.Power converters represent the main parts for the grid integration of PV systems.However,PV power converters contain several power switches that construct their circuits.The power switches in PV systems are highly subjected to high stresses due to the continuously varying operating conditions.Moreover,the grid-tied systems represent nonlinear systems and the system model parameters are changing continuously.Consequently,the grid-tied PV systems have a nonlinear factor and the fault detection and identification(FDI)methods based on using mathematical models become more complex.The proposed fuzzy logic-based FDI(FL-FDI)method is based on employing the fuzzy logic concept for detecting and identifying the location of various switch faults.The proposed FL-FDI method is designed and extracted from the analysis and comparison of the various measured voltage/current components for the control purposes.Therefore,the proposed FL-FDI method does not require additional components or measurement circuits.Additionally,the proposed method can detect the faulty condition and also identify the location of the faulty switch for replacement and maintenance purposes.The proposed method can detect the faulty condition within only a single fundamental line period without the need for additional sensors and/or performing complex calculations or precise models.The proposed FL-FDI method is tested on the widely used T-type PV inverter system,wherein there are twelve different switches and the FDI process represents a challenging task.The results shows the superior and accurate performance of the proposed FL-FDI method.展开更多
A diagnostic signal current trace detecting based single phase-to-ground fault line identifica- tion and section location method for non-effectively grounded distribution systems is presented in this paper.A special d...A diagnostic signal current trace detecting based single phase-to-ground fault line identifica- tion and section location method for non-effectively grounded distribution systems is presented in this paper.A special diagnostic signal current is injected into the fault distribution system,and then it is detected at the outlet terminals to identify the fault line and at the sectionalizing or branching point along the fault line to locate the fault section.The method has been put into application in actual distribution network and field experience shows that it can identify the fault line and locate the fault section correctly and effectively.展开更多
In this paper, we suggest a novel parsimonious neurofuzzy model realized by RBFNs for railway carriage system identification and fault diagnosis. To overcome the curse of dimensionality resulting from high dimensional...In this paper, we suggest a novel parsimonious neurofuzzy model realized by RBFNs for railway carriage system identification and fault diagnosis. To overcome the curse of dimensionality resulting from high dimensional input variables, in our developed model the features extracted from the available observations are regarded as the input variables by adopting the higher-order statistics(HOS) technique. Such a constructed model is also applied to a practical railway carriage system, simulation results indicate that the developed neurofuzzy model possesses strong identification and fault diagnosis ability.展开更多
The subsea production system is a vital equipment for offshore oil and gas production.The control system is one of the most important parts of it.Collecting and processing the signals of subsea sensors is the only way...The subsea production system is a vital equipment for offshore oil and gas production.The control system is one of the most important parts of it.Collecting and processing the signals of subsea sensors is the only way to judge whether the subsea production control system is normal.However,subsea sensors degrade rapidly due to harsh working environments and long service time.This leads to frequent false alarm incidents.A combinatorial reasoning-based abnormal sensor recognition method for subsea production control system is proposed.A combinatorial algorithm is proposed to group sensors.The long short-term memory network(LSTM)is used to establish a single inference model.A counting-based judging method is proposed to identify abnormal sensors.Field data from an offshore platform in the South China Sea is used to demonstrate the effect of the proposed method.The results show that the proposed method can identify the abnormal sensors effectively.展开更多
Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Ou...Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.展开更多
This paper proposes a parity relation based fault estimation for a class of nonlinear systems which can be modelled by Takagi-Sugeno （TS） fuzzy models. The design of a parity relation based residual generator is for...This paper proposes a parity relation based fault estimation for a class of nonlinear systems which can be modelled by Takagi-Sugeno （TS） fuzzy models. The design of a parity relation based residual generator is formulated in terms of a family of linear matrix inequalities （LMIs）. A numerical example is provided to illustrate the effectiveness of the proposed design techniques.展开更多
基金This work was supported in part by the Natural Science Foundation of Henan Province,and the specific grant number is 232300420301。
文摘Arc grounding faults occur frequently in the power grid with small resistance grounding neutral points.The existing arc fault identification technology only uses the fault line signal characteristics to set the identification index,which leads to detection failure when the arc zero-off characteristic is short.To solve this problem,this paper presents an arc fault identification method by utilizing integrated signal characteristics of both the fault line and sound lines.Firstly,the waveform characteristics of the fault line and sound lines under an arc grounding fault are studied.After that,the convex hull,gradient product,and correlation coefficient index are used as the basic characteristic parameters to establish fault identification criteria.Then,the logistic regression algorithm is employed to deal with the reference samples,establish the machine discrimination model,and realize the discrimination of fault types.Finally,simulation test results and experimental results verify the accuracy of the proposed method.The comparison analysis shows that the proposed method has higher recognition accuracy,especially when the arc dissipation power is smaller than 2×10^(3) W,the zero-off period is not obvious.In conclusion,the proposed method expands the arc fault identification theory.
基金The Natural Sciences and Engineering Research Council of Canada(NSERC)the Department of National Defence(DND)under the Discovery Grant and DND Supplemental Programs。
文摘Ahealth monitoring scheme is developed in this work by using hybrid machine learning strategies to iden-tify the fault severity and assess the health status of the aircraft gas turbine engine that is subject to component degrada-tions that are caused by fouling and erosion.The proposed hybrid framework involves integrating both supervised recur-rent neural networks and unsupervised self-organizing maps methodologies,where the former is developed to extract ef-fective features that can be associated with the engine health condition and the latter is constructed for fault severity modeling and tracking of each considered degradation mode.Advantages of our proposed methodology are that it ac-complishes fault identification and health monitoring objectives by only discovering inherent health information that are available in the system I/O data at each operating point.The effectiveness of our approach is validated and justified with engine data under various degradation modes in compressors and turbines.
文摘Fault management is crucial to pro vi de quality of service grantees for the future networks, and fault identification is an essential part of it. A novel fault identification algorithm is proposed in this paper, which focuses on the anomaly detection of network traffic. Since the fault identification has been achieved using statistical information in mana gement information base, the algorithm is compatible with the existing simple ne twork management protocol framework. The network traffic time series is verified to be non-stationary. By fitting the adaptive autoregressive model, the series is transformed into a multidimensional vector. The training samples and identif iers are acquired from the network simulation. A k-nearest neighbor classif ier identifies the system faults after being trained. The experiment results are consistent with the given fault scenarios, which prove the accuracy of the algo rithm. The identification errors are discussed to illustrate that the novel faul t identification algorithm is adaptive in the fault scenarios with network traff ic change.
文摘Nowadays, the DC distribution system has been suggested, as a replacement for the AC power distribution system with electric propulsion. This idea signifies a fresh approach of issuing energy for low-voltage installations. It can be used for any electrical application up to 20 MW and works at a nominal voltage of 1000 V DC. The DC distribution system is just an extension of the multiple DC links that previously available in all propulsion and thruster drives, which typically comprise more than 80% of the electrical power consumption on electric propulsion vessels. A fault detection and islanding scheme for DC grid connected PV system is presented in this paper. Unlike traditional ac distribution systems, protection has been challenging for dc systems. The goals of this paper are to classify and detect the fault in the PV system as well as DC grid and to isolate the faulted section so that the system keeps operating without disabling the entire system. The results show the measured values of power at PV panel and DC grid side under different fault condition, which indicates the type of fault that occurs in the system.
文摘A distributed generation system(DG)has several benefits over a traditional centralized power system.However,the protection area in the case of the distributed generator requires special attention as it encounters stability loss,failure re-closure,fluctuations in voltage,etc.And thereby,it demands immediate attention in identifying the location&type of a fault without delay especially when occurred in a small,distributed generation system,as it would adversely affect the overall system and its operation.In the past,several methods were proposed for classification and localisation of a fault in a distributed generation system.Many of those methods were accurate in identifying location,but the accuracy in identifying the type of fault was not up to the acceptable mark.The proposed work here uses a shallow artificial neural network(sANN)model for identifying a particular type of fault that could happen in a specific distribution network when used in conjunction with distributed generators.Firstly,a distribution network consisting of two similar distributed generators(DG1 and DG2),one grid,and a 100 Km distribution line is modeled.Thereafter,different voltages and currents corresponding to various faults(line to line,line to ground)at different locations are tabulated,resulting in a matrix of 500×18 inputs.Secondly,the sANN is formulated for identifying the types of faults in the system in which the above-obtained data is used to train,validate,and test the neural network.The overall result shows an unprecedented almost zero percent error in identifying the type of the faults.
文摘According to the background of the rub impact faults of aerial engines and industrial turbines, two kinds of test rigs, on the base of the dynamics model, are established to study the rub impact faults between rotor and stator with free supports. The orbit of the vibration of rotor displacement is respectively examined on the four impact conditions, which are the normal state with no impact, the early sharp impact statement, the semi sharp impact statement and the terminal blunt impact statement. The route to chaos, appearing with the early sharp impact, is observed for the first time. By analyzing the frequency domain characteristics of the experimental data on four impact conditions, it is testified that the appearance of the sub harmonic vibrations of the order 1/3 and 1/4 is the effective evidence to judge whether or not the blade has initial light rub impact. When there are only the harmonic vibrations of the order of 1/1 and 1/2, the blade stator rub impact faults have become very serious.
基金supported by the National Basic Research Program of China (No.2011CB707004)the National Natural Science Foundation of China (No.61179054)
文摘Receiver autonomous integrity monitoring（RAIM） provides integrity monitoring of global positioning system（GPS） for safety-of-life applications.In the process of RAIM, fault identification（FI） enables navigation to continue in the presence of fault measurement.Affected by satellite geometry, the leverage of each measurement in position solution may differ greatly.However, the conventional RAIM FI methods are generally based on maximum likelihood of ranging error for different measurements, thereby causing a major decrease in the probability of correct identification for the fault measurement with high leverage.In this paper, the impact of leverage on the fault identification is analyzed.The leveraged RAIM fault identification（L-RAIM FI） method is proposed with consideration of the difference in leverage for each satellite in view.Furthermore,the theoretical probability of correct identification is derived to evaluate the performance of L-RAIM FI method.The experiments in various typical scenarios demonstrate the effectiveness of L-RAIM FI method over conventional FI methods in the probability of correct identification for the fault with high leverage.
基金supported by Fundamental Research Funds Program for the Central Universities(No.2019MS014)Key-Area Research and Development Program of Guangdong Province(No.2020B010166004).
文摘With the integration of alternative energy and renewables,the issue of stability and resilience of the power network has received considerable attention.The basic necessity for fault diagnosis and isolation is fault identification and location.The conventional intelligent fault identification method needs supervision,manual labelling of characteristics,and requires large amounts of labelled data.To enhance the ability of intelligent methods and get rid of the dependence on a large amount of labelled data,a novel fault identification method based on deep reinforcement learning(DRL),which has not received enough attention in the field of fault identification,is investigated in this paper.The proposed method uses different faults as parameters of the model to expand the scope of fault identification.In addition,the DRL algorithm can intelligently modify the fault parameters according to the observations obtained from the power network environment,rather than requiring manual and mechanical tuning of parameters.The methodology was tested on the IEEE 14 bus for several scenarios and the performance of the proposed method was compared with that of population-based optimization methods and supervised learning methods.The obtained results have confirmed the feasibility and effectiveness of the proposed method.
文摘Identification and classification of DC faults are considered as fundamentals of DC grid protection.A sudden rise of DC fault current must be identified and classified to immediately operate the corresponding interrupting mechanism.In this paper,the Boltzmann machine learning(BML)approach is proposed for identification and classification of DC faults using travelling waves generated at fault point in voltage source converter based high-voltage direct current(VSC-HVDC)transmission system.An unsupervised way of feature extraction is performed on the frequency spectrum of the travelling waves.Binomial class logistic regression(BCLR)classifies the HVDC transmission system into faulty and healthy states.The proposed technique reduces the time for fault identification and classification because of reduced tagged data with few characteristics.Therefore,the faults near or at converter stations are readily identified and classified.The performance of the proposed technique is assessed via simulations developed in MATLAB/Simulink and tested for pre-fault and post-fault data both at VSC1 and VSC2,respectively.Moreover,the proposed technique is supported by analyzing the root mean square error to show practicality and realization with reduced computations.
基金Supported by the State Key Laboratory of Vibration Shock and Noise in Shanghai Jiao Tong University China
文摘The size and complexity of modern equipment require more advanced fault diagnosis techniques. Different from signal analysis based methods, a dynamic model based diagnosis technique can further diagnose the location and severity of the fault, and detect multiple faults at one time. A model based fault diagnosis method was developed to identify typical faults of rotating machinery. This method can identify mass unbalances, crack locations and sizes, and oil film parameters in rotating machinery by optimization methods and dynamics simulation technique. Numerical and experimental results demonstrate that the method is useful for detecting faults of rotating systems.
基金supported by the Natural Science Foundation of Shandong Province(ZR202103050722).
文摘This study combined fault identification with a deep learning algorithm and applied a convolutional neural network(CNN)design based on an improved balanced crossentropy(BCE)loss function to address the low accuracy in the intelligent identification of seismic faults and the slow training speed of convolutional neural networks caused by unbalanced training sample sets.The network structure and optimal hyperparameters were determined by extracting feature maps layer by layer and by analyzing the results of seismic feature extraction.The BCE loss function was used to add the parameter which is the ratio of nonfaults to the total sample sets,thereby changing the loss function to find the reference of the minimum weight parameter and adjusting the ratio of fault to nonfault data.The method overcame the unbalanced number of sample sets and improved the iteration speed.After a brief training,the accuracy could reach more than 95%,and gradient descent was evident.The proposed method was applied to fault identification in an oilfield area.The trained model can predict faults clearly,and the prediction results are basically consistent with an actual case,verifying the effectiveness and adaptability of the method.
文摘Sequential diagnosis is a very useful strategy for system-level fault identification because of its lower cost of hardware.In this paper,the characterization of sequentially t-diagnosable system is given,and a tmiversal algorithm to seek faulty units in the system is developed.
基金Supported by National Natural Science Foundation of China(Grant No51005205)Science Fund for Creative Research Groups of Nationa Natural Science Foundation of China(Grant No.51221004)+1 种基金Nationa Basic Research Program of China(973 Program,Grant No.2013CB035405)Open Foundation of State Key Laboratory of Automotive Safety and Energy,Tsinghua University,China(Grant No.KF13011)
文摘The intermittent connection（IC）of the field-bus in networked manufacturing systems is a common but hard troubleshooting network problem,which may result in system level failures or safety issues.However,there is no online IC location identification method available to detect and locate the position of the problem.To tackle this problem,a novel model based online fault location identification method for localized IC problem is proposed.First,the error event patterns are identified and classified according to different node sources in each error frame.Then generalized zero inflated Poisson process（GZIP）model for each node is established by using time stamped error event sequence.Finally,the location of the IC fault is determined by testing whether the parameters of the fitted stochastic model is statistically significant or not using the confident intervals of the estimated parameters.To illustrate the proposed method,case studies are conducted on a 3-node controller area network（CAN）test-bed,in which IC induced faults are imposed on a network drop cable using computer controlled on-off switches.The experimental results show the parameters of the GZIP model for the problematic node are statistically significant（larger than 0）,and the patterns of the confident intervals of the estimated parameters are directly linked to the problematic node,which agrees with the experimental setup.The proposed online IC location identification method can successfully identify the location of the drop cable on which IC faults occurs on the CAN network.
文摘Fractal dimensions of a terrain quantitatively describe the self-organizedstructure of the terrain geometry. However, the local topographic variation cannot be illustrated bythe conventional box-counting method. This paper proposes a successive shift box-counting method,in which the studied object is divided into small sub-objects that are composed of a series of gridsaccording to its characteristic scaling. The terrain fractal dimensions in the grids are calculatedwith the successive shift box-counting method and the scattered points with values of fractaldimensions are obtained. The present research shows that the planar variation of fractal dimensionsis well consistent with fault traces and geological boundaries.
基金supported by the Deanship of Scientific Research at Prince Sattam Bin Abdulaziz University under the research project No.2020/01/11742.
文摘Fuzzy logic control(FLC)systems have found wide utilization in several industrial applications.This paper proposes a fuzzy logic-based fault detection and identification method for open-circuit switch fault in grid-tied photovoltaic(PV)inverters.Large installations and ambitious plans have been recently achieved for PV systems as clean and renewable power generation sources due to their improved environmental impacts and availability everywhere.Power converters represent the main parts for the grid integration of PV systems.However,PV power converters contain several power switches that construct their circuits.The power switches in PV systems are highly subjected to high stresses due to the continuously varying operating conditions.Moreover,the grid-tied systems represent nonlinear systems and the system model parameters are changing continuously.Consequently,the grid-tied PV systems have a nonlinear factor and the fault detection and identification(FDI)methods based on using mathematical models become more complex.The proposed fuzzy logic-based FDI(FL-FDI)method is based on employing the fuzzy logic concept for detecting and identifying the location of various switch faults.The proposed FL-FDI method is designed and extracted from the analysis and comparison of the various measured voltage/current components for the control purposes.Therefore,the proposed FL-FDI method does not require additional components or measurement circuits.Additionally,the proposed method can detect the faulty condition and also identify the location of the faulty switch for replacement and maintenance purposes.The proposed method can detect the faulty condition within only a single fundamental line period without the need for additional sensors and/or performing complex calculations or precise models.The proposed FL-FDI method is tested on the widely used T-type PV inverter system,wherein there are twelve different switches and the FDI process represents a challenging task.The results shows the superior and accurate performance of the proposed FL-FDI method.
基金Postdoctoral Foundation of China(No.20070410755)PAN Zhencun,born in 1962,male,postdoctor researcher.
文摘A diagnostic signal current trace detecting based single phase-to-ground fault line identifica- tion and section location method for non-effectively grounded distribution systems is presented in this paper.A special diagnostic signal current is injected into the fault distribution system,and then it is detected at the outlet terminals to identify the fault line and at the sectionalizing or branching point along the fault line to locate the fault section.The method has been put into application in actual distribution network and field experience shows that it can identify the fault line and locate the fault section correctly and effectively.
文摘In this paper, we suggest a novel parsimonious neurofuzzy model realized by RBFNs for railway carriage system identification and fault diagnosis. To overcome the curse of dimensionality resulting from high dimensional input variables, in our developed model the features extracted from the available observations are regarded as the input variables by adopting the higher-order statistics(HOS) technique. Such a constructed model is also applied to a practical railway carriage system, simulation results indicate that the developed neurofuzzy model possesses strong identification and fault diagnosis ability.
基金supported by the National Key Research and Development Program of China (No.2022YFC2806102)the National Natural Science Foundation of China (No.52171287,52325107)+3 种基金High-tech Ship Research Project of Ministry of Industry and Information Technology (No.2023GXB01-05-004-03,No.GXBZH2022-293)the Science Foundation for Distinguished Young Scholars of Shandong Province (No.ZR2022JQ25)the Taishan Scholars Project (No.tsqn201909063)the Fundamental Research Funds for the Central Universities (No.24CX10006A)。
文摘The subsea production system is a vital equipment for offshore oil and gas production.The control system is one of the most important parts of it.Collecting and processing the signals of subsea sensors is the only way to judge whether the subsea production control system is normal.However,subsea sensors degrade rapidly due to harsh working environments and long service time.This leads to frequent false alarm incidents.A combinatorial reasoning-based abnormal sensor recognition method for subsea production control system is proposed.A combinatorial algorithm is proposed to group sensors.The long short-term memory network(LSTM)is used to establish a single inference model.A counting-based judging method is proposed to identify abnormal sensors.Field data from an offshore platform in the South China Sea is used to demonstrate the effect of the proposed method.The results show that the proposed method can identify the abnormal sensors effectively.
文摘Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.
基金This work was supported by the Alexander von Humboldt Foundation.
文摘This paper proposes a parity relation based fault estimation for a class of nonlinear systems which can be modelled by Takagi-Sugeno （TS） fuzzy models. The design of a parity relation based residual generator is formulated in terms of a family of linear matrix inequalities （LMIs）. A numerical example is provided to illustrate the effectiveness of the proposed design techniques.
