Distribution transformers play a vital role in power distribution systems,and their reliable operation is crucial for grid stability.This study presents a simulation-based framework for active fault diagnosis and earl...Distribution transformers play a vital role in power distribution systems,and their reliable operation is crucial for grid stability.This study presents a simulation-based framework for active fault diagnosis and early warning of distribution transformers,integrating Sample Ensemble Learning(SEL)with a Self-Optimizing Support Vector Machine(SO-SVM).The SEL technique enhances data diversity and mitigates class imbalance,while SO-SVM adaptively tunes its hyperparameters to improve classification accuracy.A comprehensive transformer model was developed in MATLAB/Simulink to simulate diverse fault scenarios,including inter-turn winding faults,core saturation,and thermal aging.Feature vectors were extracted from voltage,current,and temperature measurements to train and validate the proposed hybrid model.Quantitative analysis shows that the SEL–SO-SVM framework achieves a classification accuracy of 97.8%,a precision of 96.5%,and an F1-score of 97.2%.Beyond classification,the model effectively identified incipient faults,providing an early warning lead time of up to 2.5 s before significant deviations in operational parameters.This predictive capability underscores its potential for preventing catastrophic transformer failures and enabling timely maintenance actions.The proposed approach demonstrates strong applicability for enhancing the reliability and operational safety of distribution transformers in simulated environments,offering a promising foundation for future real-time and field-level implementations.展开更多
The Guanxian-Anxian fault zone in the Longmen Shan,Sichuan,China,exhibits long-term creep-slip but ruptured during the 2008 Wenchuan earthquake,challenging the view that creeping faults rarely generate strong earthqua...The Guanxian-Anxian fault zone in the Longmen Shan,Sichuan,China,exhibits long-term creep-slip but ruptured during the 2008 Wenchuan earthquake,challenging the view that creeping faults rarely generate strong earthquakes.To investigate the transition from creep-slip to stick-slip,we analyzed fault rocks from the WFSD-3,using microstructural observations,XRD,μXRF,Raman spectroscopy,and quartz grain size statistics.Fault rocks show intense foliation,pressure-solution structures,and abundant clay minerals,reflecting long-term aseismic creep.At the interface between black and gray fault gouges at~1249.98 m,microstructures indicate stick-slip behavior,including truncated grains,angular fragments,and finer grain sizes.Here,clay content drops sharply while strong minerals(quartz,feldspar,calcite,dolomite)increase.Elemental mapping shows Al and K enriched in black gouge,whereas Ca and Si in gray gouge;Raman spectroscopy indicates possible graphitization;the finest quartz grains occur in black gouge.These features mark co-seismic principal slip zone of the Wenchuan earthquake.We propose that fluid-driven transformation of strong minerals into clays facilitates creep-slip,whereas localized precipitation of strong minerals strengthens the fault,causing stress accumulation and controlling the creep-slip to stick-slip transition.This mechanism has implications for reassessing seismic hazards of creeping faults.展开更多
With the rapid development of large-scale offshore wind farms,efficient and reliable power transmission systems are urgently needed.Hybrid high-voltage direct current(HVDC)configurations combining a diode rectifier un...With the rapid development of large-scale offshore wind farms,efficient and reliable power transmission systems are urgently needed.Hybrid high-voltage direct current(HVDC)configurations combining a diode rectifier unit(DRU)and a modular multilevel converter(MMC)have emerged as a promising solution,offering advantages in cost-effectiveness and control capability.However,the uncontrollable nature of the DRU poses significant challenges for systemstability under offshore AC fault conditions,particularly due to its inability to provide fault current or voltage support.This paper investigates the offshore AC fault characteristics and fault ride-through(FRT)strategy of a hybrid offshore wind power transmission system based on a diode rectifier unit DRU and MMC.First,the dynamic response of the hybrid system under offshore symmetrical three-phase faults is analyzed.It is demonstrated that due to the unidirectional conduction nature of the DRU,its AC current rapidly drops to zero during faults,and the fault current is solely contributed by the wind turbine generators(WTGs)and wind farm MMC(WFMMC).Based on this analysis,a coordinated FRT strategy is proposed,which combines a segmented current limiting control for the wind-turbine(WT)grid-side converters(GSCs)and a constant AC current control for the WFMMC.The strategy ensures effective voltage support during the fault and prevents MMC current saturation during fault recovery,enabling fast and stable system restoration.Electromagnetic transient simulations in PSCAD/EMTDC verify the feasibility of the proposed fault ride-through strategy.展开更多
The Yingxiu-Beichuan fault zone(YBFZ)has long been active and experienced repeated large earthquakes.The physicochemical properties of the deep fault zone(>1000 m)are the key to understanding the deformation mechan...The Yingxiu-Beichuan fault zone(YBFZ)has long been active and experienced repeated large earthquakes.The physicochemical properties of the deep fault zone(>1000 m)are the key to understanding the deformation mechanism of large earthquakes.This study uses rock magnetic,microstructural,and geochemical analyses of representative samples exposed in FZ1681 within the Wenchuan Earthquake Fault Scientific Drilling borehole 2(WFSD-2)cores.Fault gouge and fault breccia have higher magnetic susceptibility values than wall rocks,and they contain abundant paramagnetic minerals and small quantities of magnetite and monoclinic pyrrhotite.The magnetite and monoclinic pyrrhotite in the fault gouge were mainly formed by coseismic frictional heating,indicating that large earthquakes with frictional heating temperatures of~500-900℃once occurred in the YBFZ.The seismogenic and coseismic environment was reducing with a relatively high sulfur content.The monoclinic pyrrhotite in the fault breccia was formed mainly by low-temperature hydrothermal fluid.This indicates that the fault zone experienced reducing and low-temperature(<400℃)hydrothermal fluid with a relatively high sulfur content after the earthquake.The YBFZ,which experiences frequent large earthquakes,is weakly oxidizing environment at different depths,but the effect of the low-temperature hydrothermal fluid is weaker at depth.展开更多
To address the issues of high costs and low component utilization caused by the independent configuration of hybrid DC circuit breakers(HCBs)and DC power flow controllers(DCPFCs)at each port in existing DC distributio...To address the issues of high costs and low component utilization caused by the independent configuration of hybrid DC circuit breakers(HCBs)and DC power flow controllers(DCPFCs)at each port in existing DC distribution networks,this paper adopts a component sharing mechanism to propose a composite multi-port hybrid DC circuit breaker(CM-HCB)with DC power flow and fault current limitation abilities,as well as reduced component costs.The proposed CM-HCB topology enables the sharing of the main breaker branch(MB)and the energy dissipation branch,while the load commutation switches(LCSs)in the main branch are reused as power flow control components,enabling flexible regulation of power flow in multiple lines.Meanwhile,by reconstructing the current path during the fault process,the proposed CM-HCB can utilize the internal coupled inductor to limit the current rise rate at the initial stage of the fault,significantly reducing the requirement for breaking current.A detailed study on the topological structure,steady-state power flow regulation mechanism,transient fault isolation mechanism,control strategy and characteristic analysis of the proposed CM-HCB is presented.Then,a Matlab/Simulink-based meshed three-terminal DC grid simulation platform with the proposed CM-HCB is built.The results indicate that the proposed CM-HCB can not only achieve flexible power flow control during steady-state operation,but also obtain current rise limitation and fault isolation abilities under short-circuit fault conditions,verifying its correctness and effectiveness.Finally,a comparative economic analysis is conducted between the proposed CM-HCB and the other two existing solutions,confirming that its component sharing mechanism can significantly reduce the number of components,lower system costs,and improve component utilization.展开更多
Grid-Forming(GFM)converters are prone to fault-induced overcurrent and power angle instability during grid fault-induced voltage sags.To address this,this paper develops a multi-loop coordinated fault ridethrough(FRT)...Grid-Forming(GFM)converters are prone to fault-induced overcurrent and power angle instability during grid fault-induced voltage sags.To address this,this paper develops a multi-loop coordinated fault ridethrough(FRT)control strategy based on a power outer loop and voltage-current inner loops,aiming to enhance the stability and current-limiting capability of GFM converters during grid fault conditions.During voltage sags,the GFM converter’s voltage source behavior is maintained by dynamically adjusting the reactive power reference to provide voltage support,thereby effectively suppressing the steady-state component of the fault current.To address the active power imbalance induced by voltage sags,a dynamic active power reference correction method based on apparent power is designed to mitigate power angle oscillations and limit transient current.Moreover,an adaptive virtual impedance loop is implemented to enhance dynamic transient current-limiting performance during the fault initiation phase.This approach improves the responsiveness of the inner loop and ensures safe system operation under various fault severities.Under asymmetric fault conditions,a negative-sequence reactive current compensation strategy is incorporated to further suppress negative-sequence voltage and improve voltage symmetry.The proposed control scheme enables coordinated operation of multiple control objectives,including voltage support,current suppression,and power angle stability,across different fault scenarios.Finally,MATLAB/Simulink simulation results validate the effectiveness of the proposed strategy,showcasing its superior performance in current limiting and power angle stability,thereby significantly enhancing the system’s fault ride-through capability.展开更多
Continual learning fault diagnosis(CLFD)has gained growing interest in mechanical systems for its ability to accumulate and transfer knowledge in dynamic fault diagnosis scenarios.However,existing CLFD methods typical...Continual learning fault diagnosis(CLFD)has gained growing interest in mechanical systems for its ability to accumulate and transfer knowledge in dynamic fault diagnosis scenarios.However,existing CLFD methods typically assume balanced task distributions,neglecting the long-tailed nature of real-world fault occurrences,where certain faults dominate while others are rare.Due to the long-tailed distribution among different me-chanical conditions,excessive attention has been focused on the dominant type,leading to performance de-gradation in rarer types.In this paper,decoupling incremental classifier and representation learning(DICRL)is proposed to address the dual challenges of catastrophic forgetting introduced by incremental tasks and the bias in long-tailed CLFD(LT-CLFD).The core innovation lies in the structural decoupling of incremental classifier learning and representation learning.An instance-balanced sampling strategy is employed to learn more dis-criminative deep representations from the exemplars selected by the herding algorithm and new data.Then,the previous classifiers are frozen to prevent damage to representation learning during backward propagation.Cosine normalization classifier with learnable weight scaling is trained using a class-balanced sampling strategy to enhance classification accuracy.Experimental results demonstrate that DICRL outperforms existing continual learning methods across multiple benchmarks,demonstrating superior performance and robustness in both LT-CLFD and conventional CLFD.DICRL effectively tackles both catastrophic forgetting and long-tailed distribution in CLFD,enabling more reliable fault diagnosis in industrial applications.展开更多
The shallow slip deficit(SSD)during strike-slip earthquakes raises a question of how the strain budget is accommodated over multiple cycles.However,the origin of variable SSD observed in different earthquakes is still...The shallow slip deficit(SSD)during strike-slip earthquakes raises a question of how the strain budget is accommodated over multiple cycles.However,the origin of variable SSD observed in different earthquakes is still under debate because each earthquake has its unique initial stress condition.Here,we derive the slip model of the 2021 M W 7.4 Maduo earthquake in Qinghai,China,using multi-track radar images.Our results revealed that,in contrast to the large SSD on segments close to the epicenter,a much smaller SSD was observed at the west terminus of the rupture,where aftershock distribution indicates that the fault changes dip direction at 6 km depth.The 2021 Maduo earthquake thus represents an extraordinary case of significant along-strike SSD variation.After accounting for interseismic,postseismic,and diffuse off-fault deformation,we find that this variation is likely contributed by the along-dipping geometrical variation,implying that a multi-segment earthquake may leave heterogeneous stress condition on the fault with different amounts of SSD.展开更多
Knowledge graphs,which combine structured representation with semantic modeling,have shown great potential in knowledge expression,causal inference,and automated reasoning,and are widely used in fields such as intelli...Knowledge graphs,which combine structured representation with semantic modeling,have shown great potential in knowledge expression,causal inference,and automated reasoning,and are widely used in fields such as intelligent question answering,decision support,and fault diagnosis.As high-speed train systems become increasingly intelligent and interconnected,fault patterns have grown more complex and dynamic.Knowledge graphs offer a promising solution to support the structured management and real-time reasoning of fault knowledge,addressing key requirements such as interpretability,accuracy,and continuous evolution in intelligent diagnostic systems.However,conventional knowledge graph construction relies heavily on domain expertise and specialized tools,resulting in high entry barriers for non-experts and limiting their practical application in frontline maintenance scenarios.To address this limitation,this paper proposes a fault knowledge modeling approach for high-speed trains that integrates structured logic diagrams with knowledge graphs.The method employs a seven-layer logic structure—comprising fault name,applicable vehicles,diagnostic logic,signal parameters,verification conditions,fault causes,and emergency measures—to transform unstructured knowledge into a visual and hierarchical representation.A semantic mapping mechanism is then used to automatically convert logic diagrams into machine-interpretable knowledge graphs,enabling dynamic reasoning and knowledge reuse.Furthermore,the proposed method establishes a three-layer architecture—logic structuring,knowledge graph transformation,and dynamic inference—to bridge human-expert logic with machinebased reasoning.Experimental validation and system implementation demonstrate that this approach not only improves knowledge interpretability and inference precision but also significantly enhances modeling efficiency and system maintainability.It provides a scalable and adaptable solution for intelligent operation and maintenance platforms in the high-speed rail domain.展开更多
This paper investigates the reliability of internal marine combustion engines using an integrated approach that combines Fault Tree Analysis(FTA)and Bayesian Networks(BN).FTA provides a structured,top-down method for ...This paper investigates the reliability of internal marine combustion engines using an integrated approach that combines Fault Tree Analysis(FTA)and Bayesian Networks(BN).FTA provides a structured,top-down method for identifying critical failure modes and their root causes,while BN introduces flexibility in probabilistic reasoning,enabling dynamic updates based on new evidence.This dual methodology overcomes the limitations of static FTA models,offering a comprehensive framework for system reliability analysis.Critical failures,including External Leakage(ELU),Failure to Start(FTS),and Overheating(OHE),were identified as key risks.By incorporating redundancy into high-risk components such as pumps and batteries,the likelihood of these failures was significantly reduced.For instance,redundant pumps reduced the probability of ELU by 31.88%,while additional batteries decreased the occurrence of FTS by 36.45%.The results underscore the practical benefits of combining FTA and BN for enhancing system reliability,particularly in maritime applications where operational safety and efficiency are critical.This research provides valuable insights for maintenance planning and highlights the importance of redundancy in critical systems,especially as the industry transitions toward more autonomous vessels.展开更多
The critical components of gas turbines suffer from prolonged exposure to factors such as thermal oxidation,mechanical wear,and airflow disturbances during prolonged operation.These conditions can lead to a series of ...The critical components of gas turbines suffer from prolonged exposure to factors such as thermal oxidation,mechanical wear,and airflow disturbances during prolonged operation.These conditions can lead to a series of issues,including mechanical faults,air path malfunctions,and combustion irregularities.Traditional modelbased approaches face inherent limitations due to their inability to handle nonlinear problems,natural factors,measurement uncertainties,fault coupling,and implementation challenges.The development of artificial intelligence algorithms has provided an effective solution to these issues,sparking extensive research into data-driven fault diagnosis methodologies.The review mechanism involved searching IEEE Xplore,ScienceDirect,and Web of Science for peerreviewed articles published between 2019 and 2025,focusing on multi-fault diagnosis techniques.A total of 220 papers were identified,with 123 meeting the inclusion criteria.This paper provides a comprehensive review of diagnostic methodologies,detailing their operational principles and distinctive features.It analyzes current research hotspots and challenges while forecasting future trends.The study systematically evaluates the strengths and limitations of various fault diagnosis techniques,revealing their practical applicability and constraints through comparative analysis.Furthermore,this paper looks forward to the future development direction of this field and provides a valuable reference for the optimization and development of gas turbine fault diagnosis technology in the future.展开更多
Deep learning-based wind turbine blade fault diagnosis has been widely applied due to its advantages in end-to-end feature extraction.However,several challenges remain.First,signal noise collected during blade operati...Deep learning-based wind turbine blade fault diagnosis has been widely applied due to its advantages in end-to-end feature extraction.However,several challenges remain.First,signal noise collected during blade operation masks fault features,severely impairing the fault diagnosis performance of deep learning models.Second,current blade fault diagnosis often relies on single-sensor data,resulting in limited monitoring dimensions and ability to comprehensively capture complex fault states.To address these issues,a multi-sensor fusion-based wind turbine blade fault diagnosis method is proposed.Specifically,a CNN-Transformer Coupled Feature Learning Architecture is constructed to enhance the ability to learn complex features under noisy conditions,while a Weight-Aligned Data Fusion Module is designed to comprehensively and effectively utilize multi-sensor fault information.Experimental results of wind turbine blade fault diagnosis under different noise interferences show that higher accuracy is achieved by the proposed method compared to models with single-source data input,enabling comprehensive and effective fault diagnosis.展开更多
文摘Distribution transformers play a vital role in power distribution systems,and their reliable operation is crucial for grid stability.This study presents a simulation-based framework for active fault diagnosis and early warning of distribution transformers,integrating Sample Ensemble Learning(SEL)with a Self-Optimizing Support Vector Machine(SO-SVM).The SEL technique enhances data diversity and mitigates class imbalance,while SO-SVM adaptively tunes its hyperparameters to improve classification accuracy.A comprehensive transformer model was developed in MATLAB/Simulink to simulate diverse fault scenarios,including inter-turn winding faults,core saturation,and thermal aging.Feature vectors were extracted from voltage,current,and temperature measurements to train and validate the proposed hybrid model.Quantitative analysis shows that the SEL–SO-SVM framework achieves a classification accuracy of 97.8%,a precision of 96.5%,and an F1-score of 97.2%.Beyond classification,the model effectively identified incipient faults,providing an early warning lead time of up to 2.5 s before significant deviations in operational parameters.This predictive capability underscores its potential for preventing catastrophic transformer failures and enabling timely maintenance actions.The proposed approach demonstrates strong applicability for enhancing the reliability and operational safety of distribution transformers in simulated environments,offering a promising foundation for future real-time and field-level implementations.
基金supported by the National Natural Science Foundation of China(42230312,42272270,42172262,42372266)the Deep Earth Probe and Mineral Resources Exploration-National Science and Technology Major Project(2024ZD1000500)the China Geological Survey Project(DD20240041).
文摘The Guanxian-Anxian fault zone in the Longmen Shan,Sichuan,China,exhibits long-term creep-slip but ruptured during the 2008 Wenchuan earthquake,challenging the view that creeping faults rarely generate strong earthquakes.To investigate the transition from creep-slip to stick-slip,we analyzed fault rocks from the WFSD-3,using microstructural observations,XRD,μXRF,Raman spectroscopy,and quartz grain size statistics.Fault rocks show intense foliation,pressure-solution structures,and abundant clay minerals,reflecting long-term aseismic creep.At the interface between black and gray fault gouges at~1249.98 m,microstructures indicate stick-slip behavior,including truncated grains,angular fragments,and finer grain sizes.Here,clay content drops sharply while strong minerals(quartz,feldspar,calcite,dolomite)increase.Elemental mapping shows Al and K enriched in black gouge,whereas Ca and Si in gray gouge;Raman spectroscopy indicates possible graphitization;the finest quartz grains occur in black gouge.These features mark co-seismic principal slip zone of the Wenchuan earthquake.We propose that fluid-driven transformation of strong minerals into clays facilitates creep-slip,whereas localized precipitation of strong minerals strengthens the fault,causing stress accumulation and controlling the creep-slip to stick-slip transition.This mechanism has implications for reassessing seismic hazards of creeping faults.
基金funded by the Science and Technology Projects of State Grid Zhejiang Electric Power Co.,Ltd.(5211DS24000G).
文摘With the rapid development of large-scale offshore wind farms,efficient and reliable power transmission systems are urgently needed.Hybrid high-voltage direct current(HVDC)configurations combining a diode rectifier unit(DRU)and a modular multilevel converter(MMC)have emerged as a promising solution,offering advantages in cost-effectiveness and control capability.However,the uncontrollable nature of the DRU poses significant challenges for systemstability under offshore AC fault conditions,particularly due to its inability to provide fault current or voltage support.This paper investigates the offshore AC fault characteristics and fault ride-through(FRT)strategy of a hybrid offshore wind power transmission system based on a diode rectifier unit DRU and MMC.First,the dynamic response of the hybrid system under offshore symmetrical three-phase faults is analyzed.It is demonstrated that due to the unidirectional conduction nature of the DRU,its AC current rapidly drops to zero during faults,and the fault current is solely contributed by the wind turbine generators(WTGs)and wind farm MMC(WFMMC).Based on this analysis,a coordinated FRT strategy is proposed,which combines a segmented current limiting control for the wind-turbine(WT)grid-side converters(GSCs)and a constant AC current control for the WFMMC.The strategy ensures effective voltage support during the fault and prevents MMC current saturation during fault recovery,enabling fast and stable system restoration.Electromagnetic transient simulations in PSCAD/EMTDC verify the feasibility of the proposed fault ride-through strategy.
基金supported by the Deep Earth Probe and Mineral Resources Exploration-National Science and Technology Major Project(2024ZD1000500)the National Natural Science Foundation of China(42172262 and 42372266)+1 种基金the China Geological Survey(DD20240041)the Fundamental Research Funds of the Institute of Geomechanics(DZLXJK202516).
文摘The Yingxiu-Beichuan fault zone(YBFZ)has long been active and experienced repeated large earthquakes.The physicochemical properties of the deep fault zone(>1000 m)are the key to understanding the deformation mechanism of large earthquakes.This study uses rock magnetic,microstructural,and geochemical analyses of representative samples exposed in FZ1681 within the Wenchuan Earthquake Fault Scientific Drilling borehole 2(WFSD-2)cores.Fault gouge and fault breccia have higher magnetic susceptibility values than wall rocks,and they contain abundant paramagnetic minerals and small quantities of magnetite and monoclinic pyrrhotite.The magnetite and monoclinic pyrrhotite in the fault gouge were mainly formed by coseismic frictional heating,indicating that large earthquakes with frictional heating temperatures of~500-900℃once occurred in the YBFZ.The seismogenic and coseismic environment was reducing with a relatively high sulfur content.The monoclinic pyrrhotite in the fault breccia was formed mainly by low-temperature hydrothermal fluid.This indicates that the fault zone experienced reducing and low-temperature(<400℃)hydrothermal fluid with a relatively high sulfur content after the earthquake.The YBFZ,which experiences frequent large earthquakes,is weakly oxidizing environment at different depths,but the effect of the low-temperature hydrothermal fluid is weaker at depth.
基金funded by Youth Talent Growth Project of Guizhou Provincial Department of Education(No.Qianjiaoji[2024]21)National Natural Science Foundation of China(No.62461008 and No.52507211)Guizhou Provincial Key Technology R&D Program(No.[2024]General 049).
文摘To address the issues of high costs and low component utilization caused by the independent configuration of hybrid DC circuit breakers(HCBs)and DC power flow controllers(DCPFCs)at each port in existing DC distribution networks,this paper adopts a component sharing mechanism to propose a composite multi-port hybrid DC circuit breaker(CM-HCB)with DC power flow and fault current limitation abilities,as well as reduced component costs.The proposed CM-HCB topology enables the sharing of the main breaker branch(MB)and the energy dissipation branch,while the load commutation switches(LCSs)in the main branch are reused as power flow control components,enabling flexible regulation of power flow in multiple lines.Meanwhile,by reconstructing the current path during the fault process,the proposed CM-HCB can utilize the internal coupled inductor to limit the current rise rate at the initial stage of the fault,significantly reducing the requirement for breaking current.A detailed study on the topological structure,steady-state power flow regulation mechanism,transient fault isolation mechanism,control strategy and characteristic analysis of the proposed CM-HCB is presented.Then,a Matlab/Simulink-based meshed three-terminal DC grid simulation platform with the proposed CM-HCB is built.The results indicate that the proposed CM-HCB can not only achieve flexible power flow control during steady-state operation,but also obtain current rise limitation and fault isolation abilities under short-circuit fault conditions,verifying its correctness and effectiveness.Finally,a comparative economic analysis is conducted between the proposed CM-HCB and the other two existing solutions,confirming that its component sharing mechanism can significantly reduce the number of components,lower system costs,and improve component utilization.
文摘Grid-Forming(GFM)converters are prone to fault-induced overcurrent and power angle instability during grid fault-induced voltage sags.To address this,this paper develops a multi-loop coordinated fault ridethrough(FRT)control strategy based on a power outer loop and voltage-current inner loops,aiming to enhance the stability and current-limiting capability of GFM converters during grid fault conditions.During voltage sags,the GFM converter’s voltage source behavior is maintained by dynamically adjusting the reactive power reference to provide voltage support,thereby effectively suppressing the steady-state component of the fault current.To address the active power imbalance induced by voltage sags,a dynamic active power reference correction method based on apparent power is designed to mitigate power angle oscillations and limit transient current.Moreover,an adaptive virtual impedance loop is implemented to enhance dynamic transient current-limiting performance during the fault initiation phase.This approach improves the responsiveness of the inner loop and ensures safe system operation under various fault severities.Under asymmetric fault conditions,a negative-sequence reactive current compensation strategy is incorporated to further suppress negative-sequence voltage and improve voltage symmetry.The proposed control scheme enables coordinated operation of multiple control objectives,including voltage support,current suppression,and power angle stability,across different fault scenarios.Finally,MATLAB/Simulink simulation results validate the effectiveness of the proposed strategy,showcasing its superior performance in current limiting and power angle stability,thereby significantly enhancing the system’s fault ride-through capability.
基金Supported by National Natural Science Foundation of China(Grant No.52272440)Suzhou Science Foundation(Grant Nos.SYG202323,ZXL2022027).
文摘Continual learning fault diagnosis(CLFD)has gained growing interest in mechanical systems for its ability to accumulate and transfer knowledge in dynamic fault diagnosis scenarios.However,existing CLFD methods typically assume balanced task distributions,neglecting the long-tailed nature of real-world fault occurrences,where certain faults dominate while others are rare.Due to the long-tailed distribution among different me-chanical conditions,excessive attention has been focused on the dominant type,leading to performance de-gradation in rarer types.In this paper,decoupling incremental classifier and representation learning(DICRL)is proposed to address the dual challenges of catastrophic forgetting introduced by incremental tasks and the bias in long-tailed CLFD(LT-CLFD).The core innovation lies in the structural decoupling of incremental classifier learning and representation learning.An instance-balanced sampling strategy is employed to learn more dis-criminative deep representations from the exemplars selected by the herding algorithm and new data.Then,the previous classifiers are frozen to prevent damage to representation learning during backward propagation.Cosine normalization classifier with learnable weight scaling is trained using a class-balanced sampling strategy to enhance classification accuracy.Experimental results demonstrate that DICRL outperforms existing continual learning methods across multiple benchmarks,demonstrating superior performance and robustness in both LT-CLFD and conventional CLFD.DICRL effectively tackles both catastrophic forgetting and long-tailed distribution in CLFD,enabling more reliable fault diagnosis in industrial applications.
基金the Deep Earth Probe and Mineral Resources Exploration-National Science and Technology Major Project under Grant 2024ZD1000500。
文摘The shallow slip deficit(SSD)during strike-slip earthquakes raises a question of how the strain budget is accommodated over multiple cycles.However,the origin of variable SSD observed in different earthquakes is still under debate because each earthquake has its unique initial stress condition.Here,we derive the slip model of the 2021 M W 7.4 Maduo earthquake in Qinghai,China,using multi-track radar images.Our results revealed that,in contrast to the large SSD on segments close to the epicenter,a much smaller SSD was observed at the west terminus of the rupture,where aftershock distribution indicates that the fault changes dip direction at 6 km depth.The 2021 Maduo earthquake thus represents an extraordinary case of significant along-strike SSD variation.After accounting for interseismic,postseismic,and diffuse off-fault deformation,we find that this variation is likely contributed by the along-dipping geometrical variation,implying that a multi-segment earthquake may leave heterogeneous stress condition on the fault with different amounts of SSD.
基金support from the Scientific Funding for the Center of National Railway Intelligent Transportation System Engineering and Technology,China Academy of Railway Sciences Corporation Limited(Grant No.2023YJ354)。
文摘Knowledge graphs,which combine structured representation with semantic modeling,have shown great potential in knowledge expression,causal inference,and automated reasoning,and are widely used in fields such as intelligent question answering,decision support,and fault diagnosis.As high-speed train systems become increasingly intelligent and interconnected,fault patterns have grown more complex and dynamic.Knowledge graphs offer a promising solution to support the structured management and real-time reasoning of fault knowledge,addressing key requirements such as interpretability,accuracy,and continuous evolution in intelligent diagnostic systems.However,conventional knowledge graph construction relies heavily on domain expertise and specialized tools,resulting in high entry barriers for non-experts and limiting their practical application in frontline maintenance scenarios.To address this limitation,this paper proposes a fault knowledge modeling approach for high-speed trains that integrates structured logic diagrams with knowledge graphs.The method employs a seven-layer logic structure—comprising fault name,applicable vehicles,diagnostic logic,signal parameters,verification conditions,fault causes,and emergency measures—to transform unstructured knowledge into a visual and hierarchical representation.A semantic mapping mechanism is then used to automatically convert logic diagrams into machine-interpretable knowledge graphs,enabling dynamic reasoning and knowledge reuse.Furthermore,the proposed method establishes a three-layer architecture—logic structuring,knowledge graph transformation,and dynamic inference—to bridge human-expert logic with machinebased reasoning.Experimental validation and system implementation demonstrate that this approach not only improves knowledge interpretability and inference precision but also significantly enhances modeling efficiency and system maintainability.It provides a scalable and adaptable solution for intelligent operation and maintenance platforms in the high-speed rail domain.
基金supported by Istanbul Technical University(Project No.45698)supported through the“Young Researchers’Career Development Project-training of doctoral students”of the Croatian Science Foundation.
文摘This paper investigates the reliability of internal marine combustion engines using an integrated approach that combines Fault Tree Analysis(FTA)and Bayesian Networks(BN).FTA provides a structured,top-down method for identifying critical failure modes and their root causes,while BN introduces flexibility in probabilistic reasoning,enabling dynamic updates based on new evidence.This dual methodology overcomes the limitations of static FTA models,offering a comprehensive framework for system reliability analysis.Critical failures,including External Leakage(ELU),Failure to Start(FTS),and Overheating(OHE),were identified as key risks.By incorporating redundancy into high-risk components such as pumps and batteries,the likelihood of these failures was significantly reduced.For instance,redundant pumps reduced the probability of ELU by 31.88%,while additional batteries decreased the occurrence of FTS by 36.45%.The results underscore the practical benefits of combining FTA and BN for enhancing system reliability,particularly in maritime applications where operational safety and efficiency are critical.This research provides valuable insights for maintenance planning and highlights the importance of redundancy in critical systems,especially as the industry transitions toward more autonomous vessels.
基金funded by the Science and Technology Vice President Project in Changping District,Beijing(Project Name:Research on multi-scale optimization and intelligent control technology of integrated energy systemProject number:202302007013).
文摘The critical components of gas turbines suffer from prolonged exposure to factors such as thermal oxidation,mechanical wear,and airflow disturbances during prolonged operation.These conditions can lead to a series of issues,including mechanical faults,air path malfunctions,and combustion irregularities.Traditional modelbased approaches face inherent limitations due to their inability to handle nonlinear problems,natural factors,measurement uncertainties,fault coupling,and implementation challenges.The development of artificial intelligence algorithms has provided an effective solution to these issues,sparking extensive research into data-driven fault diagnosis methodologies.The review mechanism involved searching IEEE Xplore,ScienceDirect,and Web of Science for peerreviewed articles published between 2019 and 2025,focusing on multi-fault diagnosis techniques.A total of 220 papers were identified,with 123 meeting the inclusion criteria.This paper provides a comprehensive review of diagnostic methodologies,detailing their operational principles and distinctive features.It analyzes current research hotspots and challenges while forecasting future trends.The study systematically evaluates the strengths and limitations of various fault diagnosis techniques,revealing their practical applicability and constraints through comparative analysis.Furthermore,this paper looks forward to the future development direction of this field and provides a valuable reference for the optimization and development of gas turbine fault diagnosis technology in the future.
基金supported by the China Three Gorges Corporation(No.NBZZ202300860)the National Natural Science Foundation of China(No.52275104)the Science and Technology Innovation Program of Hunan Province(No.2023RC3097).
文摘Deep learning-based wind turbine blade fault diagnosis has been widely applied due to its advantages in end-to-end feature extraction.However,several challenges remain.First,signal noise collected during blade operation masks fault features,severely impairing the fault diagnosis performance of deep learning models.Second,current blade fault diagnosis often relies on single-sensor data,resulting in limited monitoring dimensions and ability to comprehensively capture complex fault states.To address these issues,a multi-sensor fusion-based wind turbine blade fault diagnosis method is proposed.Specifically,a CNN-Transformer Coupled Feature Learning Architecture is constructed to enhance the ability to learn complex features under noisy conditions,while a Weight-Aligned Data Fusion Module is designed to comprehensively and effectively utilize multi-sensor fault information.Experimental results of wind turbine blade fault diagnosis under different noise interferences show that higher accuracy is achieved by the proposed method compared to models with single-source data input,enabling comprehensive and effective fault diagnosis.
