Polygonal fault systems(PFS),characterized by multi-directional fault patterns within layered sequences,are well-documented features in global continental margin basins.While the geometry and formation mechanisms of P...Polygonal fault systems(PFS),characterized by multi-directional fault patterns within layered sequences,are well-documented features in global continental margin basins.While the geometry and formation mechanisms of PFS have been extensively studied in the northern South China Sea,the PFS in the Zhongjiannan Basin(western South China Sea)remain relatively unexplored,with a lack of quantitative analysis regarding their propagation.This study addresses this gap by using high-resolution three-dimensional(3D)seismic data and conducting a quantitative fault analysis to thoroughly examine the planform,cross-sectional geometry,and evolution of PFS in the northern Zhongjiannan Basin.The absence of a dominant strike direction among these polygonal faults suggests that their evolution is not controlled by anisotropic stress.Our interpretation of seismic data,constrained by the spatial relationship among PFS,gullies,and pockmarks,indicates that PFS mainly developed within the Miocene strata,with their initiation occurring during the late Miocene.Furthermore,the PFS act as key conduits connecting gullies to pockmarks in this area.The formation and development of PFS may be primarily driven by thermally triggered processes within siliceous sediments.The necessary heat source is probably associated with the abundant submarine magmatism observed in the Zhongjiannan Basin.To reconstruct the regional geological history,a four-stage evolutionary model,incorporating the formation of PFS,is presented.This research significantly improves our understanding of the regional geological evolution of the Zhongjiannan Basin,providing critical insights into the initiation and development of PFS in the western South China Sea.展开更多
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
The Lake Hazar basin,located along the Palu segment of the East Anatolian Fault System(EAFS),provides a key natural laboratory for examining transtensional deformation in a major intracontinental strike-slip zone.Inte...The Lake Hazar basin,located along the Palu segment of the East Anatolian Fault System(EAFS),provides a key natural laboratory for examining transtensional deformation in a major intracontinental strike-slip zone.Integrated field mapping,fault-slip analysis,and focal mechanism inversion reveal a polyphase tectonic history involving sequential compressional,strike-slip,and extensional regimes.Rigorous discrimination of heterogeneous fault-slip datasets into homogeneous subsets enabled reconstruction of geologically consistent stress tensors and clarified the temporal transition from strike-slip to transtensional deformation.Paleostress results indicate NNE–SSW compression and NW–SE extension,consistent with present-day seismotectonic and geomorphic patterns.Variations in stress ratio Rvalues(0.26–0.57 for strike-slip;0.28–0.33 for extensional domains)and low misfit angles(<15°)reflect localized strain partitioning and reactivation of inherited faults.The Lake Hazar basin thus evolved from a pull-apart structure into a negative flower geometry through successive deformation and fault linkage.These findings highlight that discriminating polyphase fault-slip data is essential for resolving deformation dynamics in complex fault systems.The integrated structural,paleostress,and seismotectonic framework presented here refines understanding of strain localization,fault reactivation,and stress transfer along the East Anatolian Fault System.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
As informal environmental regulation,green news coverage plays an increasingly significant role in corporate environmental governance and green innovation.However,current academic research on corporate green innovatio...As informal environmental regulation,green news coverage plays an increasingly significant role in corporate environmental governance and green innovation.However,current academic research on corporate green innovation primarily focuses on formal environmental regulation,with limited attention paid to the influence of green news coverage,particularly lacking in-depth studies on its impact mechanisms.Using a sample of Chinese A-share listed companies from 2008 to 2023,this study employs text analysis and fixed-effects models to comprehensively examine the impact of green news coverage on corporate green innovation and its transmission mechanisms.Empirical results indicate that green news coverage significantly promotes corporate green innovation,with positive coverage demonstrating particularly pronounced effects.Specifically,corporate environmental investment and environmental information disclosure levels serve as key internal mechanisms through which green news coverage influences green innovation.Environmental investment and disclosure act as partial or full mediators depending on the specific context.Heterogeneity analysis reveals that green news coverage significantly boosts green innovation in heavily polluting enterprises and those with environmental executives.Positive coverage exerts greater effects on mature firms,while negative coverage impacts growth-stage enterprises more profoundly.Against the backdrop of synergistic integration between the dual carbon goals and new productive forces,green news should fully leverage its incentive and oversight functions as informal environmental rules.This will help build a multi-stakeholder governance system to advance the transition toward a green ecological civilization.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
Unmanned aerial vehicles(UAVs)are widely utilized in area coverage tasks due to their flexibility and efficiency in geo-graphic information acquisition.However,complex boundary conditions in actual water area maps oft...Unmanned aerial vehicles(UAVs)are widely utilized in area coverage tasks due to their flexibility and efficiency in geo-graphic information acquisition.However,complex boundary conditions in actual water area maps often reduce coverage efficiency.To address this issue,this paper proposes a map preprocessing algorithm that linearizes boundary lines and processes concave areas into concave polygons,followed by gridding the map.Additionally,a collaborative area coverage method for UAV swarms is introduced based on region partitioning,which considers the comprehensive cost of energy consumption and time.An improved Hungarian algorithm is utilized for region partitioning,and a Dubins-A*-based plow-ing area full coverage path planning method is proposed to achieve path smoothing and collaborative coverage of each partition.Two sets of simulation experiments are conducted.The first experiment verifies the effectiveness of the map preprocessing algorithm,and the second compares the proposed collaborative area coverage algorithm with other methods,demonstrating its performance advantages.展开更多
The nature reserves have covered one third of the total area of the Qinghai-Xizang Plateau(QXP),which play a core role in sustaining regional ecological security.However,there is lack of quantitative evidence on compa...The nature reserves have covered one third of the total area of the Qinghai-Xizang Plateau(QXP),which play a core role in sustaining regional ecological security.However,there is lack of quantitative evidence on comparing the contribution of nature reserves on the changes of landcover and vegetation coverage for both past and future in QXP.Based on two new datasets,we compared the changes of landcover and vegetation coverage during 2000-2020 inside and outside the nature reserves in QXP.Based on Patch-generating Land Use Simulation model and Pixel-by-pixel Multiple Linear Regression,we spatialized the future landcover and vegetation coverage during 2030-2050 under SSP245 and SSP585 scenarios.The results showed the grassland increased 17.7%inside the nature reserves during 2000-2020,larger than the 12.4%rate of increase outside the nature reserves.Under the SSP245 scenario during 2030-2050,the grassland will increase 12.0%inside and 9.9%outside the nature reserves,and the bare land will decrease 16.9%inside and 19.6%outside the nature reserves.During 2000-2020,the increases of fraction vegetation coverage(FVC)were 0.0015 a^(−1) inside and 0.0013 a^(−1) outside the nature reserve.The FVC increases were not mostly positively correlated with temperature and precipitation,neither inside nor outside the nature reserves.Under the SSP585 scenario during 2030-2050,the increases of FVC were 0.0020 inside and 0.0016 outside the nature reserve.These findings highlight the positive contribution of nature reserves on the ecological security in QXP for both past and future under the fast climate change and increasing human activity.展开更多
Yogyakarta was struck by a devastating Mw6.3 earthquake,which intensified awareness about the seismic hazards in the region.This study investigates the kinematic slip rate and seismogenic depth of the northern segment...Yogyakarta was struck by a devastating Mw6.3 earthquake,which intensified awareness about the seismic hazards in the region.This study investigates the kinematic slip rate and seismogenic depth of the northern segment of Opak Fault and an unmapped fault known as Ngalang Fault in Yogyakarta,utilizing Global Navigation Satellite System(GNSS)data collected between 2019 and 2023.By deploying a network of 12 GNSS stations alongside continuous observations from the InaCORS network,we perfo rmed a detailed geodetic analysis to discern current defo rmation patterns.To quantify the slip rate,we established a frame of reference using the Sundaland Block's rotational parameters and applied the Euler pole angular velocity to transform daily GNSS solutions acco rdingly.The findings reveal significant left-lateral strike-slip motion in the northern segment of Opak Fault,with a slip rate averaging 3 mm/yr and a locking depth of 2.1 km in Northern Segment,whereas the slip rate averages 1.1 mm/yr and the locking depth is estimated at 1 km in the Ngalang Fault,indicating active geological movements that may influence future seismicity.展开更多
Battery energy storage systems bolster power grids’absorption capacity,however,battery safety issues remain a formidable challenge.Timely and pre-cise fault diagnosis,coupled with early-stage fault warn-ings,is cruci...Battery energy storage systems bolster power grids’absorption capacity,however,battery safety issues remain a formidable challenge.Timely and pre-cise fault diagnosis,coupled with early-stage fault warn-ings,is crucial.This study introduces an eigen decompo-sition-based multi-fault diagnosis approach for lithi-umion battery packs,enabling online diagnosis of short circuits,electrical connection faults,and voltage sensor malfunctions.By incorporating an interleaved measurement topology,precise fault type differentiation is achieved.Eigenvector matching analysis is employed to increase sensitivity to fault characteristics and enhance robustness.The interleaved topology can be seamlessly integrated using common voltage measurement solutions,eliminating the need for additional design complexities,while sensor number redundancy enhances fault tolerance of battery management systems(BMS).A cloud-side collaboration method is proposed,where the BMS functions as an edge device for specific data computations,while the parameters are fine-tuned by the server through big data analytics.This approach circumvents cumbersome server calculations,thereby curbing server cost escalation.The edge computing process is divided into two steps,with partial calculations often sufficient to evaluate battery safety,thus reducing the computational load on edge devices.Several battery tests are conducted,and the results confirm the method’s capability,feasibility,and validity in early-stage fault diagnosis.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
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
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
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
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
To ensure the safe and stable operation of rotating machinery,intelligent fault diagnosis methods hold significant research value.However,existing diagnostic approaches largely rely on manual feature extraction and ex...To ensure the safe and stable operation of rotating machinery,intelligent fault diagnosis methods hold significant research value.However,existing diagnostic approaches largely rely on manual feature extraction and expert experience,which limits their adaptability under variable operating conditions and strong noise environments,severely affecting the generalization capability of diagnostic models.To address this issue,this study proposes a multimodal fusion fault diagnosis framework based on Mel-spectrograms and automated machine learning(AutoML).The framework first extracts fault-sensitive Mel time–frequency features from acoustic signals and fuses them with statistical features of vibration signals to construct complementary fault representations.On this basis,automated machine learning techniques are introduced to enable end-to-end diagnostic workflow construction and optimal model configuration acquisition.Finally,diagnostic decisions are achieved by automatically integrating the predictions of multiple high-performance base models.Experimental results on a centrifugal pump vibration and acoustic dataset demonstrate that the proposed framework achieves high diagnostic accuracy under noise-free conditions and maintains strong robustness under noisy interference,validating its efficiency,scalability,and practical value for rotating machinery fault diagnosis.展开更多
This paper proposes a fault-tolerant control scheme for Euler-Lagrange systems that ensures the tracking error decays to a pre-specified accuracy level within a prescribed time period,despite unknown actuation charact...This paper proposes a fault-tolerant control scheme for Euler-Lagrange systems that ensures the tracking error decays to a pre-specified accuracy level within a prescribed time period,despite unknown actuation characteristics and potential fading powering faults.By performing deliberately designed coordinate transformations on the tracking error,the complex and demanding problem of“reaching specified precision within a given time”is transformed into a bounded control problem,facilitating the development of the control scheme.To enhance practicality,the design incorporates smooth function fitting and dynamic surface control techniques.Additionally,the proposed control algorithm is robust to faults,effectively handling a combination of fading powering faults and additive actuator faults without requiring additional human intervention.Numerical simulations on a two-link robotic manipulator verify the effectiveness of the proposed control algorithm.展开更多
Deep learning-based methods have shown great potential in intelligent bearing fault diagnosis.However,most existing approaches suffer from the scarcity of labeled data,which often results in insufficient robustness un...Deep learning-based methods have shown great potential in intelligent bearing fault diagnosis.However,most existing approaches suffer from the scarcity of labeled data,which often results in insufficient robustness under complex working conditions and a general lack of interpretability.To address these challenges,we propose a physics-informed multimodal fault diagnosis framework based on few-shot learning,which integrates a 2D timefrequency image encoder and a 1Dvibration signal encoder.Specifically,we embed prior knowledge ofmulti-resolution analysis from signal processing into the model by designing a Laplace Wavelet Convolution(LWC)module,which enhances interpretability since wavelet coefficients naturally correspond to specific frequency and temporal structures.To further balance the guidance of physical priors with the flexibility of learnable representations,we introduce a parametric multi-kernel wavelet that employs channel-wise dynamic attention to adaptively select relevant wavelet bases,thereby improving the feature expressiveness.Moreover,we develop a Mahalanobis-Prototype Joint Metric,which constructs more accurate and distribution-consistent decision boundaries under few-shot conditions.Comprehensive experiments on the Case Western Reserve University(CWRU)and Paderborn University(PU)bearing datasets demonstrate the superior effectiveness,robustness,and interpretability of the proposed approach compared with state-of-the-art baselines.展开更多
基金financially supported by the National Key Research and Development Program of China(No.2021YFC3100700)the National Natural Science Foundation of China(No.42376070)+1 种基金the Natural Science Foundation of Guangdong Province(No.2024A1515012371)the Rising Star Foundation of the South China Sea Institute of Oceanology(No.NHXX2019DZ0201)。
文摘Polygonal fault systems(PFS),characterized by multi-directional fault patterns within layered sequences,are well-documented features in global continental margin basins.While the geometry and formation mechanisms of PFS have been extensively studied in the northern South China Sea,the PFS in the Zhongjiannan Basin(western South China Sea)remain relatively unexplored,with a lack of quantitative analysis regarding their propagation.This study addresses this gap by using high-resolution three-dimensional(3D)seismic data and conducting a quantitative fault analysis to thoroughly examine the planform,cross-sectional geometry,and evolution of PFS in the northern Zhongjiannan Basin.The absence of a dominant strike direction among these polygonal faults suggests that their evolution is not controlled by anisotropic stress.Our interpretation of seismic data,constrained by the spatial relationship among PFS,gullies,and pockmarks,indicates that PFS mainly developed within the Miocene strata,with their initiation occurring during the late Miocene.Furthermore,the PFS act as key conduits connecting gullies to pockmarks in this area.The formation and development of PFS may be primarily driven by thermally triggered processes within siliceous sediments.The necessary heat source is probably associated with the abundant submarine magmatism observed in the Zhongjiannan Basin.To reconstruct the regional geological history,a four-stage evolutionary model,incorporating the formation of PFS,is presented.This research significantly improves our understanding of the regional geological evolution of the Zhongjiannan Basin,providing critical insights into the initiation and development of PFS in the western South China Sea.
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.
文摘The Lake Hazar basin,located along the Palu segment of the East Anatolian Fault System(EAFS),provides a key natural laboratory for examining transtensional deformation in a major intracontinental strike-slip zone.Integrated field mapping,fault-slip analysis,and focal mechanism inversion reveal a polyphase tectonic history involving sequential compressional,strike-slip,and extensional regimes.Rigorous discrimination of heterogeneous fault-slip datasets into homogeneous subsets enabled reconstruction of geologically consistent stress tensors and clarified the temporal transition from strike-slip to transtensional deformation.Paleostress results indicate NNE–SSW compression and NW–SE extension,consistent with present-day seismotectonic and geomorphic patterns.Variations in stress ratio Rvalues(0.26–0.57 for strike-slip;0.28–0.33 for extensional domains)and low misfit angles(<15°)reflect localized strain partitioning and reactivation of inherited faults.The Lake Hazar basin thus evolved from a pull-apart structure into a negative flower geometry through successive deformation and fault linkage.These findings highlight that discriminating polyphase fault-slip data is essential for resolving deformation dynamics in complex fault systems.The integrated structural,paleostress,and seismotectonic framework presented here refines understanding of strain localization,fault reactivation,and stress transfer along the East Anatolian Fault System.
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National Social Science Fund project(Grant No.24FKSB033).
文摘As informal environmental regulation,green news coverage plays an increasingly significant role in corporate environmental governance and green innovation.However,current academic research on corporate green innovation primarily focuses on formal environmental regulation,with limited attention paid to the influence of green news coverage,particularly lacking in-depth studies on its impact mechanisms.Using a sample of Chinese A-share listed companies from 2008 to 2023,this study employs text analysis and fixed-effects models to comprehensively examine the impact of green news coverage on corporate green innovation and its transmission mechanisms.Empirical results indicate that green news coverage significantly promotes corporate green innovation,with positive coverage demonstrating particularly pronounced effects.Specifically,corporate environmental investment and environmental information disclosure levels serve as key internal mechanisms through which green news coverage influences green innovation.Environmental investment and disclosure act as partial or full mediators depending on the specific context.Heterogeneity analysis reveals that green news coverage significantly boosts green innovation in heavily polluting enterprises and those with environmental executives.Positive coverage exerts greater effects on mature firms,while negative coverage impacts growth-stage enterprises more profoundly.Against the backdrop of synergistic integration between the dual carbon goals and new productive forces,green news should fully leverage its incentive and oversight functions as informal environmental rules.This will help build a multi-stakeholder governance system to advance the transition toward a green ecological civilization.
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.
基金National Natural Science Foundation of China(62402020,62303022)Beijing Nova Program(20240484720)+1 种基金Project of Cultivation for Young Top-Notch Talents of Beijing Municipal Institutions(BPHR202203043)BTBU Digital Business Platform Project byBMEC.
文摘Unmanned aerial vehicles(UAVs)are widely utilized in area coverage tasks due to their flexibility and efficiency in geo-graphic information acquisition.However,complex boundary conditions in actual water area maps often reduce coverage efficiency.To address this issue,this paper proposes a map preprocessing algorithm that linearizes boundary lines and processes concave areas into concave polygons,followed by gridding the map.Additionally,a collaborative area coverage method for UAV swarms is introduced based on region partitioning,which considers the comprehensive cost of energy consumption and time.An improved Hungarian algorithm is utilized for region partitioning,and a Dubins-A*-based plow-ing area full coverage path planning method is proposed to achieve path smoothing and collaborative coverage of each partition.Two sets of simulation experiments are conducted.The first experiment verifies the effectiveness of the map preprocessing algorithm,and the second compares the proposed collaborative area coverage algorithm with other methods,demonstrating its performance advantages.
基金supported by the Second Qinghai-Tibet Plateau Scientific Expedition and Research Program(2019QZKK0405)the Natural Science Research Projects of Dezhou University(2021xjrc106).
文摘The nature reserves have covered one third of the total area of the Qinghai-Xizang Plateau(QXP),which play a core role in sustaining regional ecological security.However,there is lack of quantitative evidence on comparing the contribution of nature reserves on the changes of landcover and vegetation coverage for both past and future in QXP.Based on two new datasets,we compared the changes of landcover and vegetation coverage during 2000-2020 inside and outside the nature reserves in QXP.Based on Patch-generating Land Use Simulation model and Pixel-by-pixel Multiple Linear Regression,we spatialized the future landcover and vegetation coverage during 2030-2050 under SSP245 and SSP585 scenarios.The results showed the grassland increased 17.7%inside the nature reserves during 2000-2020,larger than the 12.4%rate of increase outside the nature reserves.Under the SSP245 scenario during 2030-2050,the grassland will increase 12.0%inside and 9.9%outside the nature reserves,and the bare land will decrease 16.9%inside and 19.6%outside the nature reserves.During 2000-2020,the increases of fraction vegetation coverage(FVC)were 0.0015 a^(−1) inside and 0.0013 a^(−1) outside the nature reserve.The FVC increases were not mostly positively correlated with temperature and precipitation,neither inside nor outside the nature reserves.Under the SSP585 scenario during 2030-2050,the increases of FVC were 0.0020 inside and 0.0016 outside the nature reserve.These findings highlight the positive contribution of nature reserves on the ecological security in QXP for both past and future under the fast climate change and increasing human activity.
基金funded by the Department of Geodetic Engineering,Faculty of Engineering,Universitas Gadjah Mada。
文摘Yogyakarta was struck by a devastating Mw6.3 earthquake,which intensified awareness about the seismic hazards in the region.This study investigates the kinematic slip rate and seismogenic depth of the northern segment of Opak Fault and an unmapped fault known as Ngalang Fault in Yogyakarta,utilizing Global Navigation Satellite System(GNSS)data collected between 2019 and 2023.By deploying a network of 12 GNSS stations alongside continuous observations from the InaCORS network,we perfo rmed a detailed geodetic analysis to discern current defo rmation patterns.To quantify the slip rate,we established a frame of reference using the Sundaland Block's rotational parameters and applied the Euler pole angular velocity to transform daily GNSS solutions acco rdingly.The findings reveal significant left-lateral strike-slip motion in the northern segment of Opak Fault,with a slip rate averaging 3 mm/yr and a locking depth of 2.1 km in Northern Segment,whereas the slip rate averages 1.1 mm/yr and the locking depth is estimated at 1 km in the Ngalang Fault,indicating active geological movements that may influence future seismicity.
基金supported in part by the National Natural Science Foundation of China(No.62133007)Shandong Provincial Key Research and Development Program(No.2024CXPT052).
文摘Battery energy storage systems bolster power grids’absorption capacity,however,battery safety issues remain a formidable challenge.Timely and pre-cise fault diagnosis,coupled with early-stage fault warn-ings,is crucial.This study introduces an eigen decompo-sition-based multi-fault diagnosis approach for lithi-umion battery packs,enabling online diagnosis of short circuits,electrical connection faults,and voltage sensor malfunctions.By incorporating an interleaved measurement topology,precise fault type differentiation is achieved.Eigenvector matching analysis is employed to increase sensitivity to fault characteristics and enhance robustness.The interleaved topology can be seamlessly integrated using common voltage measurement solutions,eliminating the need for additional design complexities,while sensor number redundancy enhances fault tolerance of battery management systems(BMS).A cloud-side collaboration method is proposed,where the BMS functions as an edge device for specific data computations,while the parameters are fine-tuned by the server through big data analytics.This approach circumvents cumbersome server calculations,thereby curbing server cost escalation.The edge computing process is divided into two steps,with partial calculations often sufficient to evaluate battery safety,thus reducing the computational load on edge devices.Several battery tests are conducted,and the results confirm the method’s capability,feasibility,and validity in early-stage fault diagnosis.
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.
基金supported in part by the National Natural Science Foundation of China under Grants 52475102 and 52205101in part by the Guangdong Basic and Applied Basic Research Foundation under Grant 2023A1515240021+1 种基金in part by the Young Talent Support Project of Guangzhou Association for Science and Technology(QT-2024-28)in part by the Youth Development Initiative of Guangdong Association for Science and Technology(SKXRC2025254).
文摘To ensure the safe and stable operation of rotating machinery,intelligent fault diagnosis methods hold significant research value.However,existing diagnostic approaches largely rely on manual feature extraction and expert experience,which limits their adaptability under variable operating conditions and strong noise environments,severely affecting the generalization capability of diagnostic models.To address this issue,this study proposes a multimodal fusion fault diagnosis framework based on Mel-spectrograms and automated machine learning(AutoML).The framework first extracts fault-sensitive Mel time–frequency features from acoustic signals and fuses them with statistical features of vibration signals to construct complementary fault representations.On this basis,automated machine learning techniques are introduced to enable end-to-end diagnostic workflow construction and optimal model configuration acquisition.Finally,diagnostic decisions are achieved by automatically integrating the predictions of multiple high-performance base models.Experimental results on a centrifugal pump vibration and acoustic dataset demonstrate that the proposed framework achieves high diagnostic accuracy under noise-free conditions and maintains strong robustness under noisy interference,validating its efficiency,scalability,and practical value for rotating machinery fault diagnosis.
基金supported in part by the National Natural Science Foundation of China(W2411061,624B2029)the Graduate Research and Innovation Foundation of Chongqing,China(CYS20069)+1 种基金the Fundamental Research Funds for the Central Universities(2024CDJYXTD-007)the Natural Science Foundation of Chongqing(CSTB2023NSCQ-LZX0026).
文摘This paper proposes a fault-tolerant control scheme for Euler-Lagrange systems that ensures the tracking error decays to a pre-specified accuracy level within a prescribed time period,despite unknown actuation characteristics and potential fading powering faults.By performing deliberately designed coordinate transformations on the tracking error,the complex and demanding problem of“reaching specified precision within a given time”is transformed into a bounded control problem,facilitating the development of the control scheme.To enhance practicality,the design incorporates smooth function fitting and dynamic surface control techniques.Additionally,the proposed control algorithm is robust to faults,effectively handling a combination of fading powering faults and additive actuator faults without requiring additional human intervention.Numerical simulations on a two-link robotic manipulator verify the effectiveness of the proposed control algorithm.
文摘Deep learning-based methods have shown great potential in intelligent bearing fault diagnosis.However,most existing approaches suffer from the scarcity of labeled data,which often results in insufficient robustness under complex working conditions and a general lack of interpretability.To address these challenges,we propose a physics-informed multimodal fault diagnosis framework based on few-shot learning,which integrates a 2D timefrequency image encoder and a 1Dvibration signal encoder.Specifically,we embed prior knowledge ofmulti-resolution analysis from signal processing into the model by designing a Laplace Wavelet Convolution(LWC)module,which enhances interpretability since wavelet coefficients naturally correspond to specific frequency and temporal structures.To further balance the guidance of physical priors with the flexibility of learnable representations,we introduce a parametric multi-kernel wavelet that employs channel-wise dynamic attention to adaptively select relevant wavelet bases,thereby improving the feature expressiveness.Moreover,we develop a Mahalanobis-Prototype Joint Metric,which constructs more accurate and distribution-consistent decision boundaries under few-shot conditions.Comprehensive experiments on the Case Western Reserve University(CWRU)and Paderborn University(PU)bearing datasets demonstrate the superior effectiveness,robustness,and interpretability of the proposed approach compared with state-of-the-art baselines.
