期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到899篇文章
< 1 2 … 45 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Neuromorphic Computing of Multimodal Temporal Data for Machine Fault Diagnosis:Methodology and Hardware Deployment 认领 引用
1
作者 Weipeng Fan Xiang Li +3 位作者 Yaguo Lei Shupeng Yu Naipeng Li Bin Yang 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第6期1515-1517,共3页
Dear Editor,Long-term monitoring of different mechanical signals is vital for the health management of modern industrial equipment.Traditional deep learning-based fault diagnosis methods rely much on high-performance ... Dear Editor,Long-term monitoring of different mechanical signals is vital for the health management of modern industrial equipment.Traditional deep learning-based fault diagnosis methods rely much on high-performance computing systems and are difficult to be always-on deployed at the edge.Meanwhile,most of the existing fault diagnosis methods rely on single-sourced sensing data,which only capture limited fault information and cannot well reflect the machine health condition.To address the aforementioned problems,the bio-inspired spiking neural networks(SNNs)offer a promising solution,which simulates the structure and operation of biological neural systems and is more energy and computation-efficient. 展开更多
关键词 computation efficiency fault diagnosis energy efficiency mechanical signals bio inspired spiking neural networks health management multimodal temporal data machine fault diagnosis
暂未订购 下载PDF
XJTU-DV:Open-source dynamic vision dataset for non-contact vibration measurement and fault diagnosis of mechanical systems 认领 引用
2
作者 Xiang Li Shupeng Yu +3 位作者 Xinrui Chen Yaguo Lei Bin Yang Naipeng Li 《Chinese Journal of Mechanical Engineering》 SCIE EI CAS CSCD 2026年第2期1-13,共13页
Vibration measurement is of great importance for fault diagnosis and prognosis of mechanical systems in the literature.Non-contact vibration measurement methods have been attracting growing attention in recent years.D... Vibration measurement is of great importance for fault diagnosis and prognosis of mechanical systems in the literature.Non-contact vibration measurement methods have been attracting growing attention in recent years.Dynamic vision is an emerging vision technology,which is developed with neuromorphic sensing principles.This paper introduces XJTU-DV,an open-source dynamic vision dataset for non-contact vibration measurement and fault diagnosis of mechanical systems.The XJTU-DV-Beam sub-dataset includes the dynamic vision data on a structural beam system,as well as the corresponding laser vibrometer data as ground truth.The XJTU-DVRotor and XJTU-DV-Pump sub-datasets include the dynamic vision data from a rotor and a pump test bench,respectively.The dynamic vision data are collected under different fault and operating conditions.XJTU-DV provides a data foundation for dynamic vision-based studies on vibration measurement and fault diagnosis,which may promote further development of the emerging vision algorithms for industrial applications.The dataset can be accessed at http://gffzz34a8b68aae444ae4sw5vupbffpqvp6xnk.ffgz.tsg.suse.edu.cn/web/lixiang/xjtu-dv for detailed information. 展开更多
关键词 Dynamic vision Event camera Non-contact measurement Vibration measurement Fault diagnosis
暂未订购 下载PDF
Decoupling incremental classifier and representation learning based continual learning machinery fault diagnosis framework under long-tailed distribution 认领 引用
3
作者 Changqing Shen Yao Liu +3 位作者 Bojian Chen Xuyang Tao Yifan Huangfu Dong Wang 《Chinese Journal of Mechanical Engineering》 SCIE EI CAS CSCD 2026年第1期74-87,共14页
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
关键词 Fault diagnosis Continual learning Long-tailed distribution Catastrophic forgetting
暂未订购 下载PDF
Fault Diagnosis of Wind Turbine Blades Based on Multi-Sensor Weighted Alignment Fusion in Noisy Environments 认领 引用
4
作者 Lifu He Zhongchu Huang +4 位作者 Haidong Shao Zhangbo Hu Yuting Wang Jie Mei Xiaofei Zhang 《Computers, Materials & Continua》 SCIE EI 2026年第3期1401-1422,共22页
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
关键词 Wind turbine blade multi-sensor fusion fault diagnosis CNN-transformer coupled architecture
暂未订购 下载PDF
Towards generalizable fault diagnosis:Learning invariant features across varying fault severities 认领 引用
5
作者 Yiming Zhang Hongbo Shi +1 位作者 Bing Song Yang Tao 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2026年第4期23-36,共14页
Ensuring the generalizability of fault diagnosis models is critical for maintaining the long-term safety of industrial systems operating under diverse conditions.This study presents a novel method,termed the Generaliz... Ensuring the generalizability of fault diagnosis models is critical for maintaining the long-term safety of industrial systems operating under diverse conditions.This study presents a novel method,termed the Generalizable Class-Consistent Network(GCCNet),designed to enhance diagnostic robustness under previously unseen operating conditions.Speciffiifically,GCCNet incorporates a mutual information based feature disentanglement mechanism to extract task-relevant representations.To further promote feature invariance,auxiliary samples are constructed using same-class fault data under different excitation intensities,and a class-consistency regularization is applied during training to enforce consistent predictions.This guides the network to purify task-relevant features into transferable and robust representations.Extensive experiments conducted on the Tennessee Eastman process and industrial dataset validate the effectiveness and generalization ability of the proposed method. 展开更多
关键词 Fault diagnosis Domain generalization Class-consistent learning
暂未订购 下载PDF
A Review on Fault Diagnosis Methods of Gas Turbine 认领 引用
6
作者 Tao Zhang Hailun Wang +1 位作者 Tianyue Wang Tian Tian 《Computers, Materials & Continua》 SCIE EI 2026年第3期88-116,共29页
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
关键词 Fault diagnosis machine learning gas turbine artificial intelligence deep learning
暂未订购 下载PDF
A precise identification-based mode decomposition and its application in mechanical fault diagnosis 认领 引用
7
作者 Bi Li Zhinong Li +1 位作者 Fengtao Wang Deqiang He 《Chinese Journal of Mechanical Engineering》 SCIE EI CAS CSCD 2026年第1期88-101,共14页
Current improved Empirical Mode Decomposition(EMD)methods enhance the accurate identification of peak and valley points in mechanical signals through noise-assisted filtering techniques,thereby improving the mode deco... Current improved Empirical Mode Decomposition(EMD)methods enhance the accurate identification of peak and valley points in mechanical signals through noise-assisted filtering techniques,thereby improving the mode decomposition performance,which is of great significance in extracting fault features from mechanical signals.However,noise-assisted filtering leads to the loss of critical features in mechanical signals and introduces a large amount of residual noise into Intrinsic Mode Functions(IMFs)that obscure signal features.To address these issues,a Precise Identification-based Mode Decomposition(PIMD)method is proposed.This method directly enhances the ability of EMD to precisely identify peak and valley points by using a proposed precise identifi-cation approach,which improves mode decomposition performance and avoids the negative impacts of noise-assisted filtering,thus benefiting the extraction of more mechanical fault features.Simulation results show that the proposed PIMD method can precisely identify peak and valley points of signals with noise of different signal-tonoise ratios and perform a highly rigorous high-low frequency decomposition,significantly outperforming EMD.Finally,mechanical fault diagnostic experiments on four bearing cases and two gear cases demonstrate that,compared to four mainstream methods,the PIMD method exhibits the best mode decomposition perfor-mance and can extract more and clearer mechanical fault features. 展开更多
关键词 Mechanical fault diagnosis Precise identification-based mode decomposition Peak and valley point identification Mode decomposition performance
暂未订购 下载PDF
Intelligent Fault Diagnosis of Rolling Bearing With Variable Speed Based on ASTFrFT and Time-Frequency BoTNet Model 认领 引用
8
作者 Jie Ma Jun Wei Xinyu Wang 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第7期1761-1763,共3页
Dear Editor,This letter presents an intelligent fault diagnosis method for variable speed rolling bearings based on the adaptive short-time fractional Fourier transform(ASTFrFT)and the time-frequency BoTNet(TFB)to add... Dear Editor,This letter presents an intelligent fault diagnosis method for variable speed rolling bearings based on the adaptive short-time fractional Fourier transform(ASTFrFT)and the time-frequency BoTNet(TFB)to address the challenge of extracting fault characteristics of rolling bearings under variable speed conditions and the poor classification of classical deep learning models.Firstly,to address the limitations of FrFT in time-varying signal processing,the physical mechanism of traditional STFT is extended into the FrFT domain by minimizing fuzzy entropy values to construct the order matrix. 展开更多
关键词 variable speed rolling bearings time frequency botnet rolling bearings deep learning modelsfirstlyto variable speed adaptive short time fractional fourier transform extracting fault characteristics intelligent fault diagnosis
暂未订购 下载PDF
Three-Stage Learning Framework for Compound Fault Diagnosis in Delta 3D Printers via Multi-Output Fusion Ensembles 认领 引用
9
作者 Lin Fang Razi Abdul-Rahman Cheng-Fu Yang 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第6期301-332,共32页
Parallel mechanisms are extensively employed in industrial logistics,food processing,and medical applications.Due to the strong nonlinearity and cross-axis coupling inherent in closed-chain kinematics,fault diagnostic... Parallel mechanisms are extensively employed in industrial logistics,food processing,and medical applications.Due to the strong nonlinearity and cross-axis coupling inherent in closed-chain kinematics,fault diagnostic performance is highly sensitive to signal perturbations and class imbalance under noisy measurement conditions.Furthermore,diagnostic models trained under single-fault scenarios often exhibit notable performance degradation when transferred to compound fault conditions as a result of distribution shift.In this study,a Delta 3D printer,as a representative parallel mechanism,is adopted as the experimental platform.An interpretable three-stage diagnostic framework is proposed,in which compound fault diagnosis is reformulated as a multi-output classification problem that simultaneously predicts the health states of the A-,B-,and C-belts.This formulation avoids explicit enumeration of compound fault classes while preserving maintenance-relevant,belt-level diagnostic information.Under a strict leakage-avoidance protocol,a fusion ensemble integrating LightGBM and XGBoost classifiers is employed to enhance robustness and generalization to previously unseen compound fault combinations.On the compound-fault subset of the Delta 3D printer dataset,the proposed method achieves a multi-output Macro-F1 score of 09290,with a 95%bootstrap confidence interval of 0.91980.9379.The corresponding belt-wise Macro-F1 scores reach 0.9508,0.9173,and 0.9189 for the A-,B-,and C-belts,respectively.Moreover,the average inference latency on the compound-fault subset is 0.9305 ms per sample,demonstrating a favorable balance between diagnostic accuracy and computational efficiency for edge-deployment scenarios. 展开更多
关键词 Delta 3D printer fault diagnosis compound faults multi output classification fusion ensemble
暂未订购 下载PDF
Gearbox Fault Diagnosis under Varying Operating Conditions through Semi-Supervised Masked Contrastive Learning and Domain Adaptation 认领 引用
10
作者 Zhixiang Huang Jun Li 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第2期448-470,共23页
To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervis... To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervised masked contrastive learning and domain adaptation(SSMCL-DA)method for gearbox fault diagnosis under variable conditions.Initially,during the unsupervised pre-training phase,a dual signal augmentation strategy is devised,which simultaneously applies random masking in the time domain and random scaling in the frequency domain to unlabeled samples,thereby constructing more challenging positive sample pairs to guide the encoder in learning intrinsic features robust to condition variations.Subsequently,a ConvNeXt-Transformer hybrid architecture is employed,integrating the superior local detail modeling capacity of ConvNeXt with the robust global perception capability of Transformer to enhance feature extraction in complex scenarios.Thereafter,a contrastive learning model is constructed with the optimization objective of maximizing feature similarity across different masked instances of the same sample,enabling the extraction of consistent features from multiple masked perspectives and reducing reliance on labeled data.In the final supervised fine-tuning phase,a multi-scale attention mechanism is incorporated for feature rectification,and a domain adaptation module combining Local Maximum Mean Discrepancy(LMMD)with adversarial learning is proposed.This module embodies a dual mechanism:LMMD facilitates fine-grained class-conditional alignment,compelling features of identical fault classes to converge across varying conditions,while the domain discriminator utilizes adversarial training to guide the feature extractor toward learning domain-invariant features.Working in concert,they markedly diminish feature distribution discrepancies induced by changes in load,rotational speed,and other factors,thereby boosting the model’s adaptability to cross-condition scenarios.Experimental evaluations on the WT planetary gearbox dataset and the Case Western Reserve University(CWRU)bearing dataset demonstrate that the SSMCL-DA model effectively identifies multiple fault classes in gearboxes,with diagnostic performance substantially surpassing that of conventional methods.Under cross-condition scenarios,the model attains fault diagnosis accuracies of 99.21%for the WT planetary gearbox and 99.86%for the bearings,respectively.Furthermore,the model exhibits stable generalization capability in cross-device settings. 展开更多
关键词 Gearbox variable working conditions fault diagnosis semi-supervised masked contrastive learning domain adaptation
暂未订购 下载PDF
A Single-Device Environment-Adaptive Mixed Reality Framework for Real-Time Industrial Fault Diagnosis 认领 引用
11
作者 Xueyi Li Bo Kang +3 位作者 Jing Tang Qi Li Tianyang Wang Minwei Zhang 《Journal of Dynamics, Monitoring and Diagnostics》 2026年第1期64-73,共10页
In industrial environments,monitoring and fault diagnosis of mechanical equipment face challenges such as spatial localization drift and delays in real-time data rendering,especially in complex settings with low illum... In industrial environments,monitoring and fault diagnosis of mechanical equipment face challenges such as spatial localization drift and delays in real-time data rendering,especially in complex settings with low illumination,weak textures,and strong interference.Traditional methods struggle to effectively integrate monitoring data with physical entities,increasing cognitive load and reducing diagnostic accuracy.To address these issues,we propose the Single-Device Mixed Reality(SEMR)framework,a novel solution that enhances industrial equipment monitoring and fault diagnosis.The framework integrates three key mechanisms:an environment-aware model that adjusts the confidence of Simultaneous Localization and Mapping(SLAM)to ensure precise spatial registration,a Kalman filter-based motion prediction to reduce rendering delays,and a faulttolerant gaze interaction system for hands-free operation.Experimental results demonstrate that SEMR reduces the spatial registration error by 52.1%,from 14.2 cm to 6.8 cm,and decreases latency during dynamic inspections by 26.7%,improving diagnostic accuracy and real-time performance.The proposed method provides a costeffective and reliable solution for enhancing industrial fault diagnosis and equipment monitoring,particularly in challenging environments. 展开更多
关键词 adaptive SLAM fault diagnosis industrial inspection predictive interaction real-time equipment status monitoring single-device mixed reality
暂未订购 下载PDF
A Dual-Component Elastic Adaptation Network for Rotating Machinery Incremental Fault Diagnosis under Variable Operating Conditions 认领 引用
12
作者 Yan Zhang Changqing Shen +3 位作者 Xiaofen Ye Liang Chen Juanjuan Shi Zhongkui Zhu 《Journal of Dynamics, Monitoring and Diagnostics》 2026年第1期49-63,共15页
In practical industrial environments,the data distribution of rotating machinery drifts as operating conditions vary,causing a marked deterioration in the performance of traditional fault diagnosis methods that rely o... In practical industrial environments,the data distribution of rotating machinery drifts as operating conditions vary,causing a marked deterioration in the performance of traditional fault diagnosis methods that rely on the assumption of identical distributions.Incremental learning provides a promising pathway to address dynamic operating conditions.However,existing approaches typically depend on replaying historical data and still struggle to strike a balance between stability and plasticity.To overcome these limitations,this paper proposes a dual-component elastic adaptive network(DCEAN)designed for incremental fault diagnosis of rotating machinery under varying working conditions.The proposed framework operates without access to previous data and simultaneously achieves knowledge retention and feature correction.Specifically,a sensitive parameter constraint(SPC)mechanism is introduced to curb excessive updates to parameters identified as critical,thereby stabilizing previously learned knowledge.In parallel,a feature drift self-calibration(FDSC)mechanism is employed to estimate and compensate for distribution shifts induced by condition variations,promoting consistency of feature representations across domains.Through the coordinated action of these two mechanisms,DCEAN establishes an incremental learning paradigm that harmonizes stability with adaptability.Two case studies demonstrate that the proposed method delivers superior diagnostic performance in variable operating environments,underscoring its robustness and effectiveness. 展开更多
关键词 feature drift incremental learning intelligent fault diagnosis rotating machinery variable operating conditions
暂未订购 下载PDF
Fault diagnosis of rolling bearing based on two-dimensional composite multi-scale ensemble Gramian dispersion entropy 认领 引用
13
作者 Wenqing Ding Jinde Zheng +3 位作者 Jianghong Li Haiyang Pan Jian Cheng Jinyu Tong 《Chinese Journal of Mechanical Engineering》 SCIE EI CAS CSCD 2026年第1期125-144,共20页
One-dimensional ensemble dispersion entropy(EDE1D)is an effective nonlinear dynamic analysis method for complexity measurement of time series.However,it is only restricted to assessing the complexity of one-di-mension... One-dimensional ensemble dispersion entropy(EDE1D)is an effective nonlinear dynamic analysis method for complexity measurement of time series.However,it is only restricted to assessing the complexity of one-di-mensional time series(TS1d)with the extracted complexity features only at a single scale.Aiming at these problems,a new nonlinear dynamic analysis method termed two-dimensional composite multi-scale ensemble Gramian dispersion entropy(CMEGDE2D)is proposed in this paper.First,the TS1D is transformed into a two-dimensional image(I2D)by using Gramian angular fields(GAF)with more internal data structures and geometri features,which preserve the global characteristics and time dependence of vibration signals.Second,the I2D is analyzed at multiple scales through the composite coarse-graining method,which overcomes the limitation of a single scale and provides greater stability compared to traditional coarse-graining methods.Subsequently,a new fault diagnosis method of rolling bearing is proposed based on the proposed CMEGDE2D for fault feature ex-traction and the chicken swarm algorithm optimized support vector machine(CsO-SvM)for fault pattern identification.The simulation signals and two data sets of rolling bearings are utilized to verify the effectiveness of the proposed fault diagnosis method.The results demonstrate that the proposed method has stronger dis-crimination ability,higher fault diagnosis accuracy and better stability than the other compared methods. 展开更多
关键词 Composite multi-scale ensemble Gramian dispersion entropy Dispersion entropy Fault diagnosis Rolling bearing Feature extraction
暂未订购 下载PDF
A flexible multimodal motor fault diagnosis framework with inter-modal learning discrepancy mitigation under modal missing scenarios 认领 引用
14
作者 Yuhan XIE Yuewei XI +3 位作者 Biao WANG Xiaoqing CHENG Liang GUO Yong QIN 《Science China(Technological Sciences)》 SCIE EI CAS CSCD 2026年第7期193-207,共15页
Multimodal learning has recently gained considerable attention in fault diagnosis for its ability to integrate multisource heterogeneous data and extract comprehensive fault features.However,existing multimodal fault ... Multimodal learning has recently gained considerable attention in fault diagnosis for its ability to integrate multisource heterogeneous data and extract comprehensive fault features.However,existing multimodal fault diagnosis studies have the following limitations:(1)existing multimodal methods lack flexibility in handling arbitrary modality combinations under missing-modality conditions,thereby limiting their applicability in practical industrial environments;(2)disparities in data distributions and feature scales across modalities often lead to imbalanced convergence during training,hindering the realization of its theoretical potential.To address these issues,a flexible multimodal framework with inter-modal learning discrepancy mitigation is proposed for motor fault diagnosis under modal missing scenarios.Firstly,a flexible sparse mixture of experts framework is designed to adaptively integrate arbitrary modality combinations while maintaining robustness against missing data.Then,a discrepancy-aware alignment scheme grounded in contrastive learning is introduced to harmonize faultcategory representations across modalities,bridging heterogeneous features and mitigating inter-modal learning gaps.Finally,regularization-guided synergistic loss optimization is developed to dynamically integrate unsupervised contrastive learning with multimodal representation learning,which enables more effective cross-modal feature fusion.The effectiveness of the proposed method is validated through simulated motor fault experiments,and its superiority is demonstrated by comparisons with advanced approaches for multimodal missing and imbalance scenarios. 展开更多
关键词 motor degradation intelligent fault diagnosis multimodal learning modality missing cross-modal discrepancy mitigation
暂未订购 下载PDF
Weak bearing fault diagnosis based on a time-delayed quad-stable stochastic resonance model 认领 引用
15
作者 Zhuo Wang Yanfei Jin +2 位作者 Yonghui An Haotian Wang Qiang Tian 《Acta Mechanica Sinica》 SCIE EI CAS CSCD 2026年第5期477-487,共11页
This paper proposes a time-delayed quad-stable stochastic resonance(SR)model driven by Gaussian white correlated noises and a weak periodic signal.For the small time delay,the mean first-passage times and spectral amp... This paper proposes a time-delayed quad-stable stochastic resonance(SR)model driven by Gaussian white correlated noises and a weak periodic signal.For the small time delay,the mean first-passage times and spectral amplification(SA)are derived.The curve of SA exhibits a typical resonant peak at an optimal noise intensity and SR happens.Moreover,as the time delay increases,the peak value of SA is enhanced for a fixed feedback gain.It is found that selecting appropriate crosscorrelation between noises and feedback gain for fixed time delay can induce the appearance of SR.In particular,an ideal quadstable potential structure is determined to optimize the SR effect.Subsequently,an adaptive improved quad-stable SR model based on quantum particle swarm optimization is proposed to determine the optimal structure parameters to maximize improved signal-to-noise ratio.Meanwhile,the proposed model is applied to diagnose weak bearing faults in inner race,outer race,and rolling elements.The results indicate that the time-delayed quad-stable SR model significantly enhances the fault diagnosis performance and resolves the issues related to side frequency interference compared to the underdamped bi-stable SR model and the underdamped quad-stable SR model.In the fault diagnosis of bearing rolling elements,the proposed SR model can accurately identify fault frequency values.While the underdamped bi-stable and quad-stable SR models are invalid for this case. 展开更多
关键词 Stochastic resonance A time-delayed quad-stable system Spectral amplification Weak bearing fault diagnosis
暂未订购 下载PDF
Research on Gearbox Fault Diagnosis Method Based on Multi-Dimensional Feature Extraction and Random Forest 认领 引用
16
作者 Yu Zhang Shihan Tan +3 位作者 Guangyao Lian Congying Dun Qiwei Hu Chiming Guo 《Computers, Materials & Continua》 SCIE EI 2026年第8期1700-1720,共21页
Gearboxes are critical components in the transmission systems of various mechanical equipment.Subjected to complex and harsh operating conditions for a long time,they suffer from a high failure rate and potentially se... Gearboxes are critical components in the transmission systems of various mechanical equipment.Subjected to complex and harsh operating conditions for a long time,they suffer from a high failure rate and potentially severe consequences.Traditional fault diagnosis methods are limited by problems such as noise interference,and can hardly meet the requirements in terms of diagnostic accuracy,generalization ability,and reliability.To tackle the deficiencies of traditional gearbox fault diagnosis methods,including insufficient utilization of features,poor generalization under small-sample conditions,and weak model interpretability,this paper proposes a fault diagnosis method based on multi-dimensional feature extraction and Random Forest(RF).This method integrates intelligent computing,data-driven approaches,and mechanical structural health monitoring.First,fault feature analysis is conducted from multiple dimensions including time domain,frequency domain,and envelope domain,and visualization verification is implemented using Principal Component Analysis(PCA)and t-Distributed Stochastic Neighbor Embedding(t-SNE).Then,the Random Forest(RF)algorithm is used for dataset training and testing,obtaining a stable diagnostic model with strong generalization ability.Finally,experimental analyses verify the effectiveness and superiority of the proposed method.The research results possess high application potential and practical value in improving the performance of gearbox fault diagnosis. 展开更多
关键词 Fault diagnosis feature extraction principal component analysis gearbox random forest
暂未订购 下载PDF
Automated Machine Learning for Fault Diagnosis Using Multimodal Mel-Spectrogram and Vibration Data 认领 引用
17
作者 Zehao Li Xuting Zhang +4 位作者 Hongqi Lin Wu Qin Junyu Qi Zhuyun Chen Qiang Liu 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第2期471-498,共28页
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
关键词 Automated machine learning mechanical fault diagnosis feature engineering multimodal data
暂未订购 下载PDF
An Improved Support Vector Machine Method for Fault Diagnosis of Inter-Turn Short Circuit in PMSM with Enhanced Fault Representation 认领 引用
18
作者 Yue Su Shukuan Zhang +2 位作者 Jinghao Jiao Jiankang Zhong Qianxi Zhao 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第4期613-629,共17页
This paper introduces a novel dual-layer optimization fault diagnosis framework for inter-turn shortcircuit(ITSC)faults in permanent magnet synchronous motors(PMSMs).The synergistic of a SABO-optimized VMD for enhance... This paper introduces a novel dual-layer optimization fault diagnosis framework for inter-turn shortcircuit(ITSC)faults in permanent magnet synchronous motors(PMSMs).The synergistic of a SABO-optimized VMD for enhanced feature extraction and an MFO-optimized SVM for intelligent classification is proposed.Firstly,mathematical and simulation models of ITSC faults in PMSMs are established to obtain fault phase currents and motor electromagnetic torques as characteristic fault signals.Then,the SABO algorithm is used to optimize the VMD parameters,followed by VMD decomposition of the characteristic fault signals to obtain Intrinsic Mode Functions(IMFs),and the time-domain parameters of the optimal IMF are calculated to obtain feature vectors.Finally,the fault type is predicted using an SVM optimized by the Moth-Flame Optimizer(MFO).Simulation results show that the accuracy of fault diagnosis can reach 93.6%,indicating that the proposed method can achieve accurate diagnosis of ITSC faults and effectively improve the accuracy of fault diagnosis. 展开更多
关键词 Permanent magnet synchronous motor inter-turn short circuit fault support vector machine fault diagnosis
暂未订购 下载PDF
Robust and Efficient Federated Learning for Machinery Fault Diagnosis in Internet of Things 认领 引用
19
作者 Zhen Wu Hao Liu +4 位作者 Linlin Zhang Zehui Zhang Jie Wu Haibin He Bin Zhou 《Computers, Materials & Continua》 SCIE EI 2026年第4期1051-1069,共19页
Recently,Internet ofThings(IoT)has been increasingly integrated into the automotive sector,enabling the development of diverse applications such as the Internet of Vehicles(IoV)and intelligent connected vehicles.Lever... Recently,Internet ofThings(IoT)has been increasingly integrated into the automotive sector,enabling the development of diverse applications such as the Internet of Vehicles(IoV)and intelligent connected vehicles.Leveraging IoVtechnologies,operational data fromcore vehicle components can be collected and analyzed to construct fault diagnosis models,thereby enhancing vehicle safety.However,automakers often struggle to acquire sufficient fault data to support effective model training.To address this challenge,a robust and efficient federated learning method(REFL)is constructed for machinery fault diagnosis in collaborative IoV,which can organize multiple companies to collaboratively develop a comprehensive fault diagnosis model while keeping their data locally.In the REFL,the gradient-based adversary algorithm is first introduced to the fault diagnosis field to enhance the deep learning model robustness.Moreover,the adaptive gradient processing process is designed to improve the model training speed and ensure the model accuracy under unbalance data scenarios.The proposed REFL is evaluated on non-independent and identically distributed(non-IID)real-world machinery fault dataset.Experiment results demonstrate that the REFL can achieve better performance than traditional learning methods and are promising for real industrial fault diagnosis. 展开更多
关键词 Federated learning adversary algorithm Internet of Vehicles(IoV) fault diagnosis
暂未订购 下载PDF
Active Fault Diagnosis and Early Warning Model of Distribution Transformers Using Sample Ensemble Learning and SO-SVM 认领 引用
20
作者 Long Yu Xianghua Pan +2 位作者 Rui Sun Yuan Li Wenjia Hao 《Energy Engineering》 EI 2026年第3期132-151,共20页
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
关键词 Core saturation distribution transformer early fault detection ensemble learning fault diagnosis inter-turn fault MATLAB simulation sample ensemble learning self-optimizing SVM transformer protection
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 45 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈