Traditional data-driven fault diagnosis methods depend on expert experience to manually extract effective fault features of signals,which has certain limitations.Conversely,deep learning techniques have gained promine...Traditional data-driven fault diagnosis methods depend on expert experience to manually extract effective fault features of signals,which has certain limitations.Conversely,deep learning techniques have gained prominence as a central focus of research in the field of fault diagnosis by strong fault feature extraction ability and end-to-end fault diagnosis efficiency.Recently,utilizing the respective advantages of convolution neural network(CNN)and Transformer in local and global feature extraction,research on cooperating the two have demonstrated promise in the field of fault diagnosis.However,the cross-channel convolution mechanism in CNN and the self-attention calculations in Transformer contribute to excessive complexity in the cooperative model.This complexity results in high computational costs and limited industrial applicability.To tackle the above challenges,this paper proposes a lightweight CNN-Transformer named as SEFormer for rotating machinery fault diagnosis.First,a separable multiscale depthwise convolution block is designed to extract and integrate multiscale feature information from different channel dimensions of vibration signals.Then,an efficient self-attention block is developed to capture critical fine-grained features of the signal from a global perspective.Finally,experimental results on the planetary gearbox dataset and themotor roller bearing dataset prove that the proposed framework can balance the advantages of robustness,generalization and lightweight compared to recent state-of-the-art fault diagnosis models based on CNN and Transformer.This study presents a feasible strategy for developing a lightweight rotating machinery fault diagnosis framework aimed at economical deployment.展开更多
Robustness against measurement uncertainties is crucial for gas turbine engine diagnosis.While current research focuses mainly on measurement noise,measurement bias remains challenging.This study proposes a novel perf...Robustness against measurement uncertainties is crucial for gas turbine engine diagnosis.While current research focuses mainly on measurement noise,measurement bias remains challenging.This study proposes a novel performance-based fault detection and identification(FDI)strategy for twin-shaft turbofan gas turbine engines and addresses these uncertainties through a first-order Takagi-Sugeno-Kang fuzzy inference system.To handle ambient condition changes,we use parameter correction to preprocess the raw measurement data,which reduces the FDI’s system complexity.Additionally,the power-level angle is set as a scheduling parameter to reduce the number of rules in the TSK-based FDI system.The data for designing,training,and testing the proposed FDI strategy are generated using a component-level turbofan engine model.The antecedent and consequent parameters of the TSK-based FDI system are optimized using the particle swarm optimization algorithm and ridge regression.A robust structure combining a specialized fuzzy inference system with the TSK-based FDI system is proposed to handle measurement biases.The performance of the first-order TSK-based FDI system and robust FDI structure are evaluated through comprehensive simulation studies.Comparative studies confirm the superior accuracy of the first-order TSK-based FDI system in fault detection,isolation,and identification.The robust structure demonstrates a 2%-8%improvement in the success rate index under relatively large measurement bias conditions,thereby indicating excellent robustness.Accuracy against significant bias values and computation time are also evaluated,suggesting that the proposed robust structure has desirable online performance.This study proposes a novel FDI strategy that effectively addresses measurement uncertainties.展开更多
Full ceramic bearings are mission-critical components in oil-free environments,such as food processing,semiconductor manufacturing,and medical applications.Developing effective fault diagnosis methods for these bearin...Full ceramic bearings are mission-critical components in oil-free environments,such as food processing,semiconductor manufacturing,and medical applications.Developing effective fault diagnosis methods for these bearings is essential to ensuring operational reliability and preventing costly failures.Traditional supervised deep learning approaches have demonstrated promise in fault detection,but their dependence on large labeled datasets poses significant challenges in industrial settings where fault-labeled data is scarce.This paper introduces a few-shot learning approach for full ceramic bearing fault diagnosis by leveraging the pre-trained GPT-2 model.Large language models(LLMs)like GPT-2,pre-trained on diverse textual data,exhibit remarkable transfer learning and few-shot learning capabilities,making them ideal for applications with limited labeled data.In this study,acoustic emission(AE)signals from bearings were processed using empirical mode decomposition(EMD),and the extracted AE features were converted into structured text for fine-tuning GPT-2 as a fault classifier.To enhance its performance,we incorporated a modified loss function and softmax activation with cosine similarity,ensuring better generalization in fault identification.Experimental evaluations on a laboratory-collected full ceramic bearing dataset demonstrated that the proposed approach achieved high diagnostic accuracy with as few as five labeled samples,outperforming conventional methods such as k-nearest neighbor(KNN),large memory storage and retrieval(LAMSTAR)neural network,deep neural network(DNN),recurrent neural network(RNN),long short-term memory(LSTM)network,and model-agnostic meta-learning(MAML).The results highlight LLMs’potential to revolutionize fault diagnosis,enabling faster deployment,reduced reliance on extensive labeled datasets,and improved adaptability in industrial monitoring systems.展开更多
Fault diagnosis in industrial process is essential for ensuring production safety and efficiency.However,existing methods exhibit limited capability in recognizing hard samples and struggle to maintain consistency in ...Fault diagnosis in industrial process is essential for ensuring production safety and efficiency.However,existing methods exhibit limited capability in recognizing hard samples and struggle to maintain consistency in feature distributions across domains,resulting in suboptimal performance and robustness.Therefore,this paper proposes a fault diagnosis neural network for hard sample mining and domain adaptive(SmdaNet).First,the method uses deep belief networks(DBN)to build a diagnostic model.Hard samples are mined based on the loss values,dividing the data set into hard and easy samples.Second,elastic weight consolidation(EWC)is used to train the model on hard samples,effectively preventing information forgetting.Finally,the feature space domain adaptation is introduced to optimize the feature space by minimizing the Kullback–Leibler divergence of the feature distributions.Experimental results show that the proposed SmdaNet method outperforms existing approaches in terms of classification accuracy,robustness and interpretability on the penicillin simulation and Tennessee Eastman process datasets.展开更多
Supervised learning classification has arisen as a powerful tool to perform data-driven fault diagnosis in dynamical systems,achieving astonishing results.This approach assumes the availability of extensive,diverse an...Supervised learning classification has arisen as a powerful tool to perform data-driven fault diagnosis in dynamical systems,achieving astonishing results.This approach assumes the availability of extensive,diverse and labeled data corpora for train-ing.However,in some applications it may be difficult or not feasible to obtain a large and balanced dataset including enough representative instances of the fault behaviors of interest.This fact leads to the issues of data scarcity and class imbalance,greatly affecting the performance of supervised learning classifiers.Datasets from railway systems are usually both,scarce and imbalanced,turning supervised learning-based fault diagnosis into a highly challenging task.This article addresses time-series data augmentation for fault diagnosis purposes and presents two application cases in the context of railway track.The case studies employ generative adversarial networks(GAN)schemes to produce realistic synthetic samples of geometrical and structural track defects.The goal is to generate samples that enhance fault diagnosis performance;therefore,major attention was paid not only in the generation process,but also in the synthesis quality assessment,to guarantee the suitability of the samples for training of supervised learning classification models.In the first application,a convolutional classifier achieved a test accuracy of 87.5%for the train on synthetic,test on real(TSTR)scenario,while,in the second application,a fully-connected classifier achieved 96.18%in test accuracy for TSTR.The results indicate that the proposed augmentation approach produces samples having equivalent statistical characteristics and leading to a similar classification behavior as real data.展开更多
Liquid rocket engine(LRE)fault diagnosis is critical for successful space launch missions,enabling timely avoidance of safety hazards,while accurate post-failure analysis prevents subsequent economic losses.However,th...Liquid rocket engine(LRE)fault diagnosis is critical for successful space launch missions,enabling timely avoidance of safety hazards,while accurate post-failure analysis prevents subsequent economic losses.However,the complexity of LRE systems and the“black-box”nature of current deep learning-based diagnostic methods hinder interpretable fault diagnosis.This paper establishes Granger causality(GC)extraction-based component-wise multi-layer perceptron(GCMLP),achieving high fault diagnosis accuracy while leveraging GC to enhance diagnostic interpretability.First,component-wise MLP networks are constructed for distinct LRE variables to extract inter-variable GC relationships.Second,dedicated predictors are designed for each variable,leveraging historical data and GC relationships to forecast future states,thereby ensuring GC reliability.Finally,the extracted GC features are utilized for fault classification,guaranteeing feature discriminability and diagnosis accuracy.This study simulates six critical fault modes in LRE using Simulink.Based on the generated simulation data,GCMLP demonstrates superior fault localization accuracy compared to benchmark methods,validating its efficacy and robustness.展开更多
Centrifugal Pumps(CPs)are critical machine components in many industries,and their efficient operation and reliable Fault Diagnosis(FD)are essential for minimizing downtime and maintenance costs.This paper introduces ...Centrifugal Pumps(CPs)are critical machine components in many industries,and their efficient operation and reliable Fault Diagnosis(FD)are essential for minimizing downtime and maintenance costs.This paper introduces a novel FD method to improve both the accuracy and reliability of detecting potential faults in such pumps.Theproposed method combinesWaveletCoherent Analysis(WCA)and Stockwell Transform(S-transform)scalograms with Sobel and non-local means filters,effectively capturing complex fault signatures from vibration signals.Using Convolutional Neural Network(CNN)for feature extraction,the method transforms these scalograms into image inputs,enabling the recognition of patterns that span both time and frequency domains.The CNN extracts essential discriminative features,which are then merged and passed into a Kolmogorov-Arnold Network(KAN)classifier,ensuring precise fault identification.The proposed approach was experimentally validated on diverse datasets collected under varying conditions,demonstrating its robustness and generalizability.Achieving classification accuracy of 100%,99.86%,and 99.92%across the datasets,this method significantly outperforms traditional fault detection approaches.These results underscore the potential to enhance CP FD,providing an effective solution for predictive maintenance and improving overall system reliability.展开更多
High-Speed Trains (HSTs) have emerged as a mainstream mode of transportation in China, owing to their exceptional safety and efficiency. Ensuring the reliable operation of HSTs is of paramount economic and societal im...High-Speed Trains (HSTs) have emerged as a mainstream mode of transportation in China, owing to their exceptional safety and efficiency. Ensuring the reliable operation of HSTs is of paramount economic and societal importance. As critical rotating mechanical components of the transmission system, bearings make their fault diagnosis a topic of extensive attention. This paper provides a systematic review of image encoding-based bearing fault diagnosis methods tailored to the condition monitoring of HSTs. First, it categorizes the image encoding techniques applied in the field of bearing fault diagnosis. Then, a review of state-of-the-art studies has been presented, encompassing both monomodal image conversion and multimodal image fusion approaches. Finally, it highlights current challenges and proposes future research directions to advance intelligent fault diagnosis in HSTs, aiming to provide a valuable reference for researchers and engineers in the field of intelligent operation and maintenance.展开更多
The rudder mechanism of the X-rudder autonomous underwater cehicle(AUV)is relatively complex,and fault diagnosis capability is an important guarantee for its task execution in complex underwater environments.However,t...The rudder mechanism of the X-rudder autonomous underwater cehicle(AUV)is relatively complex,and fault diagnosis capability is an important guarantee for its task execution in complex underwater environments.However,traditional fault diagnosis methods currently rely on prior knowledge and expert experience,and lack accuracy.In order to improve the autonomy and accuracy of fault diagnosis methods,and overcome the shortcomings of traditional algorithms,this paper proposes an X-steering AUV fault diagnosis model based on the deep reinforcement learning deep Q network(DQN)algorithm,which can learn the relationship between state data and fault types,map raw residual data to corresponding fault patterns,and achieve end-to-end mapping.In addition,to solve the problem of few X-steering fault sample data,Dropout technology is introduced during the model training phase to improve the performance of the DQN algorithm.Experimental results show that the proposed model has improved the convergence speed and comprehensive performance indicators compared to the unimproved DQN algorithm,with precision,recall,F_(1-score),and accuracy reaching up to 100%,98.07%,99.02%,and 98.50% respectively,and the model’s accuracy is higher than other machine learning algorithms like back propagation,support vector machine.展开更多
Rolling bearings are important parts of industrial equipment,and their fault diagnosis is crucial to maintaining these equipment’s regular operations.With the goal of improving the fault diagnosis accuracy of rolling...Rolling bearings are important parts of industrial equipment,and their fault diagnosis is crucial to maintaining these equipment’s regular operations.With the goal of improving the fault diagnosis accuracy of rolling bearings under complex working conditions and noise,this study proposes a multiscale information fusion method for fault diagnosis of rolling bearings based on fast Fourier transform(FFT)and variational mode decomposition(VMD),as well as the Senet(SE)-TCNnet(TCN)model.FFT is used to transform the original one-dimensional time domain vibration signal into a frequency domain signal,while VMD is used to decompose the original signal into several inherent mode functions(IMFs)of different scales.The center frequency method also determines the number of mode decompositions.Then,the data obtained by the two methods are fused into data containing the bearing fault information of different scales.Finally,the fused data are sent to the SE-TCN model for training.Experimental tests are conducted to verify the performance of this method.The findings reveal that an average accuracy of 98.39%can be achieved when noise is added and can even reach 100%when the signal-to-noise ratio is 6 dB.When the load changes,the accuracy of the model can reach 97.45%.The proposed method has the characteristics of high accuracy and strong generalization ability in bearing fault diagnosis.Furthermore,it can effectively overcome the effects of noise and variable working conditions in actual industrial environments,thus providing some ideas for future practical applications of bearing fault diagnosis.展开更多
The research on fault diagnosis based on multi-source information fusion technology aims to comprehensively integrate the diagnostic information of complex mechanical and electrical equipment,providing a scientific an...The research on fault diagnosis based on multi-source information fusion technology aims to comprehensively integrate the diagnostic information of complex mechanical and electrical equipment,providing a scientific and precise decision-making basis for decision-makers.However,in diagnostic practice,issues such as the impact of component replacement,rule combination explosion,and information redundancy have become research difficulties.To address these challenges,this paper innovatively combines equipment mechanisms with expert knowledge to build an optimized model that considers the impact of component replacement based on the traditional Belief Rule Base(BRB-h).Meanwhile,under the framework of traditional independent component analysis,this paper proposes an Independent Component Analysis(ICA)method that considers Expert knowledge(ICA-E).Furthermore,to quantify the impact of component replacement on equipment performance,this paper delves into the transparency and traceability of replacement impact factors and conducts a sensitivity analysis.Through empirical case studies,the advancement and practicability of this new method in the field of fault diagnosis are verified.展开更多
Intelligent fault diagnosis technology plays an indispensable role in ensuring the safety,stability,and efficiency of railway operations.However,existing studies have the following limitations.1)They are typical black-...Intelligent fault diagnosis technology plays an indispensable role in ensuring the safety,stability,and efficiency of railway operations.However,existing studies have the following limitations.1)They are typical black-box models that lacks interpretability as well as they fuse features by simply stacking them,overlooking the discrepancies in the importance of different features,which reduces the credibility and diagnosis accuracy of the models.2)They ignore the effects of potentially mistaken labels in the training datasets disrupting the ability of the models to learn the true data distribution,which degrades the generalization performance of intelligent diagnosis models,especially when the training samples are limited.To address the above items,an interpretable few-shot framework for fault diagnosis with noisy labels is proposed for train transmission systems.In the proposed framework,a feature extractor is constructed by stacked frequency band focus modules,which can capture signal features in different frequency bands and further adaptively concentrate on the features corresponding to the potential fault characteristic frequency.Then,according to prototypical network,a novel metric-based classifier is developed that is tolerant to mislabeled support samples in the case of limited samples.Besides,a new loss function is designed to decrease the impact of label mistakes in query datasets.Finally,fault simulation experiments of subway train transmission systems are designed and conducted,and the effectiveness as well as superiority of the proposed method are proved by ablation experiments and comparison with the existing methods.展开更多
The electromagnetic pulse valve,as a key component in baghouse dust removal systems,plays a crucial role in the performance of the system.However,despite the promising results of intelligent fault diagnosis methods ba...The electromagnetic pulse valve,as a key component in baghouse dust removal systems,plays a crucial role in the performance of the system.However,despite the promising results of intelligent fault diagnosis methods based on extensive data in diagnosing electromagnetic valves,real-world diagnostic scenarios still face numerous challenges.Collecting fault data for electromagnetic pulse valves is not only time-consuming but also costly,making it difficult to obtain sufficient fault data in advance,which poses challenges for small sample fault diagnosis.To address this issue,this paper proposes a fault diagnosis method for electromagnetic pulse valves based on deep transfer learning and simulated data.This method achieves effective transfer from simulated data to real data through four parameter transfer strategies,which combine parameter freezing and fine-tuning operations.Furthermore,this paper identifies a parameter transfer strategy that simultaneously fine-tunes the feature extractor and classifier,and introduces an attention mechanism to integrate fault features,thereby enhancing the correlation and information complementarity among multi-sensor data.The effectiveness of the proposed method is evaluated through two fault diagnosis cases under different operating conditions.In this study,small sample data accounted for 7.9%and 8.2%of the total dataset,and the experimental results showed transfer accuracies of 93.5%and 94.2%,respectively,validating the reliability and effectiveness of the method under small sample conditions.展开更多
Difficulty in extracting nonlinear sparse impulse features due to variable speed conditions and redundant noise interference leads to challenges in diagnosing variable speed faults.Therefore,an improved spectral amplit...Difficulty in extracting nonlinear sparse impulse features due to variable speed conditions and redundant noise interference leads to challenges in diagnosing variable speed faults.Therefore,an improved spectral amplitude modulation(ISAM)based on sparse feature adaptive convolution(SFAC)is proposed to enhance the fault features under variable speed conditions.First,an optimal bi-damped wavelet construction method is proposed to learn signal impulse features,which selects the optimal bi-damped wavelet parameters with correlation criterion and particle swarm optimization.Second,a convolutional basis pursuit denoising model based on an optimal bi-damped wavelet is proposed for resolving sparse impulses.A model regularization parameter selection method based on weighted fault characteristic amplitude ratio assistance is proposed.Then,an ISAM method based on kurtosis threshold is proposed to further enhance the fault information of sparse signal.Finally,the type of variable speed faults is determined by order spectrum analysis.Various experimental results,such as spectral amplitude modulation and Morlet wavelet matching,verify the effectiveness and advantages of the ISAM-SFAC method.展开更多
The accurate identification and diagnosis of chemical process faults are crucial for ensuring the safe and stable operation of production plants.The current hot topic in industrial process fault diagnosis research is ...The accurate identification and diagnosis of chemical process faults are crucial for ensuring the safe and stable operation of production plants.The current hot topic in industrial process fault diagnosis research is data-driven methods.Most of the existing fault diagnosis methods focus on a single shallow or deep learning model.This paper proposes a novel hybrid fault diagnosis method to fully utilize various features to improve the accuracy of fault diagnosis.Furthermore,the method addresses the issue of incomplete data,which has been largely overlooked in the majority of existing research.Firstly,the variable data is effectively fitted using orthogonal non-negative matrix tri-factorization,and the missing data in the matrix is solved to construct a complete production condition relationship.Next,the support vector machine model and the deep residual contraction network model are trained in parallel to prediagnose process faults by mining linear and non-linear interaction features.Finally,a novel mapping relationship is established between the result and model levels using the multi-layer perceptron algorithm to complete the final diagnosis and evaluation of the fault.To demonstrate the effectiveness of the proposed method,we conducted extensive comparative experiments on the Tennessee Eastman dataset and the ethylene plant cracking unit dataset.The experimental results show that the method has advantages in different evaluation metrics.展开更多
In real industrial scenarios, equipment cannot be operated in a faulty state for a long time, resulting in a very limited number of available fault samples, and the method of data augmentation using generative adversa...In real industrial scenarios, equipment cannot be operated in a faulty state for a long time, resulting in a very limited number of available fault samples, and the method of data augmentation using generative adversarial networks for smallsample data has achieved a wide range of applications. However, the current generative adversarial networks applied in industrial processes do not impose realistic physical constraints on the generation of data, resulting in the generation of data that do not have realistic physical consistency. To address this problem, this paper proposes a physical consistency-based WGAN, designs a loss function containing physical constraints for industrial processes, and validates the effectiveness of the method using a common dataset in the field of industrial process fault diagnosis. The experimental results show that the proposed method not only makes the generated data consistent with the physical constraints of the industrial process, but also has better fault diagnosis performance than the existing GAN-based methods.展开更多
With the intelligent upgrading of manufacturing equipment,achieving high-precision and efficient fault diagnosis is essential to enhance equipment stability and increase productivity.Online monitoring and fault diagno...With the intelligent upgrading of manufacturing equipment,achieving high-precision and efficient fault diagnosis is essential to enhance equipment stability and increase productivity.Online monitoring and fault diagnosis technology play a critical role in improving the stability of metal additive manufacturing equipment.However,the limited proportion of fault data during operation challenges the accuracy and efficiency of multi-classification models due to excessive redundant data.A multi-sensor and principal component analysis(PCA)and support vector machine(SVM)asymptotic classification(PCSV)for additive manufacturing fault diagnosis method is proposed,and it divides the fault diagnosis into two steps.In the first step,real-time data are evaluated using the T2 and Q statistical parameters of the PCAmodel to identify potential faults while filtering non-fault data,thereby reducing redundancy and enhancing real-time efficiency.In the second step,the identified fault data are input into the SVM model for precise multi-class classification of fault categories.The PCSV method advances the field by significantly improving diagnostic accuracy and efficiency,achieving an accuracy of 99%,a diagnosis time of 0.65 s,and a training time of 503 s.The experimental results demonstrate the sophistication of the PCSV method for high-precision and high-efficiency fault diagnosis of small fault samples.展开更多
High-speed train engine rolling bearings play a crucial role in maintaining engine health and minimizing operational losses during train operation.To solve the problems of low accuracy of the diagnostic model and unst...High-speed train engine rolling bearings play a crucial role in maintaining engine health and minimizing operational losses during train operation.To solve the problems of low accuracy of the diagnostic model and unstable model due to the influence of noise during fault detection,a rolling bearing fault diagnosis model based on cross-attention fusion of WDCNN and BILSTM is proposed.The first layer of the wide convolutional kernel deep convolutional neural network(WDCNN)is used to extract the local features of the signal and suppress the highfrequency noise.A Bidirectional Long Short-Term Memory Network(BILSTM)is used to obtain global time series features of the signal.Cross-attention combines the WDCNN layer and the BILSTM layer so that the model can recognize more comprehensive feature information of the signal.Meanwhile,to improve the accuracy,Variable Modal Decomposition(VMD)is used to decompose the signals and filter and reconstruct the signals using envelope entropy and kurtosis,which enables the pre-processing of the signals so that the data input to the neural network contains richer feature information.The feasibility of the model is tested and experimentally validated using publicly available datasets.The experimental results show that the accuracy of themodel proposed in this paper is significantly improved compared to the traditional WDCNN,BILSTM,and WDCNN-BILSTM models.展开更多
In intelligentmanufacturing processes such as aerospace production,computer numerical control(CNC)machine tools require real-time optimization of process parameters to meet precision machining demands.These dynamic op...In intelligentmanufacturing processes such as aerospace production,computer numerical control(CNC)machine tools require real-time optimization of process parameters to meet precision machining demands.These dynamic operating conditions increase the risk of fatigue damage in CNC machine tool bearings,highlighting the urgent demand for rapid and accurate fault diagnosis methods that can maintain production efficiency and extend equipment uptime.However,varying conditions induce feature distribution shifts,and scarce fault samples limitmodel generalization.Therefore,this paper proposes a causal-Transformer-based meta-learning(CTML)method for bearing fault diagnosis in CNC machine tools,comprising three core modules:(1)the original bearing signal is transformed into a multi-scale time-frequency feature space using continuous wavelet transform;(2)a causal-Transformer architecture is designed to achieve feature extraction and fault classification based on the physical causal law of fault propagation;(3)the above mechanisms are integrated into a model-agnostic meta-learning(MAML)framework to achieve rapid cross-condition adaptation through an adaptive gradient pruning strategy.Experimental results using the multiple bearing dataset show that under few-shot cross-condition scenarios(3-way 1-shot and 3-way 5-shot),the proposed CTML outperforms benchmark models(e.g.,Transformer,domain adversarial neural networks(DANN),and MAML)in terms of classification accuracy and sensitivity to operating conditions,while maintaining a moderate level of model complexity.展开更多
As industrial systems become increasingly complex,the significant research interest has been devoted to intelligent fault diagnosis approaches leveraging deep learning.However,existing methods still face two critical ...As industrial systems become increasingly complex,the significant research interest has been devoted to intelligent fault diagnosis approaches leveraging deep learning.However,existing methods still face two critical challenges in practical applications:1)the extracted features often fail to maintain robustness in nonstationary conditions;2)deep neural networks generally exhibit a black box nature,offering limited interpretability in their feature extraction process.To solve the above issues,an interpretable wavelet Kolmogorov-Arnold convolutional Long Short-Term Memory(WKAConvLSTM)is proposed,which mainly consists of two key components:1)a wavelet Kolmogorov-Arnold kernel(WKAK)with learnable scale and translation parameters is designed and then embedded into convolutional layers to enable the extracted spatial features interpretable;2)a multi-head attention-enhanced Long Short-Term Memory(MHA-LSTM)is proposed to effectively capture crucial temporal dependencies in sequential data.In order to verify its effectiveness,the proposed model is tested on bearing and gearbox datasets under complex conditions,including noise interference,nonstationary operating conditions,and data class imbalance.The experimental results demonstrate that it not only achieves superior diagnostic accuracy compared with advanced baseline models but also enhances the interpretability of the extracted features.展开更多
基金supported by the National Natural Science Foundation of China(No.52277055).
文摘Traditional data-driven fault diagnosis methods depend on expert experience to manually extract effective fault features of signals,which has certain limitations.Conversely,deep learning techniques have gained prominence as a central focus of research in the field of fault diagnosis by strong fault feature extraction ability and end-to-end fault diagnosis efficiency.Recently,utilizing the respective advantages of convolution neural network(CNN)and Transformer in local and global feature extraction,research on cooperating the two have demonstrated promise in the field of fault diagnosis.However,the cross-channel convolution mechanism in CNN and the self-attention calculations in Transformer contribute to excessive complexity in the cooperative model.This complexity results in high computational costs and limited industrial applicability.To tackle the above challenges,this paper proposes a lightweight CNN-Transformer named as SEFormer for rotating machinery fault diagnosis.First,a separable multiscale depthwise convolution block is designed to extract and integrate multiscale feature information from different channel dimensions of vibration signals.Then,an efficient self-attention block is developed to capture critical fine-grained features of the signal from a global perspective.Finally,experimental results on the planetary gearbox dataset and themotor roller bearing dataset prove that the proposed framework can balance the advantages of robustness,generalization and lightweight compared to recent state-of-the-art fault diagnosis models based on CNN and Transformer.This study presents a feasible strategy for developing a lightweight rotating machinery fault diagnosis framework aimed at economical deployment.
文摘Robustness against measurement uncertainties is crucial for gas turbine engine diagnosis.While current research focuses mainly on measurement noise,measurement bias remains challenging.This study proposes a novel performance-based fault detection and identification(FDI)strategy for twin-shaft turbofan gas turbine engines and addresses these uncertainties through a first-order Takagi-Sugeno-Kang fuzzy inference system.To handle ambient condition changes,we use parameter correction to preprocess the raw measurement data,which reduces the FDI’s system complexity.Additionally,the power-level angle is set as a scheduling parameter to reduce the number of rules in the TSK-based FDI system.The data for designing,training,and testing the proposed FDI strategy are generated using a component-level turbofan engine model.The antecedent and consequent parameters of the TSK-based FDI system are optimized using the particle swarm optimization algorithm and ridge regression.A robust structure combining a specialized fuzzy inference system with the TSK-based FDI system is proposed to handle measurement biases.The performance of the first-order TSK-based FDI system and robust FDI structure are evaluated through comprehensive simulation studies.Comparative studies confirm the superior accuracy of the first-order TSK-based FDI system in fault detection,isolation,and identification.The robust structure demonstrates a 2%-8%improvement in the success rate index under relatively large measurement bias conditions,thereby indicating excellent robustness.Accuracy against significant bias values and computation time are also evaluated,suggesting that the proposed robust structure has desirable online performance.This study proposes a novel FDI strategy that effectively addresses measurement uncertainties.
文摘Full ceramic bearings are mission-critical components in oil-free environments,such as food processing,semiconductor manufacturing,and medical applications.Developing effective fault diagnosis methods for these bearings is essential to ensuring operational reliability and preventing costly failures.Traditional supervised deep learning approaches have demonstrated promise in fault detection,but their dependence on large labeled datasets poses significant challenges in industrial settings where fault-labeled data is scarce.This paper introduces a few-shot learning approach for full ceramic bearing fault diagnosis by leveraging the pre-trained GPT-2 model.Large language models(LLMs)like GPT-2,pre-trained on diverse textual data,exhibit remarkable transfer learning and few-shot learning capabilities,making them ideal for applications with limited labeled data.In this study,acoustic emission(AE)signals from bearings were processed using empirical mode decomposition(EMD),and the extracted AE features were converted into structured text for fine-tuning GPT-2 as a fault classifier.To enhance its performance,we incorporated a modified loss function and softmax activation with cosine similarity,ensuring better generalization in fault identification.Experimental evaluations on a laboratory-collected full ceramic bearing dataset demonstrated that the proposed approach achieved high diagnostic accuracy with as few as five labeled samples,outperforming conventional methods such as k-nearest neighbor(KNN),large memory storage and retrieval(LAMSTAR)neural network,deep neural network(DNN),recurrent neural network(RNN),long short-term memory(LSTM)network,and model-agnostic meta-learning(MAML).The results highlight LLMs’potential to revolutionize fault diagnosis,enabling faster deployment,reduced reliance on extensive labeled datasets,and improved adaptability in industrial monitoring systems.
基金support from the following foundations:the National Natural Science Foundation of China(62322309,62433004)Shanghai Science and Technology Innovation Action Plan(23S41900500)Shanghai Pilot Program for Basic Research(22TQ1400100-16).
文摘Fault diagnosis in industrial process is essential for ensuring production safety and efficiency.However,existing methods exhibit limited capability in recognizing hard samples and struggle to maintain consistency in feature distributions across domains,resulting in suboptimal performance and robustness.Therefore,this paper proposes a fault diagnosis neural network for hard sample mining and domain adaptive(SmdaNet).First,the method uses deep belief networks(DBN)to build a diagnostic model.Hard samples are mined based on the loss values,dividing the data set into hard and easy samples.Second,elastic weight consolidation(EWC)is used to train the model on hard samples,effectively preventing information forgetting.Finally,the feature space domain adaptation is introduced to optimize the feature space by minimizing the Kullback–Leibler divergence of the feature distributions.Experimental results show that the proposed SmdaNet method outperforms existing approaches in terms of classification accuracy,robustness and interpretability on the penicillin simulation and Tennessee Eastman process datasets.
基金supported by the German Research Foundation(DFG)under the project“Efficient Sensor-Based Condition Monitoring Methodology for the Detection and Localization of Faults on the Railway Track(ConMoRAIL)”,Grant No.515687155.
文摘Supervised learning classification has arisen as a powerful tool to perform data-driven fault diagnosis in dynamical systems,achieving astonishing results.This approach assumes the availability of extensive,diverse and labeled data corpora for train-ing.However,in some applications it may be difficult or not feasible to obtain a large and balanced dataset including enough representative instances of the fault behaviors of interest.This fact leads to the issues of data scarcity and class imbalance,greatly affecting the performance of supervised learning classifiers.Datasets from railway systems are usually both,scarce and imbalanced,turning supervised learning-based fault diagnosis into a highly challenging task.This article addresses time-series data augmentation for fault diagnosis purposes and presents two application cases in the context of railway track.The case studies employ generative adversarial networks(GAN)schemes to produce realistic synthetic samples of geometrical and structural track defects.The goal is to generate samples that enhance fault diagnosis performance;therefore,major attention was paid not only in the generation process,but also in the synthesis quality assessment,to guarantee the suitability of the samples for training of supervised learning classification models.In the first application,a convolutional classifier achieved a test accuracy of 87.5%for the train on synthetic,test on real(TSTR)scenario,while,in the second application,a fully-connected classifier achieved 96.18%in test accuracy for TSTR.The results indicate that the proposed augmentation approach produces samples having equivalent statistical characteristics and leading to a similar classification behavior as real data.
文摘Liquid rocket engine(LRE)fault diagnosis is critical for successful space launch missions,enabling timely avoidance of safety hazards,while accurate post-failure analysis prevents subsequent economic losses.However,the complexity of LRE systems and the“black-box”nature of current deep learning-based diagnostic methods hinder interpretable fault diagnosis.This paper establishes Granger causality(GC)extraction-based component-wise multi-layer perceptron(GCMLP),achieving high fault diagnosis accuracy while leveraging GC to enhance diagnostic interpretability.First,component-wise MLP networks are constructed for distinct LRE variables to extract inter-variable GC relationships.Second,dedicated predictors are designed for each variable,leveraging historical data and GC relationships to forecast future states,thereby ensuring GC reliability.Finally,the extracted GC features are utilized for fault classification,guaranteeing feature discriminability and diagnosis accuracy.This study simulates six critical fault modes in LRE using Simulink.Based on the generated simulation data,GCMLP demonstrates superior fault localization accuracy compared to benchmark methods,validating its efficacy and robustness.
基金supported by the Technology Innovation Program(20023566,‘Development and Demonstration of Industrial IoT and AI-Based Process Facility Intelligence Support System in Small and Medium Manufacturing Sites’)funded by the Ministry of Trade,Industry,&Energy(MOTIE,Republic of Korea).
文摘Centrifugal Pumps(CPs)are critical machine components in many industries,and their efficient operation and reliable Fault Diagnosis(FD)are essential for minimizing downtime and maintenance costs.This paper introduces a novel FD method to improve both the accuracy and reliability of detecting potential faults in such pumps.Theproposed method combinesWaveletCoherent Analysis(WCA)and Stockwell Transform(S-transform)scalograms with Sobel and non-local means filters,effectively capturing complex fault signatures from vibration signals.Using Convolutional Neural Network(CNN)for feature extraction,the method transforms these scalograms into image inputs,enabling the recognition of patterns that span both time and frequency domains.The CNN extracts essential discriminative features,which are then merged and passed into a Kolmogorov-Arnold Network(KAN)classifier,ensuring precise fault identification.The proposed approach was experimentally validated on diverse datasets collected under varying conditions,demonstrating its robustness and generalizability.Achieving classification accuracy of 100%,99.86%,and 99.92%across the datasets,this method significantly outperforms traditional fault detection approaches.These results underscore the potential to enhance CP FD,providing an effective solution for predictive maintenance and improving overall system reliability.
基金supported by the Fundamental Research Funds for the Central Universities(No.2024JBZX027)the National Natural Science Foundation of China(No.52375078).
文摘High-Speed Trains (HSTs) have emerged as a mainstream mode of transportation in China, owing to their exceptional safety and efficiency. Ensuring the reliable operation of HSTs is of paramount economic and societal importance. As critical rotating mechanical components of the transmission system, bearings make their fault diagnosis a topic of extensive attention. This paper provides a systematic review of image encoding-based bearing fault diagnosis methods tailored to the condition monitoring of HSTs. First, it categorizes the image encoding techniques applied in the field of bearing fault diagnosis. Then, a review of state-of-the-art studies has been presented, encompassing both monomodal image conversion and multimodal image fusion approaches. Finally, it highlights current challenges and proposes future research directions to advance intelligent fault diagnosis in HSTs, aiming to provide a valuable reference for researchers and engineers in the field of intelligent operation and maintenance.
基金Supported by the National Natural Science Foundation of China under Grant Nos.52071099,52071104National Key Project of Research and Development Program under Grant No.2021YFC2801300Research Fund from National Key Laboratory of Autonomous Marine Vehicle Technology under Grant No.2023-SXJQR-SYSJJ01.
文摘The rudder mechanism of the X-rudder autonomous underwater cehicle(AUV)is relatively complex,and fault diagnosis capability is an important guarantee for its task execution in complex underwater environments.However,traditional fault diagnosis methods currently rely on prior knowledge and expert experience,and lack accuracy.In order to improve the autonomy and accuracy of fault diagnosis methods,and overcome the shortcomings of traditional algorithms,this paper proposes an X-steering AUV fault diagnosis model based on the deep reinforcement learning deep Q network(DQN)algorithm,which can learn the relationship between state data and fault types,map raw residual data to corresponding fault patterns,and achieve end-to-end mapping.In addition,to solve the problem of few X-steering fault sample data,Dropout technology is introduced during the model training phase to improve the performance of the DQN algorithm.Experimental results show that the proposed model has improved the convergence speed and comprehensive performance indicators compared to the unimproved DQN algorithm,with precision,recall,F_(1-score),and accuracy reaching up to 100%,98.07%,99.02%,and 98.50% respectively,and the model’s accuracy is higher than other machine learning algorithms like back propagation,support vector machine.
基金supported by Handan Science and Technology Research and Development Plan Project under Grant no.23422901031Key Laboratory of Intelligent Industrial Equipment Technology of Hebei Province(Hebei University of Engineering)under Grant no.202206.
文摘Rolling bearings are important parts of industrial equipment,and their fault diagnosis is crucial to maintaining these equipment’s regular operations.With the goal of improving the fault diagnosis accuracy of rolling bearings under complex working conditions and noise,this study proposes a multiscale information fusion method for fault diagnosis of rolling bearings based on fast Fourier transform(FFT)and variational mode decomposition(VMD),as well as the Senet(SE)-TCNnet(TCN)model.FFT is used to transform the original one-dimensional time domain vibration signal into a frequency domain signal,while VMD is used to decompose the original signal into several inherent mode functions(IMFs)of different scales.The center frequency method also determines the number of mode decompositions.Then,the data obtained by the two methods are fused into data containing the bearing fault information of different scales.Finally,the fused data are sent to the SE-TCN model for training.Experimental tests are conducted to verify the performance of this method.The findings reveal that an average accuracy of 98.39%can be achieved when noise is added and can even reach 100%when the signal-to-noise ratio is 6 dB.When the load changes,the accuracy of the model can reach 97.45%.The proposed method has the characteristics of high accuracy and strong generalization ability in bearing fault diagnosis.Furthermore,it can effectively overcome the effects of noise and variable working conditions in actual industrial environments,thus providing some ideas for future practical applications of bearing fault diagnosis.
基金co-supported by the National Natural Science Foundation of China(Nos.62273354,61673387,62227814,62203461,62203365)Shaanxi Provincial Science and Technology Innovation Team,China(No.2022TD-24)+2 种基金China Postdoctoral Science Foundation(No.2023M742843)Young Talent Promotion Program of Shaanxi Association for Science and Technology,China(Nos.20220121,20230125)Natural Science Basic Research Program of Shaanxi,China(No.2022JQ-580).
文摘The research on fault diagnosis based on multi-source information fusion technology aims to comprehensively integrate the diagnostic information of complex mechanical and electrical equipment,providing a scientific and precise decision-making basis for decision-makers.However,in diagnostic practice,issues such as the impact of component replacement,rule combination explosion,and information redundancy have become research difficulties.To address these challenges,this paper innovatively combines equipment mechanisms with expert knowledge to build an optimized model that considers the impact of component replacement based on the traditional Belief Rule Base(BRB-h).Meanwhile,under the framework of traditional independent component analysis,this paper proposes an Independent Component Analysis(ICA)method that considers Expert knowledge(ICA-E).Furthermore,to quantify the impact of component replacement on equipment performance,this paper delves into the transparency and traceability of replacement impact factors and conducts a sensitivity analysis.Through empirical case studies,the advancement and practicability of this new method in the field of fault diagnosis are verified.
基金supported in part by the National Key R&D Program of China under Grant 2022YFB4300601in part by the State Key Laboratory of Advanced Rail Autonomous Operation under Grant RAO2023ZZ003.
文摘Intelligent fault diagnosis technology plays an indispensable role in ensuring the safety,stability,and efficiency of railway operations.However,existing studies have the following limitations.1)They are typical black-box models that lacks interpretability as well as they fuse features by simply stacking them,overlooking the discrepancies in the importance of different features,which reduces the credibility and diagnosis accuracy of the models.2)They ignore the effects of potentially mistaken labels in the training datasets disrupting the ability of the models to learn the true data distribution,which degrades the generalization performance of intelligent diagnosis models,especially when the training samples are limited.To address the above items,an interpretable few-shot framework for fault diagnosis with noisy labels is proposed for train transmission systems.In the proposed framework,a feature extractor is constructed by stacked frequency band focus modules,which can capture signal features in different frequency bands and further adaptively concentrate on the features corresponding to the potential fault characteristic frequency.Then,according to prototypical network,a novel metric-based classifier is developed that is tolerant to mislabeled support samples in the case of limited samples.Besides,a new loss function is designed to decrease the impact of label mistakes in query datasets.Finally,fault simulation experiments of subway train transmission systems are designed and conducted,and the effectiveness as well as superiority of the proposed method are proved by ablation experiments and comparison with the existing methods.
基金Supported by National Natural Science Foundation of China(Grant No.51675040)。
文摘The electromagnetic pulse valve,as a key component in baghouse dust removal systems,plays a crucial role in the performance of the system.However,despite the promising results of intelligent fault diagnosis methods based on extensive data in diagnosing electromagnetic valves,real-world diagnostic scenarios still face numerous challenges.Collecting fault data for electromagnetic pulse valves is not only time-consuming but also costly,making it difficult to obtain sufficient fault data in advance,which poses challenges for small sample fault diagnosis.To address this issue,this paper proposes a fault diagnosis method for electromagnetic pulse valves based on deep transfer learning and simulated data.This method achieves effective transfer from simulated data to real data through four parameter transfer strategies,which combine parameter freezing and fine-tuning operations.Furthermore,this paper identifies a parameter transfer strategy that simultaneously fine-tunes the feature extractor and classifier,and introduces an attention mechanism to integrate fault features,thereby enhancing the correlation and information complementarity among multi-sensor data.The effectiveness of the proposed method is evaluated through two fault diagnosis cases under different operating conditions.In this study,small sample data accounted for 7.9%and 8.2%of the total dataset,and the experimental results showed transfer accuracies of 93.5%and 94.2%,respectively,validating the reliability and effectiveness of the method under small sample conditions.
基金funded by the National Natural Science Foundation of China(grant nos.52475084 and 52375076)the Postdoctoral Fellowship Program of CPSF(grant no.GZC20230202).
文摘Difficulty in extracting nonlinear sparse impulse features due to variable speed conditions and redundant noise interference leads to challenges in diagnosing variable speed faults.Therefore,an improved spectral amplitude modulation(ISAM)based on sparse feature adaptive convolution(SFAC)is proposed to enhance the fault features under variable speed conditions.First,an optimal bi-damped wavelet construction method is proposed to learn signal impulse features,which selects the optimal bi-damped wavelet parameters with correlation criterion and particle swarm optimization.Second,a convolutional basis pursuit denoising model based on an optimal bi-damped wavelet is proposed for resolving sparse impulses.A model regularization parameter selection method based on weighted fault characteristic amplitude ratio assistance is proposed.Then,an ISAM method based on kurtosis threshold is proposed to further enhance the fault information of sparse signal.Finally,the type of variable speed faults is determined by order spectrum analysis.Various experimental results,such as spectral amplitude modulation and Morlet wavelet matching,verify the effectiveness and advantages of the ISAM-SFAC method.
文摘The accurate identification and diagnosis of chemical process faults are crucial for ensuring the safe and stable operation of production plants.The current hot topic in industrial process fault diagnosis research is data-driven methods.Most of the existing fault diagnosis methods focus on a single shallow or deep learning model.This paper proposes a novel hybrid fault diagnosis method to fully utilize various features to improve the accuracy of fault diagnosis.Furthermore,the method addresses the issue of incomplete data,which has been largely overlooked in the majority of existing research.Firstly,the variable data is effectively fitted using orthogonal non-negative matrix tri-factorization,and the missing data in the matrix is solved to construct a complete production condition relationship.Next,the support vector machine model and the deep residual contraction network model are trained in parallel to prediagnose process faults by mining linear and non-linear interaction features.Finally,a novel mapping relationship is established between the result and model levels using the multi-layer perceptron algorithm to complete the final diagnosis and evaluation of the fault.To demonstrate the effectiveness of the proposed method,we conducted extensive comparative experiments on the Tennessee Eastman dataset and the ethylene plant cracking unit dataset.The experimental results show that the method has advantages in different evaluation metrics.
文摘In real industrial scenarios, equipment cannot be operated in a faulty state for a long time, resulting in a very limited number of available fault samples, and the method of data augmentation using generative adversarial networks for smallsample data has achieved a wide range of applications. However, the current generative adversarial networks applied in industrial processes do not impose realistic physical constraints on the generation of data, resulting in the generation of data that do not have realistic physical consistency. To address this problem, this paper proposes a physical consistency-based WGAN, designs a loss function containing physical constraints for industrial processes, and validates the effectiveness of the method using a common dataset in the field of industrial process fault diagnosis. The experimental results show that the proposed method not only makes the generated data consistent with the physical constraints of the industrial process, but also has better fault diagnosis performance than the existing GAN-based methods.
基金supported in part by the National Key R&D Program of China Grant 2022YFB4602200.
文摘With the intelligent upgrading of manufacturing equipment,achieving high-precision and efficient fault diagnosis is essential to enhance equipment stability and increase productivity.Online monitoring and fault diagnosis technology play a critical role in improving the stability of metal additive manufacturing equipment.However,the limited proportion of fault data during operation challenges the accuracy and efficiency of multi-classification models due to excessive redundant data.A multi-sensor and principal component analysis(PCA)and support vector machine(SVM)asymptotic classification(PCSV)for additive manufacturing fault diagnosis method is proposed,and it divides the fault diagnosis into two steps.In the first step,real-time data are evaluated using the T2 and Q statistical parameters of the PCAmodel to identify potential faults while filtering non-fault data,thereby reducing redundancy and enhancing real-time efficiency.In the second step,the identified fault data are input into the SVM model for precise multi-class classification of fault categories.The PCSV method advances the field by significantly improving diagnostic accuracy and efficiency,achieving an accuracy of 99%,a diagnosis time of 0.65 s,and a training time of 503 s.The experimental results demonstrate the sophistication of the PCSV method for high-precision and high-efficiency fault diagnosis of small fault samples.
基金funded by the Jilin Provincial Department of Science and Technology,grant number 20230101208JC。
文摘High-speed train engine rolling bearings play a crucial role in maintaining engine health and minimizing operational losses during train operation.To solve the problems of low accuracy of the diagnostic model and unstable model due to the influence of noise during fault detection,a rolling bearing fault diagnosis model based on cross-attention fusion of WDCNN and BILSTM is proposed.The first layer of the wide convolutional kernel deep convolutional neural network(WDCNN)is used to extract the local features of the signal and suppress the highfrequency noise.A Bidirectional Long Short-Term Memory Network(BILSTM)is used to obtain global time series features of the signal.Cross-attention combines the WDCNN layer and the BILSTM layer so that the model can recognize more comprehensive feature information of the signal.Meanwhile,to improve the accuracy,Variable Modal Decomposition(VMD)is used to decompose the signals and filter and reconstruct the signals using envelope entropy and kurtosis,which enables the pre-processing of the signals so that the data input to the neural network contains richer feature information.The feasibility of the model is tested and experimentally validated using publicly available datasets.The experimental results show that the accuracy of themodel proposed in this paper is significantly improved compared to the traditional WDCNN,BILSTM,and WDCNN-BILSTM models.
基金the National Key Research and Development Program of China(Grant No.2022YFB3302700)the National Natural Science Foundation of China(Grant No.52375486)the Shanghai Rising-Star Program(Grant No.22QB1404200).
文摘In intelligentmanufacturing processes such as aerospace production,computer numerical control(CNC)machine tools require real-time optimization of process parameters to meet precision machining demands.These dynamic operating conditions increase the risk of fatigue damage in CNC machine tool bearings,highlighting the urgent demand for rapid and accurate fault diagnosis methods that can maintain production efficiency and extend equipment uptime.However,varying conditions induce feature distribution shifts,and scarce fault samples limitmodel generalization.Therefore,this paper proposes a causal-Transformer-based meta-learning(CTML)method for bearing fault diagnosis in CNC machine tools,comprising three core modules:(1)the original bearing signal is transformed into a multi-scale time-frequency feature space using continuous wavelet transform;(2)a causal-Transformer architecture is designed to achieve feature extraction and fault classification based on the physical causal law of fault propagation;(3)the above mechanisms are integrated into a model-agnostic meta-learning(MAML)framework to achieve rapid cross-condition adaptation through an adaptive gradient pruning strategy.Experimental results using the multiple bearing dataset show that under few-shot cross-condition scenarios(3-way 1-shot and 3-way 5-shot),the proposed CTML outperforms benchmark models(e.g.,Transformer,domain adversarial neural networks(DANN),and MAML)in terms of classification accuracy and sensitivity to operating conditions,while maintaining a moderate level of model complexity.
基金supported by the National Natural Science Foundation of China(No.52505107)Yunnan Fundamental Research Projects(NO.202501CF070179).
文摘As industrial systems become increasingly complex,the significant research interest has been devoted to intelligent fault diagnosis approaches leveraging deep learning.However,existing methods still face two critical challenges in practical applications:1)the extracted features often fail to maintain robustness in nonstationary conditions;2)deep neural networks generally exhibit a black box nature,offering limited interpretability in their feature extraction process.To solve the above issues,an interpretable wavelet Kolmogorov-Arnold convolutional Long Short-Term Memory(WKAConvLSTM)is proposed,which mainly consists of two key components:1)a wavelet Kolmogorov-Arnold kernel(WKAK)with learnable scale and translation parameters is designed and then embedded into convolutional layers to enable the extracted spatial features interpretable;2)a multi-head attention-enhanced Long Short-Term Memory(MHA-LSTM)is proposed to effectively capture crucial temporal dependencies in sequential data.In order to verify its effectiveness,the proposed model is tested on bearing and gearbox datasets under complex conditions,including noise interference,nonstationary operating conditions,and data class imbalance.The experimental results demonstrate that it not only achieves superior diagnostic accuracy compared with advanced baseline models but also enhances the interpretability of the extracted features.
