Intelligent Fault Diagnosis Method Research Articles

Domain generalized open-set intelligent fault diagnosis based on feature disentanglement meta-learning

Abstract Existing domain generalization-based intelligent fault diagnosis methods mainly focus on learning domain-invariant features. However, in practical scenarios, these features are difficult to extract and effectively distinguish from class-related features. Moreover, these methods often assume identical label distributions between the source and target domain, making it challenging to handle scenarios where unknown classes exist in the target domain. To address these issues, this paper proposes a domain generalized open-set intelligent fault diagnosis method based on feature disentanglement meta-learning. A binary mask feature disentanglement module is constructed to overcome the information loss caused by feature reconstruction, enabling the separation of domain-specific and class-related features. Additionally, a meta-purification loss function is defined, incorporating a correlation loss term to remove impurity features from the class-related features, and further purifying class information through feature combination pairing. The method is trained on multiple source domains using a meta-learning strategy and generalized to target domains with unknown classes. The method is utilized for bearing fault diagnosis, designing multi-task experimental scenarios under different rotational speeds, and compared with existing domain generalization methods. Experimental results show that the proposed method exhibits excellent generalization ability and effectively addresses the issue of domain generalized open-set fault diagnosis.

A novel transformer-based few-shot learning method for intelligent fault diagnosis with noisy labels under varying working conditions

Recent years have witnessed the success of Few-shot Learning (FSL) methods in equipment reliability enhancement and fault diagnosis, by virtue of learning from limited data and adapting to new operating conditions. However, due to sensor bias, manual collection, and mislabeling, label noise is inevitably introduced into the dataset, which further reduces the quality of supervised information contained in the few-shot dataset, posing significant challenges for accurate fault diagnosis. In this paper, the problem of Few-shot Fault Diagnosis with Noisy Labels (FFDNL) is studied for the first time, and a novel method named Enhanced Transformer with Asymmetric Loss Function (ETALF) is proposed. ETALF leverages the self-attention mechanism of the transformer to dynamically measure the similarity between fault samples in the support set to enhance the model's robustness against label noise, then naturally aggregates the similar samples into corresponding correct prototypes. Furthermore, an asymmetric loss function is designed, which adaptively assigns the model with larger penalties for incorrect category predictions and smaller penalties for correct category predictions, thereby enhancing fault diagnostic performance through inherent asymmetry. Comprehensive experiments are conducted on two benchmark datasets, and the compared results with representative approaches validate the effectiveness of our proposed ETALF in performing intelligent fault diagnosis using limited and noise-labeled data under varying working conditions, which achieves accuracies of 97.77% and 95.78% with 0.2 noisy-level labels during meta-training and meta-testing on the CWRU and KAIST datasets, respectively.

Digital twin-assisted intelligent fault diagnosis for bearings

Abstract Data-driven intelligent fault diagnosis methods generally require a large amount of labeled data and considerable time to train network models. However, obtaining sufficient labeled data in practical industrial scenarios has always been a challenge, which hinders the practical application of data-driven methods. A digital twin (DT) model of rolling bearings can generate labeled training dataset for various bearing faults, supplementing the limited measured data. This paper proposes a novel DT-assisted approach to address the issue of limited measured data for bearing fault diagnosis. First, a dynamic model of bearing with damages is introduced to generate simulated bearing acceleration vibration signals. A DT model is constructed in Simulink, where the model parameters are updated based on the actual system behavior. Second, the structural parameters of the DT model are adaptively updated using least squares method with the measured data. Third, a Vision Transformer (ViT) -based network, integrated with short-time Fourier transform, is developed to achieve accurate fault diagnosis. By applying short-time Fourier transform at the input end of the ViT network, the model effectively extracts additional information from the vibration signals. Pre-training the network with an extensive dataset from miscellaneous tasks enables the acquisition of pre-trained weights, which are subsequently transferred to the bearing fault diagnosis task. Experiments results verify that the proposed approach can achieve higher diagnostic accuracy and better stability.

Refined composite multiscale slope entropy and its application in rolling bearing fault diagnosis

Rolling bearing is the key component of rotating machinery, and its vibration signal usually exhibits nonlinear and nonstationary characteristics when failure occurs. Multiscale permutation entropy (MPE) is an effective nonlinear dynamics analysis tool, which has been successfully applied to rolling bearing fault diagnosis in recent years. However, MPE ignores the deep amplitude information when measuring the complexity of the time series and the original multiscale coarse-graining is insufficient, which requires further research and improvement. In order to protect the integrity of information structure, a novel nonlinear dynamic analysis method termed refined composite multiscale slope entropy (RCMSlE) is proposed in this paper, which introduced the concept of refined composite to further boost the performance of MPE in nonlinear dynamical complexity analysis. Furthermore, RCMSlE utilizes a novel symbolic representation that takes full account of mode and amplitude information, which overcomes the weaknesses in describing the complexity and regularity of bearing signals. Based on this, a GWO-SVM multi-classifier is introduced to fulfill mode recognition, and then a new intelligent fault diagnosis method for rolling bearing based on RCMSlE and GWO-SVM is proposed. The experimental results show that the proposed method can not only accurately identify different fault types and degrees of rolling bearing, but also has a short computation time and better performance than other comparative methods.

Intelligent Fault Diagnosis Method for Transformer Driven by Multiple Vibration Data

Abstract Early monitoring and early warning of transformer failure are crucial to ensure the safe and dependable functioning of the power system, as transformers are essential equipment within the system. On multivariate vibration data, this work presents a sophisticated approach for diagnosing faults in transformers which integrates entropy model and machine learning. Firstly, a new coarse-grained method is introduced into the improved multiscale fuzzy entropy to improve the disadvantage of the traditional entropy model with large entropy fluctuation under high-scale factors. Furthermore, the features of transformer multivariate vibration signals are extracted by the entropy model. Finally, the extreme learning machine is utilized to achieve efficient detection of transformer defects. This method provides a useful method reference for fault diagnosis of power equipment with multi-vibration signal, and has good reference value.

Intelligent Fault Diagnosis Method Based on Cross-Device Secondary Transfer Learning of Efficient Gated Recurrent Unit Network.

In response to the issues of low model recognition accuracy and weak generalization in mechanical equipment fault diagnosis due to scarce data, this paper proposes an innovative solution, a cross-device secondary transfer-learning method based on EGRUN (efficient gated recurrent unit network). This method utilizes continuous wavelet transform (CWT) to transform source domain data into images. The EGRUN model is initially trained, and shallow layer weights are frozen. Subsequently, random overlapping sampling is applied to the target domain data to enhance data and perform secondary transfer learning. The experimental results demonstrate that this method not only significantly improves the model's ability to learn fault features but also enhances its classification accuracy and generalization performance. Compared to current state-of-the-art algorithms, the model proposed in this study shows faster convergence speed, higher diagnostic accuracy, and superior robustness and generalization, providing an effective approach to address the challenges arising from scarce data and varying operating conditions in practical engineering scenarios.

Explainable Graph Wavelet Denoising Network for Intelligent Fault Diagnosis.

Deep learning (DL)-based intelligent fault diagnosis methods have greatly promoted the development of the field of fault diagnosis due to their powerful feature extraction ability for handling massive monitoring data. However, most of them still suffer from the following three limitations. First, many existing DL-based intelligent diagnosis methods cannot extract proper discriminative features from signals with strong noise. Second, the interactions or relationships between signals are ignored, while they mainly focus on extracting temporal features from the signal. Third, owing to their black-box nature, the learned features lack interpretability, which hinders their application in the industry. To tackle these issues, an explainable graph wavelet denoising network (GWDN) is proposed to achieve intelligent fault diagnosis under noisy working conditions in this article. In GWDN, the collected signals are first transformed into graph-structured data to consider the interactions among signals. Then, the graph wavelet denoising convolution (GWDConv) is proposed based on the discrete graph wavelet frame, which allows GWDN to achieve multiscale feature extraction for graph-structured data and realize signal denoising. Extensive experiments are implemented to verify the efficacy of the proposed GWDN, and the experimental results show that GWDN can achieve state-of-the-art performance among the comparison methods. Besides, by using the square envelope spectrum to analyze the extracted features of GWDConv, we find that it can well retain the fault-related components of the signal and realize signal denoising, which further proves that GWDN is explainable.

A novel adaptive gramian angle field based intelligent fault diagnosis for motor rolling bearings

Abstract The Gramian Angle Field (GAF) can encode one-dimensional vibration signals into two-dimensional feature maps containing time correlation information. However, the feature representation ability of traditional GAF-encoded images is limited, making it challenging to further improve fault diagnosis accuracy. To address these issues, an AGAF-CNN intelligent fault diagnosis method is proposed in this paper. In addition to traditional GAF encoding, an adaptive adjustment parameter is introduced that automatically determines its value based on the dynamic distribution characteristics of the input data. This ensures that the resulting feature map after two-dimensional encoding contains optimal fault discriminant features. By leveraging CNN’s capability to process image data, the proposed method extracts deep-level feature representations from the vibration signal feature map and performs accurate diagnosis. The approach is validated using a rolling bearing dataset from Case Western Reserve University in the United States, and superior diagnostic accuracy is demonstrated compared to other vibration signal coding methods combined with CNN-based fault diagnosis methods. The theoretical and practical advantages of AGAF feature coding are explained comprehensively.

An intelligent fault diagnosis method for rolling bearing using motor stator current signals

Abstract In the diagnosis of rolling bearing faults, the Motor Current Signature Analysis (MCSA) method offers advantages such as low cost, simplicity, and convenience compared to using vibration signals, temperature information, and other diagnostic objects. However, owing to the interference of high-frequency noise, power frequency, and its harmonics in current signals, which can severely affect the accuracy of bearing fault diagnosis, it is extremely challenging to use the original current signals during bearing faults directly for diagnostic purposes. Therefore, this paper proposes an intelligent fault diagnosis method based on the feature reconstruction (FR) method and convolutional neural networks (CNN). This method can achieve high-precision fault diagnosis using single-phase stator current signals from motors as the diagnostic objects. First, the FR method effectively removes the impact of high-frequency noise, supply frequency, and its harmonics from the current signals, while also highlighting subtle fault feature signals to a certain extent. Second, a CNN suitable for learning the characteristics of the current signals was constructed. Through feature extraction, learning, and classification of the current signal samples processed by the FR method, a diagnostic method with a high classification accuracy was obtained. Visualization techniques were used to present the final diagnosis results intuitively. The experimental results demonstrated the highest diagnostic accuracy and average diagnostic accuracy of the proposed method in diagnosing rolling bearing fault types, with an average diagnostic accuracy of approximately 99% for actual faulty bearing samples.

A novel intelligent fault diagnosis method for commercial vehicle pneumatic braking system

The application of convolutional neural network (CNN) has greatly broaden the application range of intelligent fault diagnosis, which is beneficial to the stability of industrial production. However, traditional CNN based fault diagnosis methods cannot capture the global features. To address the problem, this paper proposed a method called PSO-Conformer to extract features integrating global and local information. First, convolutional layers are uesd for local feature extraction, and then using Encode module of Transformer to extract global features. The diagnostic performance of the model can be significantly improved and the model hyperparameters are optimized using the PSO algorithm. The proposed method is applied to the fault diagnosis of pneumatic brake systems of commercial vehicles and compared with several methods based on deep learning. And this paper use the t-Distributed Stochastic Neighbor Embdedding (TSNE) to visualize the output features of models in two dimensional plane and four evaluation indexes based on confusion matrix are used to evaluate the model. The results show that the diagnostic performance of the proposed method is better than the existing method.

Transformer-based intelligent fault diagnosis methods of mechanical equipment: A survey

Abstract Transformer is extensively employed in natural language processing, and computer vision (CV), with the self-attention structure. Due to its outstanding long-range dependency modeling and parallel computing capability, some leading researchers have recently attempted to apply Transformer to intelligent fault diagnosis tasks for mechanical equipment, and have achieved remarkable results. Physical phenomena such as changes in vibration, sound, and heat play a crucial role in the research of mechanical equipment fault diagnosis, which directly reflects the operational status and potential faults of mechanical equipment. Currently, intelligent fault diagnosis of mechanical equipment based on monitoring signals such as vibration, sound, and temperature using Transformer-based models remains a popular research topic. While some review literature has explored the related principles and application scenarios of Transformer, there is still a lack of research on its application in intelligent fault diagnosis tasks for mechanical equipment. Therefore, this work begins by examining the current research status of fault diagnosis methods for mechanical equipment. This study first provides a brief overview of the development history of Transformer, outlines its basic structure and principles, and analyzes the characteristics and advantages of its model structure. Next it focuses on three model variants of Transformer that have generated a significant impact in the field of CV. Following that, the research progress and current challenges of Transformer-based intelligent fault diagnosis methods for mechanical equipment are discussed. Finally, the future development direction of Transformer in the field of mechanical equipment fault diagnosis is proposed.

A lightweight dynamic dual-damped wavelet-based convolutional neural network for interpretable bearing fault diagnosis

Wavelet-based convolutional neural networks (CNNS) have attracted widespread attention because they can improve the interpretability of intelligent fault diagnosis methods. However, the fault feature representation capability of typical wavelet-based convolution kernel frameworks must be strengthened to improve the diagnostic accuracy of complex faults. In the meantime, the large number of network parameters leads to high computational costs. To address these issues, a lightweight wavelet-based dynamic CNN, which comprises a dual-damping wavelet-based dynamic CNN (DWDC) block and a discrete wavelet transformation (DWT) enhancement (DWTE) block, is put forward. In the DWDC block, a wavelet convolution layer is initially designed, where a dual-damping wavelet is used as the kernel function to improve the match of the convolution kernel with fault impulses. Subsequently, a dynamic convolution layer with multiple parallel small-size convolutional kernels is designed to screen the fault features instead of a multilayer network structure, thereby greatly reducing the number of network parameters. Finally, the DWTE block is constructed by combining the DWT and residual dense block, and it can mine more fault information from the previously extracted features. The experiments on the variable speed bearing dataset, locomotive bearing dataset with constant speed and the Case Western Reserve University dataset prove that the proposed approach outperforms five classical CNN models and six advanced wavelet-based CNN models. In addition, it can effectively solve the issue of data imbalance because of its powerful feature extraction capability.

A high-accuracy intelligent fault diagnosis method for aero-engine bearings with limited samples

As a crucial component supporting aero-engine functionality, effective fault diagnosis of bearings is essential to ensure the engine's reliability and sustained airworthiness. However, practical limitations prevail due to the scarcity of aero-engine bearing fault data, hampering the implementation of intelligent diagnosis techniques. This paper presents a specialized method for aero-engine bearing fault diagnosis under conditions of limited sample availability. Initially, the proposed method employs the refined composite multiscale phase entropy (RCMPhE) to extract entropy features capable of characterizing the transient signal dynamics of aero-engine bearings. Based on the signal amplitude information, the composite multiscale decomposition sequence is formulated, followed by the creation of scatter diagrams for each sub-sequence. These diagrams are partitioned into segments, enabling individualized probability distribution computation within each sector, culminating in refined entropy value operations. Thus, the RCMPhE addresses issues prevalent in existing entropy theories such as deviation and instability. Subsequently, the bonobo optimization support vector machine is introduced to establish a mapping correlation between entropy domain features and fault types, enhancing its fault identification capabilities in aero-engine bearings. Experimental validation conducted on drivetrain system bearing data, actual aero-engine bearing data, and actual aerospace bearing data demonstrate remarkable fault diagnosis accuracy rates of 99.83%, 100%, and 100%, respectively, with merely 5 training samples per state. Additionally, when compared to the existing eight fault diagnosis methods, the proposed method demonstrates an enhanced recognition accuracy by up to 28.97%. This substantiates its effectiveness and potential in addressing small sample limitations in aero-engine bearing fault diagnosis.

A Fault Diagnosis Method for Key Components of the CNC Machine Feed System Based on the DoubleEnsemble–LightGBM Model

To solve the problem of fault diagnosis for the key components of the CNC machine feed system under the condition of variable speed conditions, an intelligent fault diagnosis method based on multi-domain feature extraction and an ensemble learning model is proposed in this study. First, various monitoring signals including vibration signals, noise signals, and current signals are collected. Then, the monitoring signals are preprocessed and the time domain, frequency domain, and time–frequency domain feature indices are extracted to construct a multi-dimensional mixed-domain feature set. Finally, the feature set is entered into the constructed DoubleEnsemble–LightGBM model to realize the fault diagnosis of the key components of the feed system. The experimental results show that the model can achieve good diagnosis results under different working conditions for both the widely used dataset and the feed system test bench dataset, and the average overall accuracy is 91.07% and 98.06%, respectively. Compared with XGBoost and other advanced ensemble learning models, this method demonstrates better accuracy. Therefore, the proposed method provides technical support for the stable operation and intelligence of CNC machines.

Intelligent fault diagnosis methods for hydraulic components based on information fusion: review and prospects

Abstract Hydraulic component faults have the characteristics of nonlinear time-varying signal, strong concealment, and difficult feature extraction, etc. Timely and accurately fault diagnosis of hydraulic components is helpful to curb economic losses and accidents, so researches have carried out a lot of research on hydraulic components. Information fusion technology can combine multi-source data from multiple dimensions to mine fault data characteristics, which effectively improves the accuracy and reliability of fault diagnosis results. However, there is currently a lack of a comprehensive and systematic review in this domain. Therefore, in this paper, the hydraulic components information fusion fault diagnosis technologies are summarized and analyzed, including the main process information fusion fault diagnosis and the research status of information fusion fault diagnosis of hydraulic system. The methods and techniques involved in the fusion process, data source and fusion method of fault diagnosis of hydraulic components information fusion are described and summarized. The problems of information fusion in fault diagnosis of hydraulic components are analyzed, the solutions are discussed, and the research ideas of improving information fusion fault diagnosis are put forward. Finally, digital twin technology is introduced, and the advantages and research status of intelligent fault diagnosis based on digital twin are summarized. On this basis, the intelligent fault diagnosis of hydraulic components based on information fusion is summarized, and the challenges and future research ideas of applying information fusion and digital twin to intelligent fault diagnosis of hydraulic components are put forward and analyzed comprehensively.

A gray texture image data-driven intelligent fault diagnosis method of induction motor rotor-bearing system under variable load conditions

Induction motors often operate in variable conditions, and the data distribution of diverse conditions is different. To solve the issue of low accuracy of diagnosis methods caused by large differences in data distribution, an intelligent fault diagnosis method of induction motor rotor-bearing system is proposed. The method combines convolutional neural network with adaptive batch normalization, and the gray texture images transformed from vibration signals are used as the input samples. A total of thirteen conditions including constant and time-varying loads are designed to verify the performance of the method. The average accuracy of the model for thirteen conditions of test set reaches 98.7 %, and the average accuracy for eight unknown conditions of test set is 99.0 %. The proposed method can extract features that are not affected by the variable load conditions, facilitate the transfer from no-load to on-load and known to unknown conditions.

Intelligent fault diagnosis of photovoltaic systems based on deep digital twin

The energy loss and substantial costs associated with faults in photovoltaic (PV) systems impose significant limitations on their efficiency and reliability. Addressing current issues in PV fault diagnosis such as the lack of typical fault data, imbalanced data distribution, and poor diagnostic performance, this paper proposes an intelligent fault diagnosis method for PV systems, deep digital twins (DDT) with information gain stacking sparse autoencoders (IGSSAEs). Initially, the method designs a novel DDT modeling framework tailored to actual PV system specifications. This framework utilizes a mechanism simulation model to generate typical data under various states. Simultaneously, a deep data model is constructed to learn the distribution characteristics of the mechanism model and complete data diversification, achieving the fusion and complementation of data from both models. Subsequently, a diagnostic network using IGSSAE is introduced. This network utilizes information gain ratio to assess feature classification contributions, enabling automatic feature selection. Based on the input features, a stacked sparse autoencoder fault classification network is designed, incorporating multi-level feature compression to enhance the model’s stability and diagnostic accuracy. Finally, a case study is conducted using a 250 kW grid-connected PV system, thoroughly validating the method’s effectiveness with a diagnostic accuracy of 98.4%.

Bearing Fault Diagnosis Based on Parameter-Optimized Variational Mode Extraction and an Improved One-Dimensional Convolutional Neural Network

When faults occur in rolling bearings, vibration signals exhibit sensitivity to periodic impact components, susceptibility to complex background noise, and non-stationary and nonlinear characteristics. Consequently, using traditional signal processing methods to effectively identify bearing faults presents significant challenges. To facilitate the accurate fault diagnosis of bearings in noisy conditions, we propose an intelligent fault diagnosis method using the Archimedes optimization algorithm (AOA), coupled with a one-dimensional multi-scale residual convolutional neural network (1D-MRCNN), to optimize the variational mode extraction (VME) parameters. First, we introduce a weighted correlated kurtosis (WCK) indicator, formulated using the correlation coefficient and correlated kurtosis as the objective function, to optimize the VME’s center frequency ω and penalty factor α, enabling targeted signal extraction. Second, deep learning techniques are employed to construct the 1D-MRCNN. The neural network then processes the extracted signal for feature extraction and automated fault-type identification. Our simulation results show that the WCK objective function effectively isolates impact components under fault conditions, and our experimental validation confirms that the proposed method accurately identifies diverse fault types across multiple noise levels.

Intelligent fault diagnosis based on improved convolutional neural network for small sample and imbalanced bearing data

The failure of bearings is a prevalent cause of machinery breakdowns. The rapid development of intelligent technology has significantly promoted the use of deep learning techniques for identifying problems with machinery bearings. To achieve accuracy, deep learning-based diagnostic techniques require a substantial and uniformly diversified amount of training data. However, obtaining artificial labels for bearing fault data poses a major obstacle in engineering practice. This paper proposes an intelligent fault diagnosis method for bearings based on an improved convolutional neural network (CNN) to address the challenges of small training data and imbalanced distribution. To enable intelligent diagnosis of bearings with a small sample and imbalanced distribution, a clustering loss layer is introduced into the CNN. Furthermore, we optimize the parameters of the CNN by utilizing back-propagation of both the clustering loss function and the cross-entropy loss function. This optimization process improves the accuracy of fault diagnosis. Finally, the proposed method is applied to diagnose bearing faults and analyze the simulation results. The simulation results demonstrate the effectiveness of the method in handling small data volumes and imbalanced data distributions, as well as its strong generalization performance.

A novel subdomain adaptive intelligent fault diagnosis method based on multiscale adaptive residual networks

Traditional fault diagnosis methods may not capture key information during feature extraction due to the large distribution difference under different working conditions, which can result in poor accuracy of the diagnostic model. To address this issue, a subdomain adaptive bearing fault identification method guided by the local maximal mean difference (LMMD) under the multiscale adaptive residual network is proposed in this paper. The bearing vibration signals are preprocessed by wavelet convolution and wide convolution to generate initial features. Then, the multi-scale adaptive residual network is used to adjust the feature weights of different scales and extract richer feature information. To reduce the intra-class distribution difference, the LMMD is employed. Additionally, local interclass maximum mean difference (LIMMD) is used to increase the inter-class difference, preventing misclassification of samples from different classes due to their close proximity and achieving sub-domain distribution alignment. The fault diagnosis performance of the domain distance metric model guided by LMMD and LIMMD under the multiscale adaptive residual network is verified through two different bearing model validation experiments.