Rolling Bearing Fault Diagnosis Research Articles

FDS-MOMEDA: Optimization-Blind Deconvolution in Finite High-Dimensional Spaces for Extracting Pulse Signal in Rolling Bearing Fault Diagnosis

Abstract Rolling bearing fault diagnosis is crucial for ensuring the safe and reliable operation of mechanical equipment. Detecting faults directly from measurement signals is challenging due to severe noise and interference. Blind deconvolution, as a preferred method, effectively recovers periodic pulses from the measured vibration signals of faulty bearings. This study introduces a simulated annealing-based blind deconvolution approach to enhance the pulse signal components reflecting faults in vibration signals measured on rolling bearings. This method iteratively searches for the optimal coordinates in a high-dimensional orthogonal optimization space, where the optimal coordinates reflect the combination of the inverse filter coefficients. Compared to the generalized spherical optimization space used in the “Optimization-Blind Deconvolution” method in previous works, the proposed finite high-dimensional optimization space helps overcome the problem of inverse filter coefficient convergence, allowing for the design of inverse filters without limit of its shape. To better accommodate the cyclostationarity characteristics of bearing signal measured in reality, the proposed method employs a target vector that allows for uncertainty in pulse occurrence moments, thus overcomes challenges introduced by pseudo-periodic phenomena resulting from bearing slippage. Numerical simulations and experimental results on real bearing vibration signals confirm that the proposed method can design more flexible filters to enhance pulse-like patterns in signals, effectively utilize limited filter resources. Its capacity to tolerate inaccurate fault period estimates, high background noise, and pulse randomness enables it to effectively address vibration measurement signals in real-world scenarios.

A Novel Semi-Supervised Learning Rolling Bearing Fault Diagnosis Method Based on SNNGAN

Abstract n practical industrial environments, rotating machinery typically operates under normal conditions. As a result, the signals collected are primarily normal signals. This imbalance in the sample data diminishes the effectiveness of fault diagnosis. To address this issue, this paper produces a novel semi-supervised fault diagnosis approach based on a Siamese neural network combined with a generative adversarial network (SNNGAN) to enhance classification accuracy. Firstly, vibration signals collected are subjected to continuous wavelet transformation to obtain time-frequency representations, which are utilized for pre-training convolutional encoders in the generator and discriminator. Subsequently, a cosine similarity algorithm is employed to ensure the quality of generated samples. For generated data, set a similarity threshold. Those surpassing the threshold are assigned their corresponding labels and added to the original sample set. Otherwise, those falling below the threshold are transformed back into vibration vectors through an inverse transform and then serve as input to create new samples. Finally, fault diagnosis experiments are conducted on the newly balanced data set. In four imbalanced data experiments, the results demonstrate that SNNGAN outperforms other methods in average accuracy, G-mean, and F1 score, with average accuracy values of 0.919, 0.948, 0.927, and 0.953 for the respective datasets. Therefore, SNNGAN exhibits outstanding fault diagnosis performance under conditions of data imbalance.

Analysis of hot spots and trends in rolling bearing fault diagnosis research based on scientific knowledge mapping

As a key component of mechanical equipment, real-time monitoring and diagnosis of rolling bearings play a critical role in ensuring the stable operation of equipment and the safety of operators. In order to present the current status and trends of fault diagnosis research on rolling bearings more intuitively, the scientific knowledge mapping was used to visualize and analyze the relevant literature in the article. The results show that the number of publications in this area of research has grown significantly in recent years, with China, India, the United States, and England having contributed significantly. The journals such as MECHANICAL SYSTEMS AND SIGNAL PROCESSING, MEASUREMENT, and JOURNAL OF SOUND AND VIBRATION have played an important role in disseminating cutting-edge technologies in this field. In addition, the exploration of modern methods based on data-driven and artificial intelligence, as well as their application to real-world problems, are gradually becoming the focus of research. Through summarising and analysing, the application of modern data processing techniques, the development of more efficient and practical intelligent fault diagnosis techniques, and the close integration of laboratory research and practical applications will become future research trends.

Research on deep learning rolling bearing fault diagnosis driven by high-fidelity digital twins

Research on deep learning rolling bearing fault diagnosis driven by high-fidelity digital twins

Blind cyclostationary fault feature extraction in rolling bearings: a dual adaptive filtering approach

Extracting cyclostationary features from vibration signals is one of the most effective approaches in bearing fault diagnosis. However, current methods require prior knowledge of cycle-frequencies or other statistical information, which constrains their applicability across various scenarios. In this paper, we introduce a novel dual adaptive filtering method, incorporating cycle-frequency estimation to solve the existing problem. The method firstly employs an adaptive line enhancer (ALE) to isolate the first-order cyclostationary signal, thereby the cycle-frequencies can be effectively detected using an exhaustive estimation technique. Subsequently, an adaptive frequency-shift (FRESH) filter is further applied to extract the second-order cyclostationary features from the residual components. The proposed method successfully overcomes the challenge of separating cyclostationary signals without prior knowledge and can be tailored to real-time application scenarios. Besides, the approach distinguishes between the two cyclostationary signal types, effectively resolving any aliasing concerns inherent in their statistical characteristics. The effectiveness of the method is verified through simulation, experiments, and engineering data analysis. It is demonstrated that the method significantly enhances diagnostic accuracy and is more suitable for early fault diagnosis of rolling bearings by estimating spectral coherence on the extracted signals.

The double-feature extraction method based on slope entropy and symbolic dynamic entropy for the fault diagnosis of rolling bearing

The double-feature extraction method based on slope entropy and symbolic dynamic entropy for the fault diagnosis of rolling bearing

A rolling bearing fault diagnosis method based on interactive generative feature space oversampling-based autoencoder under imbalanced data

With the rapid development of railroads and the yearly increase in the scale of operation, the safe operation and maintenance of rail trains have become particularly important. Among them, deep learning-based bearing fault diagnosis methods have attracted more and more attention in rail train operation and maintenance. However, rail trains usually operate normally. Collecting complete fault data for deep learning model training is often difficult. Such scenarios with a large difference between the number of normal data and fault data usually affect the performance of fault diagnosis models. Here, an interactive generative feature space oversampling-based autoencoder (IGFSO-AE) is proposed to realize fault sample generation under imbalanced data. First, the original vibration signal is converted into a semantically stable amplitude–frequency signal by fast Fourier transform and input into the autoencoder; second, the order of the hidden layer space features of the autoencoder is randomly exchanged, and the interactive sample generation learning strategy trains the autoencoder; then, interpolation oversampling is used to interpolate samples in the hidden layer space where the Euclidean distance between samples is large, and is input into the decoder, the generated samples are mixed with the original samples to form a new training set, which is used to train the intelligent fault diagnosis model and output the diagnosis results. Finally, the performance of the proposed method is evaluated using the publicly available bearing dataset and the bogie-bearing fault simulation bench in our lab. The experimental results show that IGFSO-AE can generate diverse samples with incremental information and exhibits robustness and superiority in different imbalanced proportions of data.

A short time series rolling bearing fault diagnosis method based on FMTF-CNN

Abstract The signal characteristics are extracted directly from the convolutional level when the Convolutional Neural Network (CNN) is used as a fault diagnosis method in most instances. Some scholars have proposed to use the Markov Transition Field (MTF) to extract the signal characteristics before convolution. However, for time-domain signals, the fault characteristics extraction is difficult, and the training process of the neural network parameters is slow. Therefore, in this paper, based on Fast Fourier Transform (FFT) and MTF algorithm, the Fourier Markov Transition Field (FMTF) characteristics extraction method in frequency domain is proposed, and a large number of experiments are carried on the public bearing data set of Jiangnan University. The final verification shows that the FMTF-CNN method has higher accuracy, faster training process and more accurate characteristics extraction than the traditional MTF-CNN diagnosis method.

Dual-path multi-scale attention residual network for fault diagnosis of rolling bearings under complex operating conditions

Rolling bearing faults inevitably occur during the long-term continuous operation of rotating machinery. Therefore, fault diagnosis is greatly important for ensuring the normal and safe operation of rolling bearings. However, the complexity and diversity of working conditions of rolling bearings present a significant challenge in extracting fault characteristics accurately, which further affects the ultimate fault diagnosis results. In this article, we propose a new model, called dual-path multi-scale attention residual network (DPMARN), for diagnosing bearing faults under complex operating conditions. DPMARN can effectively capture the feature-feature correlation information at different scales, which is more beneficial for fusing fault features at different scales to improve the model’s performance. The main contributions of this work are summarized as follows: (1) the designed dual-path network model which incorporates parallel multi-scale branches of convolutional kernels and serially connects skip-layer multi-scale branches can integrate both low-frequency and high-frequency information and enhance the multi-scale feature extraction and complex data representation abilities. (2) The squeeze-and-excitation attention mechanism is embedded into the residual blocks to improve the ability of learning feature correlations and utilizing feature information effectively, which is helpful for extracting important fault characteristics. Extensive experiments conducted on two public bearing datasets demonstrate the superior performance of the DPMARN model for addressing the complex fault diagnosis problem. These results indicate that our proposed approach provides an effective solution for fault diagnosis of rolling bearings under complex operating conditions.

Feature selection and interpretability analysis of compound faults in rolling bearings based on the causal feature weighted network

Feature selection is a crucial step in fault diagnosis. When rolling bearings are susceptible to compound faults, causal relationships are hidden within the signal features. Complex network analysis methods provide a tool for causal relationship modeling and feature importance assessment. Existing studies mainly focus on unweighted networks, overlooking the impact of the strength of causal relationships on feature selection. To address this issue, we propose a compound fault feature selection method based on the causal feature weighted network. First, we construct a weighted network using the incremental association Markov blanket discovery algorithm and Pearson correlation coefficient. Then, we quantify the importance of features by treating node strength as a centrality index and rank them to partition the feature subset. Finally, the optimal feature subset is obtained through a neural network with the accuracy of compound fault diagnosis as the threshold. Analysis of public datasets and comparative experiments demonstrate the advantages of our method. Compared to existing research, our method not only effectively reduces the number of optimal feature subsets to 11 but also improves the accuracy of compound fault diagnosis to 95.2%. Furthermore, we employ the SHapley Additive exPlanations to interpret the contribution of each feature in the optimal subset to the accuracy of compound fault diagnosis. This provides reference from both physical and network perspectives to feature selection and compound fault diagnosis in rolling bearings in practical working conditions.

Research on Feature Extraction and Fault Diagnosis Method for Rolling Bearing Vibration Signals Based on Improved FDM-SVD and CYCBD

In mechanical equipment, rolling bearing components are constantly exposed to intricate and diverse environmental conditions, rendering them vulnerable to wear, performance degradation, and potential malfunctions. To precisely extract and discern rolling bearing vibration signals amidst intricate noise interference, this paper introduces a fault feature extraction and diagnosis methodology that seamlessly integrates an improved Fourier decomposition method (FDM), singular value decomposition (SVD), and maximum second-order cyclostationary blind convolution (CYCBD). Initially, the FDM is employed to meticulously decompose the bearing fault signals into numerous signal components. Subsequently, a comprehensive weighted screening criterion is formulated, aiming to strike a balance between multiple indicators, thereby enabling the selective screening and reconstruction of pertinent signal components. Furthermore, SVD and CYCBD techniques are introduced to carry out intricate processing and envelope demodulation analysis of the reconstructed signals. Through rigorous simulation experiments and practical rolling bearing fault diagnosis tests, the method’s noteworthy effectiveness in suppressing noise interference, enhancing fault feature information, and efficiently extracting fault features is unequivocally demonstrated. Furthermore, compared to traditional time–frequency analysis methods such as EMD, EEMD, ITD, and VMD, as well as traditional deconvolution methods like MED, OMEDA, and MCKD, this method exhibits significant advantages, providing an effective solution for diagnosing rolling bearing faults in environments with strong background noise.

Multi-scale deep residual shrinkage networks with a hybrid attention mechanism for rolling bearing fault diagnosis

The fault diagnosis of rolling bearings based on deep networks is hindered by the unexpected noise involved with accessible vibration signals and global information abatement in deepened networks. To combat the degradation, a multi-scale deep residual shrinkage network with a hybrid attention mechanism (MH-DRSN) is proposed in this paper. First, a spatial domain attention mechanism is introduced into the residual shrinkage module to represent the distance dependence of the feature maps. Then, a hybrid attention mechanism considering both the inner-channeled and cross-channeled characteristics is constructed. Through the comprehensive evaluation of the feature map, it provides a soft threshold for the activation function and realizes the feature-map selection adaptively. Second, the dilated convolution with different dilation rates is implemented for multi-scale context information extraction. Through the feature combination of the DRSN and the dilated convolution, the global information of the rolling bearing fault is strengthened and preserved as the fault diagnosis network is deepened. Finally, the performance of the proposed fault-diagnosis model is validated on the dataset from Case Western Reserve University (CWRU). The experimental results show that, compared with common convolution neural networks, the proposed neural diagnosis model provides a higher identification accuracy and better robustness under noise interference.

Rolling bearing fault diagnosis based on multi-source data fusion

In this paper, a fault diagnosis method is proposed based on multi-source data fusion to address the inaccurate results caused by single evidence used for decision-making. First, empirical mode decomposition is performed using sensor data to extract fault features, and a fault feature matrix and a diagnostic matrix are established. Then the deviation vector is defined to obtain the difference between the diagnostic sample and the fault sample, and then the basic probability assignment is obtained for each diagnostic sample. Finally, the Dempster combination rule is used for fusion. The effectiveness and accuracy of this method in fault diagnosis of rolling bearings have been verified through examples of rolling bearings.

Adaptive fast nonlinear blind deconvolution based on nonuniform particle swarm optimization for the rolling bearing fault diagnosis

Although superior fault extraction performance is possessed by fast nonlinear blind deconvolution (FNBD) through the introduction of penalty terms and nonlinear features, its wide application is limited by the complexity and diversity of parameter selection. The fault extraction performance of FNBD is impacted by the contingency of parameter selection. To reduce the prior experience dependence of FNBD and improve the performance of fault extraction, an end-to-end adaptive fast nonlinear blind deconvolution (AFNBD) is proposed. First, the proposed nonuniform particle swarm optimization (NPSO) is employed to assign parameters to be optimized for each particle to construct its Hankel matrix, nonlinear features and objective functions. Secondly, Gaussian fitting is applied to modify the filters. Then, NPSO is utilized to update relevant parameters and the corresponding filter of each particle to explore the optimum filter. Finally, simulations and experiments verify the effectiveness of AFNBD and the results indicate that AFNBD is a powerful tool for incipient fault feature extraction.

A bearing fault diagnosis method based on M-SSCNN and M-LR attention mechanism

Bearing fault diagnosis is vital for mechanical maintenance and fault prediction. It ensures equipment safety, extends lifespan, reduces maintenance costs, and improves production efficiency. Nevertheless, it should be acknowledged that some existing diagnostic methods have achieved high accuracy rates in certain scenarios. However, the challenge lies in their limited generalization capabilities, which can lead to reduced accuracy when applied to diverse or unseen conditions. In this study, we proposed a new bearing fault diagnosis method to address the issue of low accuracy caused by the inadequate generalization of models in the process of rolling bearing fault diagnosis. The method is based on a multi-scale sliding convolution neural network and multi-level residual attention mechanism, the model exhibits high accuracy, strong generalization capability, and lightweight structure. Firstly, the time domain signal of the bearing vibration is converted into a two-dimensional time–frequency map, and the image is pixel-segmented using superpixel segmentation techniques. Next, a multi-scale parallel convolution approach is used to extract features to improve the adaptability and robustness of the model to objects of different sizes and scales. Sliding convolution is used instead of pooling to avoid the problem of feature loss caused by maximum pooling and average pooling. A multi-level attention mechanism is then introduced for all stacked channels to focus on the more important and critical information of the module, and residual connections are added to prevent degradation of the network performance. Finally, the proposed method is passed through the fully connected layer for classification using the Softmax classifier. Experimental verification using public datasets and experimental data of our research group shows that the proposed method has better performance than the existing diagnostic methods and diagnostic models. The proposed method offers an advanced and innovative solution in the domain of bearing fault diagnosis.

Image Enhancement Based on Dual-Branch Generative Adversarial Network Combining Spatial and Frequency Domain Information for Imbalanced Fault Diagnosis of Rolling Bearing

To address the problems of existing 2D image-based imbalanced fault diagnosis methods for rolling bearings, which generate images with inadequate texture details and color degradation, this paper proposes a novel image enhancement model based on a dual-branch generative adversarial network (GAN) combining spatial and frequency domain information for an imbalanced fault diagnosis of rolling bearing. Firstly, the original vibration signals are converted into 2D time–frequency (TF) images by a continuous wavelet transform, and a dual-branch GAN model with a symmetric structure is constructed. One branch utilizes an auxiliary classification GAN (ACGAN) to process the spatial information of the TF images, while the other employs a GAN with a frequency generator and a frequency discriminator to handle the frequency information of the input images after a fast Fourier transform. Then, a shuffle attention (SA) module based on an attention mechanism is integrated into the proposed model to improve the network’s expression ability and reduce the computational burden. Simultaneously, mean square error (MSE) is integrated into the loss functions of both generators to enhance the consistency of frequency information for the generated images. Additionally, a Wasserstein distance and gradient penalty are also incorporated into the losses of the two discriminators to prevent gradient vanishing and mode collapse. Under the supervision of the frequency WGAN-GP branch, an ACWGAN-GP can generate high-quality fault samples to balance the dataset. Finally, the balanced dataset is utilized to train the auxiliary classifier to achieve fault diagnosis. The effectiveness of the proposed method is validated by two rolling bearing datasets. When the imbalanced ratios of the four datasets are 0.5, 0.2, 0.1, and 0.05, respectively, their average classification accuracy reaches 99.35% on the CWRU bearing dataset. Meanwhile, the average classification accuracy reaches 96.62% on the MFS bearing dataset.

SSPENet: Semi-supervised prototype enhancement network for rolling bearing fault diagnosis under limited labeled samples

Real industrial scenarios struggle with the issues of a limited number of labeled samples and difficulty in accessing, which results in deep learning-based fault diagnosis models having poor generalization capabilities and decreased diagnostic accuracy. To address this problem, a semi-supervised prototype enhancement network (SSPENet) is proposed for rolling bearing fault diagnosis in this study. Firstly, a dual pooling attention residual network is proposed to be used in the feature extraction module. The goal is to efficiently extract the hidden features within rolling bearings, thus enabling the accurate classification of different sample categories. Subsequently, the Hungarian algorithm is utilized to design a strategic approach to update prototypes with pseudo-labels, which achieves the effect of augmenting prototypes by accurately adjusting the prototype position of each class of limited labeled samples through unlabeled samples, to improve the discriminative ability of the network model for fault classes. Finally, validation and experimental analysis are carried out on two bearing datasets, which achieve the average diagnostic accuracy of the proposed model to be above 90 % for both 1-shot and 2-shot cases, obtaining more satisfactory diagnostic results.

An improved envelope spectrum via Hoyer index-gram for bearing fault extraction

Resonance demodulation is one of the most commonly used methods in rolling bearing fault diagnosis, yet determining the optimal demodulation band has been a significant challenge. The vibration signal from a faulty bearing may include not only periodic fault impulses but also discrete harmonic interferences, random impulses, Gaussian white noise, among others. To enhance fault information and attenuate the impact of interference signals, this paper proposes an improved envelope spectrum via Hoyer index-gram (IESHoyergram). By utilizing the Hoyer index of the spectrum-related enhanced envelope spectrum as the frequency band filtering criterion, the proposed method extracts periodic impulses while suppressing interference from random impulses and other sources. Moreover, owing to the multilevel segmentation based on the different trend components in the spectral correlation spectrogram, IESHoyergram avoids the shortcomings of traditional segmentation methods. The proposed method is validated through both simulated and experimentally acquired data, demonstrating its capability not only to enhance the characteristics of a single fault but also to separate multiple component faults.

Bearing fault diagnosis based on transfer learning with dual-flow manifold ResNet and improved CapsNet

In intelligent fault diagnosis for rolling bearings, the variable operating conditions of rotating machinery lead to inconsistent distributions between training and testing data, inevitably decreasing fault diagnosis accuracy. To overcome this issue, we propose a bearing fault diagnosis method based on transfer learning with a dual-flow manifold residual network and improved capsule network (DMRCN). Firstly, we introduce a dual-flow manifold residual network structure consisting of continuous wide-kernel convolution, continuous narrow-kernel convolution, and manifold learning spatial information description blocks. This architecture is utilized to extract low-level features from the data. Then, we present a novel architecture of the capsule network with self-attention output. We incorporate a self-attention mechanism into the dynamic routing algorithm to transfer richer high-level features from the low-level capsule layer to the higher-level capsule layer. During training, we propose a loss function known as global-local distribution discrepancy loss to enhance the model’s generalization ability and accelerate model convergence. Finally, we validate the performance of DMRCN in cross-condition transfer fault diagnosis on both the Case Western Reserve University public dataset and a laboratory-built bearing experimental rig dataset. Experimental results demonstrate that DMRCN outperforms other commonly used deep transfer learning methods regarding fault diagnosis across different operating conditions.

Fault transfer diagnosis of rolling bearings across different devices via multi-domain information fusion and multi-kernel maximum mean discrepancy

The current deep learning-based intelligent diagnosis algorithms depend on large amounts of well-labeled data, but they may not perform well in engineering practice where the fault data available from a single device is limited. The significant difference in data distribution between different devices makes it more difficult to transfer diagnosis across devices. Therefore, aiming at the problem that the great difference in the data distribution of source and target domains in cross-device transfer diagnosis leads to the low diagnosis accuracy, this paper investigates a deep transfer network model based on multi-domain information fusion and multi-kernel maximum mean discrepancy (MK-MMD) for fault diagnosis of rolling bearings across different devices. Firstly, to address the problem that single-domain information is difficult to adequately characterize rolling bearing health status information of different devices, a multi-domain information feature extractor based on multi-attention mechanism is constructed to capture the important features of vibration signals in different transform domains. Secondly, the extracted multi-domain features are input into the bidirectional gated recurrent unit (BiGRU) network for feature fusion, and MK-MMD is used to narrow the distribution distance between the source domain and target domain to obtain domain invariant features, and then achieve the transfer diagnosis of rolling bearing faults between different devices. Finally, the method investigated is verified by rolling bearing fault transfer diagnosis tests between different devices, and the results show that the suggested method can adapt to the feature distribution between different domains, and improve the transfer diagnosis accuracy between different devices.