Rolling Bearing Fault Diagnosis Method Research Articles

A Rolling Bearing Fault Diagnosis Method via 2D Feature Map of CSCoh After Denoising and MSCNN Under Different Conditions

The vibration signal of rolling bearing is interfered by the coupling of other various components and environment, which brings challenges to effective feature expression and the establishment of accurate predictor. A fault diagnosis method via 2D feature map of cyclic spectral coherence (CSCoh) after denoising and multi-scale convolutional neural network (MSCNN) under different conditions is proposed. The original vibration signal is processed by DTCWPT and threshold denoising, and a 2D feature map extraction model based on CSCoh is established to reflect hidden periodic characteristics. The feature differences can be highlighted and the coupling interference can be further eliminated. The multi-scale convolution kernels are proposed to build a parallel structure, and a fusion structure is followed. Benefit by the structures in MSCNN, the local and global features of 2D feature map can be preserved comprehensively, the learning ability and diagnostic performance can be improved. Finally, the verification experiments of rolling bearings in different positions under different operating conditions are carried out, and the experimental results show the proposed method has better generalization ability and comprehensive accuracy of more than 95% under different conditions.

A Variable Working Condition Rolling Bearing Fault Diagnosis Method Based on Improved Triplet Loss Algorithm

A Variable Working Condition Rolling Bearing Fault Diagnosis Method Based on Improved Triplet Loss Algorithm

A fault diagnosis method based on improved parallel convolutional neural network for rolling bearing

There are many disadvantages for traditional Convolutional Neural Network (CNN) in rolling bearing fault diagnosis, such as low efficiency, weak noise immunity, and poor generalization with changing load. To solve the problem, this paper proposes a methodology of improved parallel CNN (IPCNN). In IPCNN, the simple pooling layer is removed and the parallel structure is to stack directly convolutional layers, with three branches, each branch has 4 layers, where the convolution kernels are all 3 × 3 and the stride sizes are 1, 2, and 3, respectively. The structure that is capable of feature fusion can extract features from the input information. Subsequently, the global average pooling (GAP) layer is used for down sampling, and the bearing faults are classified by the fully connected (FC) layer. In addition, the effectiveness of the proposed model structure is verified by testing the datasets. To further verify the validity of the model, the performance of the model was evaluated by diagnostic accuracy, prediction time, SD, and model size. In order to verify the noise immunity and generalization of the proposed model, the AlexNet, Vgg16, and ResNet18 models are compared, respectively. By performing 2D gray images transformation on the Case Western Reserve University (CWRU) bearing data, rolling bearing fault diagnosis method based on IPCNN model has higher efficiency, stronger noise resistance in the noise environment, and better generalization ability when the load changes.

Multi-input parallel graph neural network for semi-supervised rolling bearing fault diagnosis

Rolling bearing fault diagnosis is the key technology to ensure the reliable, efficient and sustainable operation of rotating machinery. Many fault diagnosis methods have been proposed based on vibration signal analysis from the perspective of data-driven analytics. However, these methods normally take signals of multiple sensors as a whole for feature extraction without considering the relationship among samples. This drawback leads to insufficient feature mining, thereby affecting the accuracy of fault diagnosis. Moreover, these methods need large numbers of labeled samples to achieve high diagnosis accuracy, which requires extensive human labor and is impractical in many real-world applications. To address these issues, a semi-supervised rolling bearing fault diagnosis method based on multi-input parallel graph neural network is proposed in this paper. In the proposed model, signals of multiple sensors are treated separately; thus, features will be extracted parallelly in a more sufficient way. Then, signals of each sensor are constructed into a graph based on limited-radius nearest neighbor, which will add extra relationship information to aid in fault diagnosis. In addition, with the implementation of graph convolutional neural network, the proposed method is able to achieve a more accurate diagnosis than the comparison methods in the case of few labeled data. Finally, the proposed model is evaluated on rolling bearing dataset provided by Case Western Reserve University. Compared with some classical fault diagnosis methods, the proposed model can improve the diagnosis accuracy up to more than 99% even when the proportion of training samples is only 20%.

A Novel Rolling Bearing Fault Diagnosis Method Based on BLS and CNN with Attention Mechanism

In actual industrial application scenarios, noise pollution makes it difficult to extract fault features accurately via conventional methods. A novel method for rolling bearing fault diagnosis combining a convolutional neural network (CNN), an attention mechanism for a squeeze-and-excitation network (SENet) module and a broad learning system (BLS) is proposed (SECNN–BLS). The one-dimensional bearing vibration signal is processed by using multiple short-time Fourier transforms (STFT); the two-dimensional image in the time-frequency domain is used as the model input. In the CNN fault feature extraction process, SENet is introduced to replace the CNN convolution layer, and global information is obtained through the squeeze operation. Excitation operation captures the importance of image channels, assigns weights adaptively to improve the attention on important information and eliminates the interference of irrelevant features without increasing the spatial and temporal complexity. The weighted feature representation is then transferred to the BLS input. The BLS has the characteristics of a flat structure and ridge regression to quickly solve the weights; as a fault classifier, it can save more computing resources and improve the accuracy of the fault classification. The SECNN–BLS fault diagnosis has achieved more than 98% accuracy on the Society for Machinery Failure Prevention Technology (MFPT) dataset. We also demonstrate the excellent performance of SECNN–BLS in a noisy environment.

A Rolling Bearing Fault Diagnosis Method Based on Switchable Normalization and a Deep Convolutional Neural Network

Aiming to address the problems of a low fault detection rate and poor diagnosis performance under different loads and noise environments, a rolling bearing fault diagnosis method based on switchable normalization and a deep convolutional neural network (SNDCNN) is proposed. The method effectively extracted the fault features from the raw vibration signal and suppressed high-frequency noise by increasing the convolution kernel width of the first layer and stacking multiple layers’ convolution kernels. To avoid losing the intensity information of the features, the K-max pooling operation was adopted at the pooling layer. To solve the overfitting problem and improve the generalization ability, a switchable normalization approach was used after each convolutional layer. The proposed SNDCNN was evaluated with two sets of rolling bearing datasets and obtained a higher fault detection rate than SVM and BP, reaching a fault detection rate of over 90% under different loads and demonstrating a better anti-noise performance.

Rolling bearing fault diagnosis based on 2D time-frequency images and data augmentation technique

It confronts great difficulty to apply the traditional rolling bearing fault diagnosis methods to adaptively extract features conducive to fault diagnosis under complex operating conditions, and obtaining numerous fault data under real operating conditions is difficult and costly. To address this problem, a fault diagnosis method based on two-dimensional time-frequency images and data augmentation is proposed. To begin with, the original one-dimensional time series signal is converted into two-dimensional time-frequency images by continuous wavelet transform to obtain the input data suitable for two-dimensional convolutional neural network (CNN). Secondly, data augmentation technique is employed to expand labeled fault data. Finally, the generated and original fault data are served as training samples to train the fault diagnosis model based on CNNs. Experimental studies are conducted on standard and real-world datasets to validate the proposed method and demonstrate its superiority over the traditional methods in detecting bearing faults.

Rolling bearing fault diagnosis based on the enhanced channel attention network

ABSTRACT This paper proposes a rolling bearing fault diagnosis method based on the enhanced channel attention network. The vibration signals are collected via a wireless sensor node, which are input to the neural network, and channel attention block is used to strengthen the assignment of important features, so that the attention of network is paid onto the critical fault information. Furthermore, channel attention block and residual convolution block are combined to form an enhanced channel attention network to extract the detail features. Experiment results show that the model can achieve 100% recognition accuracy for rolling bearings in various working conditions. It is also shown that the proposed new learning algorithm can provide a higher diagnosis accuracy than those state-of-the-arts in a strong disturbance environment, which reflects better robustness and generalisation ability.

Rolling bearing fault diagnosis method based on dynamic convolution capsule network

Aiming at the weak generalization ability of traditional rolling bearing fault diagnosis methods, a rolling bearing diagnosis method based on dynamic convolutional capsule networks (DC-CapNets) was proposed. First, one-dimensional vibration signals are preprocessed and divided into a training set and a test set. Then the fast Fourier transform (FFT) is used to convert the training set and the test set. In this model, two dynamic convolution layers and pooling layers are used to extract the features of the input frequency signals, and the feature information is transmitted to the capsule network to obtain the diagnosis results. The CWRU (Western Reserve University) data set validation shows that the proposed method still has high fault diagnosis accuracy under noise and variable load conditions, and has good anti-noise and generalization performance, which is superior to the convolutional neural network (CNN) and deep neural network (DNN).

Intelligent Rolling Bearing Fault Diagnosis Method Using Symmetrized Dot Pattern Images and CBAM-DRN

Rolling bearings are a vital component of mechanical equipment. It is crucial to implement rolling bearing fault diagnosis research to guarantee the stability of the long-term action of mechanical equipment. Conversion of rolling bearing vibration signals into images for fault diagnosis research has been a practical diagnostic approach. The current paper presents a rolling bearing fault diagnosis method using symmetrized dot pattern (SDP) images and a deep residual network with convolutional block attention module (CBAM-DRN). The rolling bearing vibration signal is first visualized and transformed into an SDP image with distinct fault characteristics. Then, CBAM-DRN is utilized to derive characteristics directly and detect faults from the input SDP images. In order to prevent conventional time-frequency images from being limited by their inherent flaws and avoid missing the fault features, the SDP technique is employed to convert vibration signals into images for visualization. DRN enables adequate extraction of rolling bearing fault characteristics and prevents training difficulties and gradient vanishing in deep level networks. CBAM assists the diagnostic model in concentrating on the image's more distinctive parts and preventing the interference of non-featured parts. Finally, the method's validity was tested with a composite fault dataset of motor bearings containing multiple loads and fault diameters. The experimental results reflect that the presented approach can attain a diagnostic precision of over 99% and good stability and generalization.

Rolling Bearing Fault Diagnosis Method Based on MCMF and SAIMFE

Fault diagnosis of rolling bearing is important for ensuring the safe operation of industrial machinery. In order to improve diagnosis accuracy of bearing fault, a rolling bearing fault diagnosis method based on multiscale combined morphological filter (MCMF) and self-adaption improved multiscale fuzzy entropy (SAIMFE) is proposed in this paper. First, the MCMF is designed to eliminate noise and preserve fault information more effectively. Second, SAIMFE is proposed to extract bearing fault features, and the optimized scale factor of SAIMFE is determined based on the absolute skewness. Third, some experiments are completed to demonstrate the effectiveness and superiority of the proposed method. The experimental results show that the proposed method not only has high diagnosis accuracy but also less dependent on the diagnosis model.

A Lightweight Bearing Fault Diagnosis Method Based on Multi-Channel Depthwise Separable Convolutional Neural Network

The existing rolling bearing fault diagnosis method based on the deep convolutional neural network has the issues of insufficient feature extraction ability, poor anti-noise ability, and a large number of model parameters. A lightweight bearing fault diagnosis method based on depthwise separable convolutions is proposed. The proposed method can simultaneously extract different features from vibration signals in different directions to enhance the stability of the diagnosis model. The lightweight unit based on depthwise separable convolutions in the feature extraction layer reduces the size of the model and the number of parameters that need to be learned. The vibration signals of bearings in different directions are converted into time-frequency signals by the short-time Fourier transform (STFT) and then into pictures as the input of the model. In order to verify the effectiveness and generalization of the method, this paper uses the gearbox data set of Southeast University and the CWRU (Case Western Reserve University) bearing data set for experiments. Comparisons of bearing fault diagnosis results using the proposed model with other classical deep learning models are implemented. The results show that the proposed model is superior to other classical deep learning models; thus, it has a smaller model size, higher accuracy, and less computation burden. Compared with using a single-direction vibration signal as input, the proposed model that uses multiple vibration signals in different directions as input has more accuracy.

Network Construction for Bearing Fault Diagnosis Based on Double Attention Mechanism.

Aiming at the difficulty of feature extraction in the case of multicomponent and strong noise in the traditional rolling bearing fault diagnosis method, this paper proposes a bearing fault diagnosis network with double attention mechanism. The original signal with noise is decomposed into a series of intrinsic mode functions (IMFs) by the Empirical Mode Decomposition method. The Pearson correlation coefficient is discussed to filter the IMFs components for signal reconstruction. The spatial features of the reconstructed signal are extracted by attention convolutional networks. Then, time series features are extracted based on the long short-term memory method. Furthermore, the importance of temporal features is measured through a temporal attention mechanism. The Softmax layer of the constructed network is used as the classifier for fault diagnosis. Comparing this method with the existing methods of experiments, the proposed method has not only better diagnosis accuracy but also stronger antiinterference ability and generalization ability, which can accurately diagnose and classify the bearing fault types. The fault diagnosis accuracy rate for each load is above 99%.

Rolling bearing intelligent fault diagnosis method based on IPSO-WCNN

In the bearing fault diagnosis process using the convolution neural network (CNN), there are some problems, such as complex signal data processing and the complex network parameter setting. A rolling bearing fault diagnosis method is proposed to solve these problems based on improved particle swarm optimization and convolution neural networks with wide kernels in first-layer (IPSO-WCNN). The particle self-adaptive jump out algorithm is proposed to overcome particle swarm optimization (PSO) shortcomings. The adaptive inertia weight and the linear change acceleration coefficients are adopted for improved particle swarm optimization (IPSO). The convolution neural networks with wide kernels in first-layer (WCNN) fault diagnosis method is proposed for one-dimensional rolling bearing vibration signals, and the parameters of the WCNN is optimised by IPSO. According to the verification experiments, the proposed method can get higher accuracy than others with good adaptability.

A Novel Fault Diagnosis Method for Rolling Bearing Based on Hierarchical Refined Composite Multiscale Fluctuation-Based Dispersion Entropy and PSO-ELM

This paper proposes a novel fault diagnosis method for rolling bearing based on hierarchical refined composite multiscale fluctuation-based dispersion entropy (HRCMFDE) and particle swarm optimization-based extreme learning machine (PSO-ELM). First, HRCMFDE is used to extract fault features in the vibration signal at different time scales. By introducing the hierarchical theory algorithm into the vibration signal decomposition process, the problem of missing high-frequency signals in the coarse-grained process is solved. Fluctuation-based dispersion entropy (FDE) has the characteristics of insensitivity to noise interference and high computational efficiency based on the consideration of nonlinear time series fluctuations, which makes the extracted feature vectors more effective in describing the fault information embedded in each frequency band of the vibration signal. Then, PSO is used to optimize the input weights and hidden layer neuron thresholds of the ELM model to improve the fault identification capability of the ELM classifier. Finally, the performance of the proposed rolling bearing fault diagnosis method is verified and analyzed by using the CWRU dataset and MFPT dataset as experimental cases, respectively. The results show that the proposed method has high identification accuracy for the fault diagnosis of rolling bearings with varying loads and has a good load migration effect.

SWT-KELM-based rolling bearing fault diagnosis method under noise conditions with different SNRs

Most existing studies carry out bearing fault diagnosis tasks in labs with weak noise. However, field noise is so heavy under actual conditions that some methods may suffer from degradation or failure. To solve this problem, a fault diagnosis framework is proposed based on the synchrosqueezing wavelet transform and kernel extreme learning machine (SWT-KELM). First, vibration signals are collected, and white Gaussian noise is added. Second, SWT is employed for signal decomposition in the time–frequency domain, and inverse SWT is applied for subsignal reconstruction. Subsignals with high correlation coefficients are selected for further feature extraction, specifically by singular value decomposition, to obtain singular values as the fault feature. Third, the KELM model, in which the beetle antennae search algorithm is employed for parameter optimization, is constructed to classify the faults. For verification, the proposed method is implemented on the Case Western Reserve University dataset and Lab-625 dataset, and the results show that it maintains satisfactory outcomes on original and noise-contaminated data. Specifically, under noisy conditions, the accuracies of the two datasets average at 96% and 83%, respectively, indicating the robustness and generalization of the method compared to other methods.

Rolling Bearing Fault Diagnosis Method Based on Attention CNN and BiLSTM Network

Rolling Bearing Fault Diagnosis Method Based on Attention CNN and BiLSTM Network

Rolling bearing fault diagnosis method based on multi-sensor two-stage fusion

Despite the great achievements of deep learning methods based on a single sensor in fault diagnosis, learning useful information from multi-sensor data is still a challenge. In order to make full use of multi-sensor information and improve the performance of rolling bearing fault diagnosis, a novel multi-sensor information fusion framework is proposed in this paper. First, a multi-sensor-based multi-frequency information fusion method is proposed. The multi-frequency information of each sensor is segmented first to enhance the datasets, and then a weighted fusion rule based on fuzzy entropy is constructed to fuse the information of different frequency components for multi-sensors. Second, a multi-kernel attention convolutional neural network is designed to realize multi-frequency feature capture, fusion, and fault classification of multi-sensors. Finally, two different rolling bearing datasets are used to implement fault diagnosis experiments. Experimental results show that the proposed method outperforms the comparative methods in terms of diagnostic performance and robustness.

Bearing Fault Diagnosis Using Piecewise Aggregate Approximation and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise.

Complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) effectively separates the fault vibration signals of rolling bearings and improves the diagnosis of rolling bearing faults. However, CEEMDAN has high memory requirements and low computational efficiency. In each iteration of CEEMDAN, fault vibration signals are added with noises, both the vibration signals added with noises and the added noises are decomposed with classical empirical mode decomposition (EMD). This paper proposes a rolling bearing fault diagnosis method that combines piecewise aggregate approximation (PAA) with CEEMDAN. PAA enables CEEMDAN to decompose long signals and to achieve enhanced diagnosis. In particular, the method first yields the vibration envelope using bandpass filtering and demodulation, then compresses the envelope using PAA, and finally decomposes the compressed signal with CEEMDAN. Test data verification results show that the proposed method is more effective and more efficient than CEEMDAN.

Rolling Bearing Fault Diagnosis Based on WGWOA-VMD-SVM.

A rolling bearing fault diagnosis method based on whale gray wolf optimization algorithm-variational mode decomposition-support vector machine (WGWOA-VMD-SVM) was proposed to solve the unclear fault characterization of rolling bearing vibration signal due to its nonlinear and nonstationary characteristics. A whale gray wolf optimization algorithm (WGWOA) was proposed by combining whale optimization algorithm (WOA) and gray wolf optimization (GWO), and the rolling bearing signal was decomposed by using variational mode decomposition (VMD). Each eigenvalue was extracted as eigenvector after VMD, and the training and test sets of the fault diagnosis model were divided accordingly. The support vector machine (SVM) was used as the fault diagnosis model and optimized by using WGWOA. The validity of this method was verified by two cases of Case Western Reserve University bearing data set and laboratory test. The test results show that in the bearing data set of Case Western Reserve University, compared with the existing VMD-SVM method, the fault diagnosis accuracy rate of the WGWOA-VMD-SVM method in five repeated tests reaches 100.00%, which preliminarily verifies the feasibility of this algorithm. In the laboratory test case, the diagnostic effect of the proposed fault diagnosis method is compared with backpropagation neural network, SVM, VMD-SVM, WOA-VMD-SVM, GWO-VMD-SVM, and WGWOA-VMD-SVM. Test results show that the accuracy rate of WGWOA-VMD-SVM fault diagnosis is the highest, the accuracy rate of a single test reaches 100.00%, and the accuracy rate of five repeated tests reaches 99.75%, which is the highest compared with the above six methods. WGWOA plays a good optimization role in optimizing VMD and SVM. The signal decomposed by VMD is optimized by using the WGWOA algorithm without mode overlap. WGWOA has the better convergence performance than WOA and GWO, which further verifies its superiority among the compared methods. The research results can provide an effective improvement method for the existing rolling bearing fault diagnosis technology.