In complex industrial environments, the vibration signal of the rolling bearing is covered by noise, which makes fault diagnosis inaccurate. In order to overcome the effect of noise on the signal, a rolling bearing fault diagnosis method based on the WOA-VMD (Whale Optimization Algorithm-Variational Mode Decomposition) and the GAT (Graph Attention network) is proposed to deal with end effect and mode mixing issues in signal decomposition. Firstly, the WOA is used to adaptively determine the penalty factor and decomposition layers in the VMD algorithm. Meanwhile, the optimal combination is determined and input into the VMD, which is used to decompose the original signal. Then, the Pearson correlation coefficient method is used to select IMF (Intrinsic Mode Function) components that have a high correlation with the original signal, and selected IMF components are reconstructed to remove the noise in the original signal. Finally, the KNN (K-Nearest Neighbor) method is used to construct the graph structure data. The multi-headed attention mechanism is used to construct the fault diagnosis model of the GAT rolling bearing in order to classify the signal. The results show an obvious noise reduction effect in the high-frequency part of the signal after the application of the proposed method, where a large amount of noise was removed. In the diagnosis of rolling bearing faults, the accuracy of the test set diagnosis in this study was 100%, which is higher than that of the four other compared methods, and the diagnosis accuracy rate of various faults reached 100%.

Feature extraction is one of the challenging problems in fault diagnosis, and it has a direct bearing on the accuracy of fault diagnosis. Therefore, in this paper, a new method based on ensemble empirical mode decomposition (EEMD), wavelet semi-soft threshold (WSST) signal reconstruction, and multi-scale entropy (MSE) is proposed. First, the EEMD method is applied to decompose the vibration signal into intrinsic mode functions (IMFs), and then, the high-frequency IMFs, which contain more noise information, are screened by the Pearson correlation coefficient. Then, the WSST method is applied for denoising the high-frequency part of the signal to reconstruct the signal. Secondly, the MSE method is applied for calculating the MSE values of the reconstructed signal, to construct an eigenvector with the complexity measure. Finally, the eigenvector is input to a support vector machine (SVM) to find the fault diagnosis results. The experimental results prove that the proposed method, with a better classification performance, can better solve the problem of the effective signal and noise mixed in high-frequency signals. Based on the proposed method, the fault types can be accurately identified with an average classification accuracy of 100%.

In engineering practice, the bearing fault signal is composed of a series of complex multi-component signals containing multiple fault characteristics information. In the early stage of fault sprouting and evolution, the fault features are easily disturbed by noise and irrelevant signals, eliminating the fault signals in the strong background noise. To overcome the influence of noise on the signal, this study proposes multi-frequency weak signal decomposition and reconstruction of rolling bearing based on adaptive cascaded stochastic resonance. First, the original signal is passed through the Hilbert transform to obtain the envelope signal. The envelope signal is high-pass filtered to eliminate the interference of low-frequency components on the response of the stochastic resonance system. Secondly, cascaded stochastic resonance system parameters are adaptively optimized by the quantum particle swarm algorithm (QPSO). The high-pass filtered signal input to the adaptive cascaded stochastic resonance system (ACSRS) can further enhance the weak fault characteristics, allowing the gradual transfer of high-frequency noise energy to the low-frequency fault characteristic components. Finally, the signal is decomposed using the variational mode decomposition (VMD) method to jointly determine the location of the fault characteristic frequencies in the intrinsic mode functions (IMF) component by the energy loss coefficient and correlation coefficient to achieve the reconstruction of multi-frequency weak signals. Through simulation and experimental validation, the effectiveness and superiority of the method for multi-frequency weak signal detection in bearings are verified. The results show that the method not only achieves the adaptive optimization of the stochastic resonance system parameters gradually removing the high-frequency noise in the signal and improving the energy of the low-frequency signal but also reduces the number of decomposition layers of the VMD, enhances the fault characteristic information in the weak signal, and effectively identifies the early weak fault characteristics of rolling bearings.

Flow Direction Algorithm (FDA) has better searching performance than some traditional optimization algorithms. To give the basic Flow Direction Algorithm more effective searching ability and avoid multiple local minima under the searching space, and enable it to obtain better search results, an improved FDA based on the Lévy flight strategy and the self-renewable method (LSRFDA) was proposed in this paper. The Lévy flight strategy and the self-renewable approach were added to the basic Flow Direction Algorithm. Random parameters generated by the Lévy flight strategy can increase the algorithm’s diversity of feasible solutions in a short calculation time and greatly enhance the operational efficiency of the algorithm. The self-renewable method lets the algorithm quickly obtain a better possible solution and jump to the local solution space. Then, this paper tested different mathematical testing functions, including low-dimensional and high-dimensional functions, and the test results were compared with those of different algorithms. This paper includes iterative figures, box plots, and search paths to show the different performances of the LSRFDA. Finally, this paper calculated different engineering optimization problems. The test results show that the proposed algorithm in this paper has better searching ability and quicker searching speed than the basic Flow Direction Algorithm.

To improve the accuracy of rolling-bearing fault diagnosis and solve the problem of incomplete information about the feature-evaluation method of the single-measurement model, this paper combines the advantages of various measurement models and proposes a fault-diagnosis method based on multi-measurement hybrid-feature evaluation. In this study, an original feature set was first obtained through analyzing a collected vibration signal. The feature set included time- and frequency-domain features, and also, based on the empirical-mode decomposition (EMD)-obtained time-frequency domain, energy and Lempel–Ziv complexity features. Second, a feature-evaluation framework of multiplicative hybrid models was constructed based on correlation, distance, information, and other measures. The framework was used to rank features and obtain rank weights. Then the weights were multiplied by the features to obtain a new feature set. Finally, the fault-feature set was used as the input of the category-divergence fault-diagnosis model based on kernel principal component analysis (KPCA), and the fault-diagnosis model was based on a support vector machine (SVM). The clustering effect of different fault categories was more obvious and classification accuracy was improved.

Aiming to resolve the problem of redundant information concerning rolling bearing degradation characteristics and to tackle the difficulty faced by convolutional deep learning models in learning feature information in complex time series, a prediction model for remaining useful life based on multiscale fusion permutation entropy (MFPE) and a multiscale convolutional attention neural network (MACNN) is proposed. The original signal of the rolling bearing was extracted and decomposed by resonance sparse decomposition to obtain the high-resonance and low-resonance components. The multiscale permutation entropy of the low-resonance component was calculated. Moreover, the locally linear-embedding algorithm was used for dimensionality reduction to remove redundant information. The multiscale convolution module was constructed to learn the feature information at different time scales. The attention module was used to fuse the feature information and input it into the remaining useful life prediction module for evaluation. The appropriate network structure and parameter configuration were determined, and a multiscale convolutional attention neural network was designed to determine the remaining useful life prediction model. The results show that the method demonstrates effectiveness and superiority in degrading the feature information representation and improving the remaining useful life prediction accuracy compared with other models.