Fault diagnosis of rolling bearings with noise signal based on modified kernel principal component analysis and DC‐ResNet

Abstract

In view of the influence of aliasing noise on the effectiveness and accuracy of bearing fault diagnosis, a bearing fault diagnosis algorithm based on the spatial decoupling method of modified kernel principal component analysis (MKPCA) and the residual network with deformable convolution (DC‐ResNet) is innovatively proposed. Firstly, the Gaussian noise with different signal‐to‐noise ratios (SNRs) is added to the data to simulate the different degrees of noise in the actual data acquisition process. The MKPCA is used to project the fault signal with different SNRs in the kernel space to reduce the data dimension and eliminate some noise effects. Finally, the DC‐ResNet model is used to further filter the noise effects and fully extract the fault features through the training of the preprocessed data. The proposed algorithm is tested on the Case Western Reserve University (CWRU) and Xi'an Jiaotong University and Changxing Sumyoung Technology Co., Ltd. (XJTU‐SY) bearing data sets with different SNR noise. The fault diagnosis accuracy can reach 100% within 30 min, which has better performance than most of the existing methods. The experimental results show that the algorithm has an excellent effect on accuracy and computation complexity under different noise levels.

A Data-Driven Kernel Principal Component Analysis–Bagging–Gaussian Mixture Regression Framework for Pulverizer Soft Sensors Using Reduced Dimensions and Ensemble Learning

“…KPCA is a non-linear dimensionality reduction technique that represents a variant of Principal Component Analysis (PCA) [25,26]. PCA is a commonly used linear dimensionality reduction method that reduces the dimensionality of data by finding projections along the directions of maximum variance, which has been widely used in other fields [27][28][29]. In contrast, KPCA employs the use of the kernel trick to map the data into a higher dimensional feature space, where PCA is performed.…”

A lightweight multi-feature fusion vision transformer bearing fault diagnosis method with strong local sensing ability in complex environments

“…Zong et al [16] developed an adaptive singular value decomposition to reduce signal noise, but this method required manual analysis of singular value thresholds to ensure that the center frequency and bandwidth of the filter did not change. Zhao et al [17] proposed a bearing fault diagnosis algorithm based on the spatial decoupling method of modified kernel principal component analysis and deformable convolution residual network for the effect of aliasing noise on bearing fault diagnosis. The effect of noise was eliminated by both kernel space projection and deformable convolution residual network.…”