Bayesian-Optimized Hybrid Kernel SVM for Rolling Bearing Fault Diagnosis

Abstract

We propose a new fault diagnosis model for rolling bearings based on a hybrid kernel support vector machine (SVM) and Bayesian optimization (BO). The model uses discrete Fourier transform (DFT) to extract fifteen features from vibration signals in the time and frequency domains of four bearing failure forms, which addresses the issue of ambiguous fault identification caused by their nonlinearity and nonstationarity. The extracted feature vectors are then divided into training and test sets as SVM inputs for fault diagnosis. To optimize the SVM, we construct a hybrid kernel SVM using a polynomial kernel function and radial basis kernel function. BO is used to optimize the extreme values of the objective function and determine their weight coefficients. We create an objective function for the Gaussian regression process of BO using training and test data as inputs, respectively. The optimized parameters are used to rebuild the SVM, which is then trained for network classification prediction. We tested the proposed diagnostic model using the bearing dataset of the Case Western Reserve University. The verification results show that the fault diagnosis accuracy is improved from 85% to 100% compared with the direct input of vibration signal into the SVM, and the effect is significant. Compared with other diagnostic models, our Bayesian-optimized hybrid kernel SVM model has the highest accuracy. In laboratory verification, we took sixty sets of sample values for each of the four failure forms measured in the experiment, and the verification process was repeated. The experimental results showed that the accuracy of the Bayesian-optimized hybrid kernel SVM reached 100%, and the accuracy of five replicates reached 96.7%. These results demonstrate the feasibility and superiority of our proposed method for fault diagnosis in rolling bearings.

A new model for bearing fault diagnosis based on mutual mapping of signals and images and sparse representation

“…Of course, it is also important to choose a suitable classifier based on the extracted features after feature extraction. The commonly used small sample classifiers in bearing fault diagnosis currently include support vector machines (SVMs) [13], decision trees [14], and k-nearest neighbor (KNN) [15]. The performance of SVM is easily affected by parameters, and parameter optimization undoubtedly increases the time cost and complexity of the algorithm.…”

Study on the optimization of the classification method of rolling bearing fault type and damage degree based on SFO–VMD

“…Currently, common feature indicators include quantitative, dimensionless, and comprehensive evaluation indexes. For instance, Song et al [22] utilized the discrete Fourier transform to extract 15 features from the vibration signals in the time and frequency domains as indicators. Tong et al [23] extracted time domain, frequency domain, and multi-scale entropy features, and combined them into a multi-domain feature indicator dataset.…”

Rolling Bearing Fault Diagnosis Based on Support Vector Machine Optimized by Improved Grey Wolf Algorithm

“…Rolling bearing fault diagnosis includes multiple processes of vibration signal data acquisition, data preprocessing, feature extraction, and fault identification [ 5 , 6 , 7 , 8 ]. During research on fault feature extraction, rolling bearing fault vibration signal features are commonly extracted based on signal time-domain features [ 9 ].…”