Bearing Fault Diagnosis Using a Particle Swarm Optimization-Least Squares Wavelet Support Vector Machine Classifier

Abstract

Bearing is one of the key components of a rotating machine. Hence, monitoring health condition of the bearing is of paramount importace. This paper develops a novel particle swarm optimization (PSO)-least squares wavelet support vector machine (PSO-LSWSVM) classifier, which is designed based on a combination between a PSO, a least squares procedure, and a new wavelet kernel function-based support vector machine (SVM), for bearing fault diagnosis. In this work, bearing fault classification is transformed into a pattern recognition problem, which consists of three stages of data processing. Firstly, a rich information dataset is built by extracting the features from the signals, which are decomposed by the nonlocal means (NLM) and empirical mode decomposition (EMD). Secondly, a minimum-redundancy maximum-relevance (mRMR) method is employed to determine a subset of feature that can provide an optimal performance. Thirdly, a novel classifier, namely LSWSVM, is proposed with the aid of a PSO, to provide higher classification accuracy. The key innovative science of this work is to propropose a new classifier with the aid of an new wavelet kernel type to increase the classification precision of bearing fault diagnosis. The merit features of the proposed approach are demonstrated based on a benchmark bearing dataset and a comprehensive comparison procedure.

Application of ICEEMDAN Energy Entropy and AFSA-SVM for Fault Diagnosis of Hoist Sheave Bearing

“…As one of the most intelligent and cutting-edge fields in the field of artificial intelligence, the application of SVM received increasing attention [ 12 , 13 , 14 ], reflecting in the aspects of regression estimation, pattern recognition, and fault diagnosis, such as the fault diagnosis of the vehicle suspensions, automatic detection of diabetic eye disease, and predictive control of the industrial process [ 15 , 16 , 17 ]. In the aspect of bearing fault diagnosis, the application of SVM has been reported in many literatures [ 18 , 19 , 20 , 21 ]. For example, Gu et al [ 18 ] proposes an approach based on the variational mode decomposition, support vector machine, and statistical characteristics to analyze the vibration signals of bearing on the spindle device of the mine hoist.…”

“…Li et al [ 19 ] used ensemble SVM for the intelligent classification of the bearing’s faults, combined with the nonlinear dynamics entropy. Van et al [ 20 ] proposed a hybrid fault-diagnosis method for bearing based on the particle swarm optimization and least squares wavelet support vector machine, whose feature vectors are obtained by minimum-redundancy maximum-relevance method. In the paper [ 21 ], the authors used the time and frequency domain features as the feature vectors of the support vector machine for early detection and classification of bearing faults in electrical motors and generators.…”

Fault Diagnosis of Rolling Bearings Based on a Residual Dilated Pyramid Network and Full Convolutional Denoising Autoencoder

“…Then these statistical features are input into a machine learning classifier for fault diagnosis, such as K-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), gradient boosting decision tree (GBDT) and artificial neural network (ANN), etc. [ 6 , 7 , 8 , 9 , 10 ]. Bhakta et al used cepstrum analysis to pre-process the rolling bearing datasets provided by the Case Western Reserve University (CWRU) laboratory, then used the gradient boosting (GB) learning algorithm for fault diagnosis, and achieved good results [ 11 ].…”

Input Feature Mappings-Based Deep Residual Networks for Fault Diagnosis of Rolling Element Bearing With Complicated Dataset

“…Many ML algorithms have been used for REB fault diagnosis, and achieved considerable success [4][5][6][7][8][9][10][11][12]. Van et.al [13] proposed a support vector machine (SVM)-based model for REB fault diagnosis. Firstly, they used the nonlocal means method and empirical mode decomposition to extract the fault features from the raw signals.…”