Bearing Fault Diagnosis Based on Discriminant Analysis Using Multi-View Learning

Abstract

Bearing fault diagnosis has been a challenge in rotating machinery and has gained considerable attention. In order to correctly classify faults, the conventional fault diagnosis methods are mostly based on vibration signals. However, features extracted from a single view of vibration signals may leave out useful information, which can cause the incompleteness of intrinsic information and increase the risk of the performance degradation of fault classifications. In this paper, a novel bearing fault diagnosis method, discriminant analysis using multi-view learning (DAML), is proposed to tackle this issue. Multi-view datasets referring to vibration and acoustic signals are obtained by carrying out a fast Fourier transform (FFT). Then, multi-view feature (MVF) representation, including view-invariant and category discriminative information in a common subspace, is achieved based on canonical correlation analysis (CCA) and uncorrelated linear discriminant analysis (ULDA). Ultimately, with the help of the K-nearest neighbor (KNN) classifier built on the multi-view features, bearing faults are identified. The extensive experimental results show that DAML can identify the bearing fault accurately and outperforms other competitive approaches.

Fault diagnosis of electrical faults of three phase induction motors using acoustic analysis

“…Discriminant analysis using multi-view learning for bearing fault diagnosis was described in the next paper [11]. FFT, multiview features, and KNN were used for the analysis.…”

Research on SVM-Based Bearing Fault Diagnosis Modeling and Multiple Swarm Genetic Algorithm Parameter Identification Method

“…Lu et al [29] investigated an effective and reliable deep learning method based on convolutional neural networks (CNN) using cognitive theory to introduce the advantages of image recognition and visual perception into bearing fault diagnosis by simulating the cognitive processes in the cerebral cortex, and the method improved the accuracy of failure mode classification of rolling bearings with respect to environmental noise and fluctuating operating conditions. Tong et al [30] proposed a multi-view learning (DAML)-based bearing fault diagnosis method which obtains a multi-view data set involving vibration and acoustic signals by performing a fast Fourier transform (FFT), and then implements a multi-view feature (MVF) representation including view-invariant information and class discrimination information in a common subspace based on typical correlation analysis (CCA) and uncorrelated linear discriminant analysis (ULDA). The multi-view feature (MVF) representation including view invariant information and class discriminant information is then implemented in a common subspace based on typical correlation analysis (CCA) and uncorrelated linear discriminant analysis (ULDA), and finally a bearing fault is identified using a K-nearest neighbor (KNN) classifier based on the multi-view feature.…”

Optimizing Allocation Rules in Discrete and Continuous Discriminant Analysis

“…For example, using dynamic feature extraction along with quadratic discriminant analysis classifier can significantly enhance fault classification and diagnosis in dynamic nonlinear processes, as demonstrated by Li, Jia, and Mao [12]. Furthermore, Tong et al [13] demonstrated the effectiveness of discriminant analysis in their work on bearing fault diagnosis, representing a crucial development in fault diagnosis for dynamic nonlinear processes. For more information on discriminant analysis, see McLachlan [14].…”