Intelligence Bearing Fault Diagnosis Model Using Multiple Feature Extraction and Binary Particle Swarm Optimization With Extended Memory

Chun-Yao Lee,Truong-An Le

doi:10.1109/access.2020.3035081

Abstract

This article presents an effective bearing fault diagnosis model based on multiple extraction and selection techniques. In multiple feature extraction, the discrete wavelet transform, envelope analysis, and fast Fourier transform are considered. While the combined binary particle swarm optimization with extended memory is focusing on feature selection. The current signals are analyzed by discrete wavelet transform. From there, the statistical features in the time and frequency domain are extracted by two techniques: envelope analysis, fast Fourier transform. Subsequently, the binary particle swarm optimization is combined with extended memory and two proposed position update mechanisms to eliminate redundant or irrelevant features to achieve the optimal feature subset. Besides, three classifiers including naïve Bayes, decision tree, and linear discriminant analysis are applied and compared to select the best model to detect the bearing fault.

Highlights

Rotary machines are one of the most important equipment in the manufacturing industry and other fields nowadays
Case study 2: The effectiveness of the proposed bearing fault diagnosis model is evaluated and analyzed based on the dataset acquired from test motors including healthy motor and bearing failure motors
A highly effective fault diagnosis model is introduced in this study

Summary

Introduction

Rotary machines are one of the most important equipment in the manufacturing industry and other fields nowadays. Many rotating machinery failures cause lead to huge economic losses and potentially serious casualties. One of the most important components in rotating machinery is bearings. According to Electric Power Research Institute research, the failure rate of bearings accounts for 41% of the faults in rotary machines [1]. In recent years, bearings fault diagnosis models have been getting more and more attention from researchers. A highperformance bearings fault diagnosis model is investigated based on a combination of techniques to extract attributes from the current signals of the induction motors. An appropriate classifier is used to identify bearing faults via the optimal feature subset

Methods

Results

Conclusion