Particle swarm optimization algorithm to solve the deconvolution problem for rolling element bearing fault diagnosis

Yao Cheng; Zhiwei Wang; Weihua Zhang; Guanhua Huang

doi:10.1016/j.isatra.2019.01.012

Particle swarm optimization algorithm to solve the deconvolution problem for rolling element bearing fault diagnosis

ISA Trans. 2019 Jul:90:244-267. doi: 10.1016/j.isatra.2019.01.012. Epub 2019 Jan 16.

Authors

Yao Cheng¹, Zhiwei Wang², Weihua Zhang³, Guanhua Huang⁴

Affiliations

¹ State key laboratory of Traction power, Southwest Jiaotong University, Chengdu 610031, People's Republic of China. Electronic address: chengyao2015@my.swjtu.edu.cn.
² State key laboratory of Traction power, Southwest Jiaotong University, Chengdu 610031, People's Republic of China. Electronic address: wlyouth@sina.cn.
³ State key laboratory of Traction power, Southwest Jiaotong University, Chengdu 610031, People's Republic of China. Electronic address: tpl@home.swjtu.edu.cn.
⁴ Beijing Haidongqing Electrical and Mechanical Equipment Co., Ltd, Beijing 101300, People's Republic of China. Electronic address: hgh7735@126.com.

PMID: 30732991
DOI: 10.1016/j.isatra.2019.01.012

Abstract

Extraction of the fault related impulses from the raw vibration signal is important for rolling element bearing fault diagnosis. Deconvolution techniques, such as minimum entropy deconvolution (MED), MED adjusted (MEDA) and maximum correlated kurtosis deconvolution (MCKD), optimal MED adjusted (OMEDA) and multipoint optimal MED adjusted (MOMEDA), are typical techniques for enhancing the impulse-like component in the fault signal. This paper introduces the particle swarm optimization (PSO) algorithm to solve the filter of deconvolution problem. The proposed approaches solve the filter coefficients of the deconvolution problems by the PSO algorithm, assisted by a generalized spherical coordinate transformation. Compared with MED, MEDA, and OMEDA, the proposed PSO-MED and PSO-OMEDA can effectively overcome the influence of large random impulses and tend to deconvolve a series of periodic impulses rather than a signal impulse. Compared with MCKD and MOMEDA, the proposed PSO-MCKD and PSO-MOMEDA can achieve good performances even when the fault period is inaccurate. The effectiveness of the proposed methods is validated by the simulated signals. The study of experimental bearing fault signal shows that the PSO based deconvolution methods delivered better performance for rolling element bearing fault detection than the traditional deconvolution methods. Additionally, the proposed methods are compared with the following two popular signal processing methods: the ensemble empirical mode decomposition (EEMD) and fast kurtogram, which are used to highlight the improved performance of the proposed methods.

Keywords: Deconvolution problem; Fault diagnosis; Maximum correlated kurtosis deconvolution (MCKD); Minimum entropy deconvolution (MED); Particle swarm optimization (PSO); Rolling element bearing.