Research Area:  Metaheuristic Computing

Abstract:

This article proposes an effective rotor fault diagnosis model of an induction motor (IM) based on local mean decomposition (LMD) and wavelet packet decomposition (WPD)-based multilayer signal analysis and hybrid genetic binary chicken swarm optimization (HGBCSO) for feature selection. Based on the multilayer signal analysis, this technique can reduce the dimension of raw data, extract potential features, and remove background noise. To compare the validity of the proposed HGBCSO method, three well-known evolutionary algorithms are adopted, including binary-particle swarm optimization (BPSO), binary-bat algorithm (BBA), and binary-chicken swarm optimization (BCSO). In addition, the robustness of three classifiers including the decision tree (DT), support vector machine (SVM), and naive Bayes (NB) was compared to select the best model to detect the rotor bar fault. The results showed that the proposed HGBCSO algorithm can obtain better global exploration ability and a lower number of selected features than other evolutionary algorithms that are adopted in this research. In conclusion, the proposed model can reduce the dimension of raw data and achieve high robustness.

Keywords:  
rotor
fault diagnosis
local mean decomposition
wavelet packet decomposition
chicken swarm optimization
feature selection

Author(s) Name:  Chun-Yao Lee, Guang-Lin Zhuo

Publisher name:  MDPI

DOI:  10.3390/sym13030487

Volume Information:  13(3), 487

Paper Link:   https://www.mdpi.com/2073-8994/13/3/487