Fault Diagnosis Method of PMSM Based on Adaptive Dynamic Cat Swarm Optimization of SVM

Authors

Wang Yan, Engineering Research Center of Internet of Things Technology Applications Ministry of Education, Wuxi 214122, China;
Wang Xin, Engineering Research Center of Internet of Things Technology Applications Ministry of Education, Wuxi 214122, China;
Zhicheng Ji, Engineering Research Center of Internet of Things Technology Applications Ministry of Education, Wuxi 214122, China;
Dahu Yan, Engineering Research Center of Internet of Things Technology Applications Ministry of Education, Wuxi 214122, China;

Abstract

Abstract: In order to solve the problems of common inter-turn short circuit faults of permanent magnet synchronous motor (PMSM), a corresponding motor fault model based on the existing basis of PMSM is established. The eigenvector is extracted by energy spectrum analysis. The penalty factor and RBF-kernel parameter of SVM are optimized by adaptive dynamic cat swarm optimization (ADACSO) algorithm. The optimized SVM is adopted to motor fault diagnosis. The eigenvector obtained by energy spectrum analysis is taken as sample data to conduct simulation experiment. The experiment results indicate that, compared with other optimization algorithms, using ADACSO to optimize SVM parameters can improve the accuracy of SVM in fault diagnosis of PMSM.

Recommended Citation

Yan, Wang; Xin, Wang; Ji, Zhicheng; and Yan, Dahu (2020) "Fault Diagnosis Method of PMSM Based on Adaptive Dynamic Cat Swarm Optimization of SVM," Journal of System Simulation: Vol. 29: Iss. 11, Article 38.
DOI: 10.16182/j.issn1004731x.joss.201711038
Available at: https://dc-china-simulation.researchcommons.org/journal/vol29/iss11/38

First Page

2881

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.201711038

Last Page

2889

CLC

TP18;TM341

Recommended Citation

Wang Yan, Wang Xin, Ji Zhicheng, Yan Dahu. Fault Diagnosis Method of PMSM Based on Adaptive Dynamic Cat Swarm Optimization of SVM[J]. Journal of System Simulation, 2017, 29(11): 2881-2889.

DOI

10.16182/j.issn1004731x.joss.201711038