The Diagnosis Method of Stator Winding Faults in PMSMs Based on SOM Neural Networks. (May 2017)

• Record Type: Journal Article
• Authors: Chuang, Cao; Wei, Zhang; Zhifu, Wang; Zhi, Li
• Is Part Of: Energy procedia. Volume 105(2017)
• Page Start: 2295
• Page End: 2301
• Publication Date: 2017-05
• Subjects: fault diagnosis -- wavelet transform -- Self-organizing feature map -- artificial intelligence; Power resources -- Congresses; Power resources -- Periodicals; Power resources; Conference proceedings; Periodicals; 333.7905
• DOI: 10.1016/j.egypro.2017.03.663
• Languages: English
• ISSNs: 1876-6102

Abstract

Abstract: In this paper, the diagnosis method based on wavelet and neural network is proposed. This method needs not to collect a large number of data, but simplifies the diagnostic process while ensuring the accuracy of diagnostic result. The three-phase stator current data were decomposed by db6 wavelet function. It does not require the introduction of additional detection equipment, but also avoid the intrusion detection that may destruct the motor. This study has significance in engineering application to the development of on-line diagnosis system. The research on fault diagnosis system will promote the development of electric vehicle industry. As the improvement of safety control, it will accelerate the popularization of electric vehicles.