Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Transactions of China Electrotechnical Society》 2015-24
Add to Favorite Get Latest Update

Stator Fault Diagnosis of Induction Motors Using the Optimal Wavelet Tree and Improved BP Neural Network

Shi Liping;Tang Jiasheng;Wang Panpan;Han Li;Zhang Xiaolei;China University of Mining and Technology;  
In order to accurately identify and eliminate the stator winding inter-turn short circuit fault of induction motors in time and guarantee the safe operation of electrical equipment, a novel method for fault diagnosis is proposed based on the optimal wavelet tree and predator search genetic algorithm(PSGA). Using the optimal wavelet tree combined with the characteristics of the fault current, the remnants of stator current signal is decomposed into different nodes after filtering out the fundamental component. As the input feature vectors of BP neural network, the energy range of each node represents the strongest intrinsic regularity of the fault signal. The BP neural network is used to solve the classification problem and the PSGA is taken to choose the initial weights and threshold of network, which will improve the speed and precision of network training. The final experimental results show that the proposed method can not only extract the better optimal feature vectors than wavelet package method but also accurately identify the three failure extent of motor stator inter-turn short circuit fault.
【Fund】: 教育部科学技术研究重大资助项目(311021)
【CateGory Index】: TM346
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved