作者：赵四化, 王琪

作者单位：成都电子机械高等专科学校, 四川成都 610031

关键词：异步电机; 模式识别; 故障诊断; 统计学习理论; 支持向量机

摘要：

提出了一种基于支持向量机的鼠笼式电机转子断条故障检测方法,通过对电机转子断条故障进行实验模拟,获取了采样信号,利用支持向量机(SVM)对故障样本进行训练,使得支持向量机(SVM)具有分类功能。最后,采用支持向量机(SVM)对电动机各种转子断条故障进行诊断分类,取得较满意的结果。

Application study on support vector machine in rotor fault diagnosis and recognition

ZHAO Si-hua, WANG Qi

Chengdu Electronic and Mechanism Altitude School, Chengdu 610031, China

Abstract: Squirrel-cage rotor broken bars fault detection method was put forward based on support vector machines. Through the simulation experiment of rotor broken bars fault, getting the experimental sample signal, using support vector machine(SVM) to carry out failure sample training, support vector machine(SVM) had the classification function. Finally, using support vector machine(SVM) to fault diagnose and classify of variety electric rotors broken bars, achieve more satisfactory results.

Keywords: Asynchronism motor; Pattern recognition; Fault diagnosis; Statistical learning theory; Support vector machines

2009, 35(3): 121-124  收稿日期: 2008-11-17;收到修改稿日期: 2009-1-13

基金项目: 

作者简介: 赵四化(1963-),男,副教授,研究方向为电气自动化。

参考文献

[1] Deng X,Ritchie E, Jokinen T. An improved knowledge base of a fuzzy logic system for an induct ion motor with rotor faults[C]. Proceedings of C ICEM'95,Hangzhou,1995: 901-905.
[2] Cao Z, Ritchie E. Rotor fault diagnosis of induction motor based on a dynamic associative memory of chaotic neural network[C]. Proceedings of ICEM 2000,2000:863-867.
[3] Filip Mulier. Vapnik-chervonenk is(VC) learning theory and its applications[J]. IEEE Trans. on Neural N etworks,1999,10(5):31-36.
[4] Vapnik V. Nature of statistical learning theory[M]. New York:JohnWiley and Sons,Inc.
[5] 张学工,译.统计学习理论的本质[M].北京:清华大学出版社,2000.
[6] Corinna C, Vapnik V. Support vector network[J]. Machine Learning, 1995(20):273-297.
[7] 张周锁,李凌均,何正嘉.基于支持向量机的多故障分类器及应用[J].机械科学与技术,2004,23(5):536-538.
[8] 张学工.关于统计学习理论与向量机[J].自动化学报,2000,26(1):32-34.
[9] 阎威武,邵惠鹤.支持向量机和最小二乘支持向量机的比较及应用研究[J].控制与决策,2003,18(3):358-360.
[10] Vapnik V N. The nature of statistical learning theory[M]. New York:Springer-Verlag,1995.