基于支持向量机的异步电机故障诊断系统

作者：杨俊，吴建华 日期：2008-02-25/span> 浏览：3344 查看PDF文档

基于支持向量机的异步电机故障诊断系统

杨俊，吴建华
（浙江大学 电气工程学院，浙江 杭州 310027）

摘要：电机故障将造成巨大的经济损失，甚至于人身安全。一个准确的故障诊断系统能够最大程度地降低风险，有利于生产、生活的正常进行。阐述了支持向量机(SVM)及最小二乘支持向量机(LSSVM)算法的原理，研究了基于LSSVM的异步电动机故障诊断，比较了正常状况与3类故障的不同，并对3类故障进行了自动分类，测试了分类结果。实验表明，基于SVM的异步电机故障诊断可靠性好，实用性强，验证了SVM的优越性。
关键词：故障诊断；支持向量机；最小二乘支持向量机
中图分类号：TM343；TP806+.3文献标识码：A文章编号：1001-4551(2008)01-0072-03

Fault diagnosis system of induction motor based on SVM
YANG Jun, WU Jianhua
(College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China)
Abstract: The motor fault will bring great loss in economy and safety. An accurate fault diagnosis system can reduce the risk in great degree. It is favor of normal life and production.The principle of support vector machine(SVM) and least square support vector machine (LSSVM) algorithm were described. An induction motor fault diagnosis experiment using LSSVM was investigated, based on comparing normal state with three different artificial faults, automatically classifying the three faults, and testing the classification results. Experimental results indicate the high reliability and practicality of SVM induction motor fault diagnosis, and validate the advantage of SVM.
Key words: fault diagnosis; support vector machine (SVM); least squavessupport vector machine (LSSVM)
参考文献(Reference):
［1］沈标正.电机故障诊断技术［M］.北京：机械工业出版社，1996.
［2］陆颂元,汪江,刘晓峰,等.关于当前国内故障智能诊断研究中的若干问题［J］.汽轮机技术,2003,45(5):257-259.
［3］曹建伟.电机故障诊断专家系统及其应用［J］.中国设备管理,2001（3）:37-38.
［4］ZHANG Sheng, ASAKURA T, XV Xiaoli, et al. Fault Diagnosis System for Rotary Machines based on Fuzzy Neural Networks［C］//Preceedings of AIM 2003. Beijing: ［s.n.］,2003:199-204.
［5］曹志彤,陈宏平,何国光.电机故障诊断支持向量机［J］.仪器仪表学报,2004,25(6):738-741
［6］PELCKMANS K, JAK S, GESTEL T V, et al. LSSVM Lab Toolbox Users Guide［EB/OL］. ［2003-02-06］. http://www.esat.kuleuven.ac.be/sista/lssvmlab/tutorial/tutorial1-5.pdf.
［7］CRISTIANINI N, TAYLO J S.支持向量机导论［M］.北京:电子工业出版社,2004.
［8］NANDI S, TOLIYAT H A. Condition Monitoring and Fault Diagnosis of Electrical Machines—A Review［C］//Industry Applications Conference. USA: ［s.n.］,1999:197-204.
［9］HSU C W, CHANG C C, LIN C J. A Practical Guide to Support Vector Classification［EB/OL］.［ 2003-07-11］. http://www.csie.ntu.edu.tw/~cjlin/libsvm.
［10］PZYHZNEN S. Support Vector Machine based Classification in Condition Monitoring of Induction Motor［D］. Finland: Helsinki University of Technology,2004.