基于支持向量机的电机故障诊断方法综述  

Review of Motor Fault Diagnosis Based on Support Vector Machines

作　　者：蒋波涛 张博[1] 黄新波[1] JIANG Botao, ZHANG Bo, HUANG Xinbo(School of Electronics and Information, Xi＇an Polytechnic University, Xi＇an 710048, Chin)

机构地区：[1]西安工程大学电子信息学院,西安710048

出　　处：《微电机》2018年第7期58-61,67,共5页Micromotors

基　　金：陕西省教育厅专项科研计划项目(15JK1297);西安工程大学博士科研启动基金项目(BS1339)

摘　　要：基于统计学理论的支持向量机因其具有良好的学习性能和泛化能力,而被国内外学者广泛地应用于电机故障诊断领域。对现有应用于电机故障诊断的各种支持向量机模型的特点进行了系统的分析,包括标准型支持向量机、最小二乘支持向量机以及和其相关的混合模型,并对未来电机故障诊断方法的研究发展方向进行了总结和探讨。Support vector machines（ SVMs） based on statistical learning theory are widely used in the field of motor fault diagnosis because of their good learning performance and generalization ability. The characteristics of various support vector machine models used in motor fault diagnosis were analyzed systematically,including the standard support vector machine,the least squares support vector machine and the related hybrid model. The development direction of the future motor fault diagnosis method was summarized and discussed.

关 键 词：电机故障诊断 标准支持向量机 最小二乘支持向量机 

分 类 号：TM307.1[电气工程—电机]