Since motor drive has wide applications in many fields,high reliability of motor drive is required in industrial applications.The Multi-phase motor has better reliability and fault tolerance performance than the three-phase motor,and its fault diagnosis technology has become a hot research.In this paper,five-phase fault-tolerant permanent-magnet motor of inter-turn short circuit fault is investigated.Support vector machine (SVM) and least squares support vector machines (LS-SVM)are analyzed and discussed.The multi-fault diagnosis clas-sifier is constructed and the multi-fault diagnosis model based on LS-SVM is established.The PSO algorithm is applied for parameter optimization.Test results show that LS-SVM method has improved the speed and precision. The feasibility of the short-circuit fault diagnosis method for five-phase fault-tolerant permanent-magnet motor is proved.%随着电机驱动系统的应用领域越来越广泛，对电机的安全性能提出越来越高的要求，多相电机比三相电机具有更好的可靠性和容错性，其故障诊断技术成为研究的热点。针对五相容错永磁电机的匝间短路故障进行研究，分析支持向量机（SVM）与最小二乘支持向量机（LS-SVM）在该电机匝间短路故障诊断中的应用机理，构造多故障诊断分类器，建立基于LS-SVM的多故障诊断模型，采用粒子群优化算法进行参数寻优，测试结果表明：LS-SVM方法在快速性和精度上均有所提高，证明此方法用于五相容错永磁电机匝间短路故障诊断的可行性。
展开▼
