基于MCSA和SVM的异步电机转子故障诊断

本文提出一种基于电机电流信号频谱分析和支持向量机的异步电机转子故障诊断方法，该方法可以利用支持向量机对电机电流频谱信号的特征信息和故障模式进行关联。对电机定子电流采样后，其信号经FFT变换后提取故障特征量作为支持向量机的输入，基于1对1算法构造了感应电机转子故障多类分类器。实验结果表明，该方法具有很好的分类和泛化能力，可以提高电机故障诊断的准确性。

Fault diagnosis for rotor of induction machine based on MCSA and SVM

A fault diagnosis method for induction machine is presented, which is based on motor current signal analysis (MCSA) and support vector machine (SVM). This method correlates the motor current spectrum characteristic and the fault mode using SVM. The stator current is sampled, the fault spectrum is extracted from the sampling data through FFT, and the spectrum data are used as the input of the SVM. A multi-class fault classifier is constructed based on one to one strategy to identify different rotor faults. Experiment results show that this method has good classification and generalization ability, and improves the accuracy in rotor fault diagnosis of induction machine.