摘  要：构建了两种基于BP神经网络和支持向量机的的永磁直流电机故障模式识别分类器，并对该两种模式识别分类器在永磁直流电机故障诊断中的应用进行了实验研究与理论分析。研究结果表明：基于支持向量机的永磁直流电机故障模式识别方法在小样本情况下的诊断正确率高于基于BP神经网络，最好能达到94.6667%，且不存在局部极小值问题和过学习问题。
关键词：永磁直流电机；支持向量机；BP神经网络；模式识别；故障诊断

Abstract: Fault diagnosis method based on SVM (Support Vector Machine) and BP were developed for permanent magnetic DC motor. The fault diagnosis results of this method in cases where only limited training samples are available were compared with that of another classification algorithm BP ANN. It shows that SVM have better performance than ANN both in training speed and recognition rate and its greatest rate gets to 94.6667%. SVM can also avoid over-fitting and trapping in local extreme which often happened in the neural networks algorithm, especially in case of limited trained samples.
Key words: permanent magnetic DC Motor; support vector machines; BP; failure recognize; failure diagnosis