基于支持向量机的矿用电机故障诊断

提出一种基于电流信号频谱分析和支持向量机(SVM)的矿用感应电机早期故障诊断方法。对定子电流采样后,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算法和混合矩阵组合策略构造了多故障SVM分类,对不同类型的故障进行诊断和分类。实验结果表明,该方法能够有效解决电机故障诊断中小样本集、非线性、高维数时的故障分类问题,提高电机故障诊断的准确性。

Mine-used Motor Fault Diagnosis Based on Support Vector Machine

A method based on Motor Current Signal Analysis(MCSA) and Support Vector Machine(SVM) was presented and applied to the early faults diagnosis in induction motors used in the mine.After the stator current being sampled,the fault feature was extracted from the sampling data through FFT and used as the input of the SVM.A multi-class fault classifier was constructed to identify different faults,which was based on one to one algorithm and mixed matrix combination.Experiment results show that Support Vector Machine(SVM) has good performance for classifying non-linear and high dimension and small sample set.This method improves the accuracy in rotor fault diagnosis.