基于因子分析和支持向量机算法的高压断路器机械故障诊断方法

Diagnosis Method on the Mechanical Failure of High Voltage Circuit Breakers Based on Factor Analysis and SVM

高压断路器操作过程中的振动信号能够反映断路器的机械状态。以高压断路器机械振动信号中振动事件的起始点作为特征参量,使用因子分析对特征量进行降维优化、支持向量机(Support Vector Machine,SVM)经粒子群参数寻优(Particle Swarm Optimization,PSO)后可对断路器的不同状态进行分类。本文对断路器机械故障进行了模拟试验,结果表明,因子分析和支持向量机算法适于诊断高压断路器的机械状态。

The mechanical state of high voltage circuit breaker can be reflected by its vibration signals during operation. The starting moment of vibration events extracted from the vibration signal can be taken as the characteristic parameter. The factor analysis can optimize and reduce the dimension of the characteristic parameters. The support vector machine(SVM) optimized by particle swarm optimization(PSO) can classify the different states of the circuit breaker. Several mechanical failures of circuit breaker are simulated and the results show that the factor analysis and SVM are suitable for mechanical state diagnosis of high voltage circuit breaker.