基于集合经验模态分解和多分类相关向量机的高压断路器机械故障诊断方法研究

Mechanical Fault Diagnosis of High-voltage Circuit Breaker Based on EEMD and M-RVM

作为电力系统中最重要的控制和保护设备的高压断路器,由于其故障中机械故障所占的比例最大,所以为了保证电力系统能够可靠地运行和电网质量的提高,有必要对高压断路器机械故障进行诊断及时了解其运行状态。通过对高压断路器分、合闸时产生的声波信号分析发现在声波信号中存在着大量的机械状态信息,因此可以依据声波信号的特征量对高压断路器机械故障进行诊断。通过集合经验模态分解方法提取高压断路器分闸过程中的声波信号特征量,并与多分类相关向量机相结合对高压断路器机械故障进行诊断,实验结果表明该方法具有良好的诊断效果。

High-voltage circuit breaker is the most important control and protection equipment in power system.Among all kinds of faults of high-voltage circuit breaker,mechanical faults occupy the largest proportion,thus,it is necessary to diagnose the operation state of the high-voltage circuit breaker in time in order to ensure the reliable operation of the power system and the improvement of the power grid quality.It is found that there is a lot of mechanical state information in the acoustic signal,which can be used to diagnose the mechanical fault of the high-voltage circuit breaker according to the characteristic value of the acoustic signal.In this paper,the EEMD method is used to extract the acoustic signal characteristic of the high-voltage circuit breaker,and it is combined with the multi-classification correlation vector machine(M-RVM)to diagnose the mechanical fault of the high-voltage circuit breaker.The experimental results show that the method has good diagnosis effect.