Online monitoring and diagnosis of high voltage circuit breaker faults: feature extraction analysis of vibration signals

International journal of metrology and quality engineering

article

Long Li¹  Jianfeng Xiao¹  Bin Wu¹  Mengge Zhou¹  Qian Wang¹ 

[1] Electric Power Research Institute, State Grid Chongqing Electric Power Company

关键词: High voltage circuit breaker;    vibration signal;    feature extraction;    wavelet packet energy entropy;   

DOI  :  10.1051/ijmqe/2019012

学科分类：土木及结构工程学

来源: EDP Sciences

【 摘 要 】

The development of power grid system not only increases voltage and capacity, but also increases power risk. This paper briefly introduces the feature extraction method of the vibration signal of high voltage circuit breaker and support vector machine (SVM) algorithm and then analyzed the high voltage circuit breaker in three states: normal operation, fixed screw loosening and falling of opening spring, using the SVM based on the above feature extraction method. The results showed that the accuracy and precision rates of fault identification of circuit breaker were the highest by using the wavelet packet energy entropy extraction features, the false alarm rate was the lowest, and the detection time was the shortest.

【 授权许可】

CC BY