Corona fault detection in switchgear with extreme learning machine

Sanuri Ishak, Siaw-Paw Koh, Jian-Ding Tan, Sieh-Kiong Tiong, Chai-Phing Chen

Abstract


Switchgear is a very important component in a power distribution line. Failure in a switchgear can lead to catastrophic danger and losses. In this research, a fault detection system is proposed with the implementation of Extreme Learning Machine (ELM). This algorithm is capable to identify faults in a switchgear by analyzing the sound wave generated. Experiments are carried out to investigate the performance of the developed algorithm in identifying Corona faults in switchgears. The performances are analyzed in time and frequency domains, respectively. In time domain analysis, the results show 90.63%, 87.5%, and 87.5% of success rates in differentiating the Corona and non-Corona cases in training, validation and testing phases respectively. In frequency domain analysis, the results show 89.84%, 83.33%, and 87.5% success rates in training, validation and testing phases respectively. It can thus be concluded that the developed algorithm performed well in identifying Corona faults in switchgears.

Keywords


Categorization; Corona discharge; Extreme learning machine; Switchgear faults

Full Text: PDF

Refbacks

  • There are currently no refbacks.


Bulletin of EEI Stats