Arcing Faults Detection in Switchgear with Extreme Learning Machine

Abstract The robustness of switchgears has critical impacts on the general efficiency power distribution systems. Faulty lead to many unwanted complications for utility bodies, which in turn even bigger issues. In this paper, a remote arcing fault sensing technique is proposed using ELM. By analysing sonic waves emitted, method capable detect possible faults switchgears. Tests and experiments have been conducted investigate performance algorithm detecting these faults. obtained results are analysed time frequency domains. domain analysis, show 93.75% success rate training stage, 95.83% validation 87.5% testing stage. 91.67% 100% It thus concluded that identify