Fault Classification System for Switchgear CBM from an Ultrasound Analysis Technique Using Extreme Learning Machine

Currently, the existing condition-based maintenance (CBM) diagnostic test practices for ultrasound require tester to interpret results manually. Different testers may give different opinions or interpretations of detected ultrasound. It leads wrong interpretation due depending on experience. Furthermore, there is no commercially available product standardize data. Therefore, objective correct an ultrasound, which one CBM methods medium switchgears, by using artificial neural network (ANN), more accurate when assessing their condition. Information and from various switchgears were gathered in order develop classification severity corona, surface discharge, arcing inside switchgear. The data segregated based defects found during maintenance. In total, 314 cases normal, 160 149 tracking, 203 collected. Noise was removed before uploading it as a training process ANN engine, used extreme learning machine (ELM) model. developed AI-based switchgear faults system designed incorporated with feature scalability can be tested replicated other conditions. A customized graphical user interface (GUI), Ultrasound Analyzer System (UAS), also developed, enable users obtain condition output via screen. Hence, decision-making this analysis made prioritize urgency remedial works.