A Detailed Analysis of Data Mining Procedures for Problem Detection In Energy Rcd Systems

Abstract

Critically important early recognition of failures within electrical electrical appliances (PESs) to guarantee reliability is an obstacle that has garnered a great deal attention recently. After examining diverse literature on defect detection in PESs, this study introduces data mining-based techniques include deep learning computations, learning from data, and artificial neural networks. Then, in PESs, the defect detection process is described by adding signal measuring sensors and how to extract the characteristic from them. Finally, the efficacy of various data mining algorithms in detecting PESs flaws is evaluated based on research. The assessment findings reveal that deep learning-based techniques with being able to extract features from measured signals are markedly more effective than alternative techniques and serve as an appropriate device for the prospective applications in the power electronics sector are discussed