A Decentralized Equivalent Circuit Modeling of Power Transformer Winding using Frequency Response Analysis and Artificial Intelligence

Frequency response analysis (FRA) has been accepted as a broadly used tool for the power transformer winding diagnosis. Therefore, the interpretation of FRA results has challenges still. Nowadays, the newly developing artificial intelligence (AI) based algorithms provide an accepted interpretation. Most of reported studies are directly input into the construction of Electrical Equivalent Circuit Model (EECM) basing on AI. In this context, this study proposes a new methodology to construct a decentralized EECM from three frequency sub-bands (low, medium, and high frequency) separately basing on JAYA algorithm. The proposed study is applied on a real transformer winding to show its effectiveness.