Kolmogorov–Arnold Network in the Fault Diagnosis of Oil-Immersed Power Transformers

Abstract

Instabilities in energy supply caused by equipment failures, particularly in power transformers, can significantly impact efficiency and lead to shutdowns, which can affect the population. To address this, researchers have developed fault diagnosis strategies for oil-immersed power transformers using dissolved gas analysis (DGA) to enhance reliability and environmental responsibility. However, the fault diagnosis of oil-immersed power transformers has not been exhaustively investigated. There are gaps related to real scenarios with imbalanced datasets, such as the reliability and robustness of fault diagnosis modules. Strategies with more robust models increase the overall performance of the entire system. To address this issue, we propose a novel approach based on Kolmogorov–Arnold Network (KAN) for the fault diagnosis of power transformers. Our work is the first to employ a dedicated KAN in an imbalanced data real-world scenario, named KANDiag, while also applying the synthetic minority based on probabilistic distribution (SyMProD) technique for balancing the data in the fault diagnosis. Our findings reveal that this pioneering employment of KANDiag achieved the minimal value of Hamming loss—0.0323—which minimized the classification error, guaranteeing enhanced reliability for the whole system. This ground-breaking implementation of KANDiag achieved the highest value of weighted average F1-Score—96.8455%—ensuring the solidity of the approach in the real imbalanced data scenario. In addition, KANDiag gave the highest value for accuracy—96.7728%—demonstrating the robustness of the entire system. Some key outcomes revealed gains of 68.61 percentage points for KANDiag in the fault diagnosis. These advancements emphasize the efficiency and robustness of the proposed system.