Transformer fault diagnosis method based on TLR-ADASYN balanced dataset

Abstract

As the cornerstone of transmission and distribution equipment, power transformer plays a very important role in ensuring the safe operation of power system. At present, the technology of dissolved gas analysis (DGA) has been widely used in fault diagnosis of oil-immersed transformer. However, in the actual scene, the limited number of transformer fault samples and the uneven distribution of different fault types often lead to low overall fault detection accuracy or a few types of fault misjudgment. Therefore, a transformer fault diagnosis method based on TLR-ADASYN balanced data set is presented. This method effectively addresses the issue of samples imbalance, reducing the impact on misjudgment caused by a few samples. It delves deeply into the correlation between the ratio of dissolved gas content in oil and fault type, eliminating redundant informations and reducing characteristic dimensions. The diagnostic model SO-RF (Snake Optimization-Random Forest) is established, achieving a diagnostic accuracy rate of 97.06%. This enables online diagnosis of transformers. Comparative analyses using different sampling methods, various features, and diverse diagnostic models were conducted to validate the effectiveness of the proposed method. In conclusion, validation was conducted using a public dataset, and the results demonstrate that the proposed method in this paper exhibits strong generalization capabilities.