Transformer fault diagnosis method based on ATT-CNN-Bi-LSTM

With the advancements in online monitoring technology for power equipment, real-time monitoring of transformers has become feasible. It is of immense significance to assess and predict the operational status of transformers in real-time. This paper introduces a methodology that utilizes ATT-CNN-Bi-LSTM for diagnosing the state of transformers. The proposed approach involves preprocessing transformer monitoring data and historical operation and maintenance data acquired from the central control station. It conducts initial feature extraction on fault data and extends overall state features from local state features using Bi-LSTM to achieve transformer state assessment. Through experimental comparative analysis, the method put forward in this paper effectively addresses the limitations of traditional deep learning methods, such as dependence on extensive data and low accuracy, which significantly enhances the predictive capability of transformer fault diagnosis.