A Novel Approach to Transformer Fault Diagnosis Based on Transfer Learning

Abstract

Background: The condition of the power transformer directly affects the reliability and efficiency of the power system. The dissolved gas analysis (DGA) has been widely recognized as one of the effective methods in the field of transformer fault diagnosis. Objective: To tackle the problem of insufficient single transformer fault data and weak generalization ability of the diagnosis model, this paper proposes a transformer fault diagnosis model based on data cleaning and transfer learning. Methods: 21 kinds of dissolved gas characteristics of the to-be-diagnosed transformer (TDT) and auxiliary transformers (ATs)are selected as fault features to detect transformer fault. The first data cleaning is used for auxiliary fault data (AFD) based on similarity analysis between target fault data (TFD) and AFD. Then the TFD and AFD are all cleaned to remove the singular edge interference data for the second cleaning. The transfer learning algorithm is applied to extract effective information from AFD and train the fault diagnosis model. Results: Test results show that the proposed method can improve the efficiency of fault diagnosis and the accuracy of fault identification Conclusion: The two data cleanings complement each other and both play a role in eliminating bad data and ensuring the accuracy of the fault diagnosis. Transfer learning can effectively extract effective information from AFD and train a better transformer fault diagnotor to improve fault diagnosis accuracy.