State Evaluation Method of Traction Transformer Based on Variable Weight Coefficient and Bayesian Network

Traction transformer is one of the core equipment of traction power supply system, and its safe and stable operation are very important for this electrified railway. In this paper, a comprehensive evaluation method combining variable weight coefficient with Bayesian network is proposed based on the information generated by various states of traction transformer during the operation. Firstly, the support and confidence of each single state quantity and comprehensive state quantity are calculated by association rule algorithm based on the historical statistical data of traction transformer, and the constant weight coefficient values of each state quantity are determined; secondly, the score of comprehensive state quantity is determined by the score values and constant weight coefficient of single state quantity; then, the comprehensive state quantity and operation performance are calculated and analyzed by the method of variable weight coefficient. The overall evaluation score and the comprehensive state quantity score were calculated by variable weight coefficient. Finally, Bayesian network method is used to analyze the relationship between state levels at different times, and the final evaluation results are obtained. In this paper, the state information of traction transformer in a railway substation is used to verify the model. The evaluation method proposed in this paper can accurately evaluate the operation status of traction transformer, so that the on-site operation and maintenance personnel can timely repair and maintain the transformer with abnormal operation, so as to achieve the purpose of saving costs and reducing safety risks.