Fault prediction and maintenance of urban rail transit power supply system based on big data

In order to guarantee the normal operation of urban rail transit system, the research constructs the fault prediction system of urban rail transit power supply system, analyzes the equipment failure rate under each weather condition, and constructs the Monte Carlo-based traction power supply fault simulation model. After the fault ranging of the traction power supply system, the fault prediction reasoning is carried out. The fault prediction method of this paper is used in the prediction of contact network wear, and its prediction effect on the degree of contact network wear is initially explored. The prediction method of this paper is compared with other methods, and three exogenous faults are predicted to verify the performance of the fault prediction method of this paper. Finally, the fault prediction system of this paper is utilized to diagnose and predict the reactor insulation faults, and the maintenance decision-making method is proposed. The prediction method in this paper achieves the best prediction results in contact network abrasion prediction, contact network lightning trip fault prediction, floating object infestation contact network fault prediction and haze fouling flash fault prediction. In reactor insulation fault prediction, the method in this paper can accurately determine the reactor front-end grounding and accurately predict the degree of grounding insulation degradation.