Fault diagnosis model of high-speed railway traction transformer based on SSA-RF

Abstract

Real time and accurate grasp of the health of traction transformer is one of the effective means to avoid large-scale railway powe failure. In order to better diagnose the fault of high-speed railway traction transformer equipment, combined with the actual railway maintenance operation, a transformer fault diagnosis model based on random forest is proposed, and the fault diagnosis process is optimizer by sparrow search algorithm. Firstly, the fault characteristics of high-speed railway transformer are extracted and data preprocessed, there the random forest model is used to accurately evaluate the transformer fault state, and the sparrow search algorithm is used to optimize the parameters of the random forest model, so as to ensure the optimal SSA-RF model for fault diagnosis. The example shows that the RF mode has higher diagnostic accuracy, and the diagnostic accuracy of the RF model optimized by SSA is further improved. It has certain practica application value.