Research on Stator Inter-turn Short Circuit Fault Diagnosis of Three-phase Asynchronous Motor Driven by Model-data Fusion

Faults in the stator windings of a three-phase asynchronous motor can cause abnormal operation of the motor，which in turn affects the stable operation of the entire power system equipment and even leads to major accidents.Based on this，taking the three-phase asynchronous motor as the research object，the stator inter-turn short-circuit faults of the motor are analyzed.In response to the problem of scarce motor fault data，a model-data fusion-driven fault diagnosis method is proposed.The fault data output by the finite element simulation model is used to train the fault diagnosis model based on the random forest algorithm，and the Bayesian optimization algorithm is introduced to optimize the model parameters.Experimental results show that，compared with other algorithms such as extreme learning machine，grey wolf algorithm optimized extreme learning machine，etc.，the Bayesian-random forest algorithm has the advantages of fast training speed，high accuracy，and less tendency to fall into local optimum.This proves that the three-phase asynchronous motor stator inter-turn short-circuit fault diagnosis method based on model-data fusion-driven has certain feasibility and practicability.