Research of motor fault diagnosis based on the improved genetic algorithm and BP network

According to the complexity and coupling of steam turbine-generator, the diagnosis model based on improved genetic algorithm and BP network is proposed in this paper. First, the time factor is considered in the fitness function of genetic algorithm, then use the adaptive crossover rate and mutation rate to improve the genetic algorithm. As soon as the improved genetic algorithm optimizes the initial weights and bias values, the BP network trains and diagnoses aim at the fault samples. After experience analysis, this model can well solve the convergence rate and local minimum trouble of the tradition BP network, and the results show there are great advancements in training rate and diagnosing accuracy.