针对电机故障诊断的特点,提出一种基于遗传神经网络(BP)进行异步电机故障检测的新方法。针对神经网络易陷入局部最小点的固有缺点,采用遗传算法(Genetic Algorithm,简称GA)对神经网络初始权值进行全局优化。实践证明该方法可以有效地实现对异步电机的故障诊断,且易于实现,有一定实用价值。
To the characteristic of motor fault diagnosis, this paper proposed the motor fault diagnosis new method based on genetic neural network. Genetic algorithm (GA) was used to optimize the initial weights in global view to avoid the inherent defect of local minimal points. The experiments could realize the fault diagnose of asynchronous motors, and proves that this method is correct and effective.