提出了一种基于遗传算法和小波神经网络的 PI 参数整定方法。首先 ,利用具有自然进化的遗传算法对小波神经网络的初始权值进行优化训练 ,解决了控制器网络初始权系数对控制效果产生的影响 其次 ,利用小波神经网络对PID参数进行在线调节 最后将此算法运用到电机控制系统的 P I D参数寻优中。-A new-type controller based on genetic algorithm andwavelet neural net work was presented.The genetic algorithm was

utilized to train and optimize the initia weights of wavelet neuralnet work, the method solved the influence of the initial weights of wavelet neural net work on the control effectiveness.