Aiming at the shortcomings of ball and plate systemsuch as severe PID control oscillationtedious manual PID tuning and poor dynamic qualitya scheme combining Wavelet Neural Network (WNN) identification with WNN-PID self-tuning parameters is studied.Firstlyaccording to the strong coupling characteristics of ball and platea ball and plate system model consisting of two parts is established by Lagrange equation.SecondlyWNN-PID controller is constructed to overcome the problems of tedious manual tuning and poor stability of PID.Considering that gradient descent method and fixed learning rate are easy to fall into extreme valuethe momentum gradient and AdaDec algorithm are used to accelerate the training speed of the network.Thenthe convergence of the system is verified by Lyapunov stability theory.Finally the Matlab simulation shows that the stability and robustness of the proposed stragegy in ball and plate system are better than those of conventional PID and BP-PID strategies.