中文摘要：

利用神经网络自学习的特性,结合常规PID（比例-积分-微分）控制理论,提出基于BP（back propaga-tion）神经网络进行PID参数整定的控制策略.该方案能实现控制器参数的自动调整,以及在线调节参数Kp,Ki,Kd,适应被控过程的时变性,提高控制的性能和可靠性.仿真结果表明：相对于传统的PID控制方法,神经网络PID控制系统取得更满意的控制效果.

英文摘要：

Using the self-learning characteristic of neural network,combining with conventional PID（proportional integral differential） control theory,the PID parameter tuning strategy based on the BP（back propagation）neural network is proposed in this paper.This strategy can achieve automatic adjustment of the controller parameters,as well as adjust the parameters Kp,Ki,Kd online to adapt to the time variability of the controlled process,and also improve the performance and reliability of the control.Simulation results show that： compared with the traditional PID control method,the neural network PID control system can achieve a more satisfactory control effect.