基于神经网络实现的自校正PID调节

本文讨论模型未知的离散系统基于神经网络实现的自校正ND调节。本文方法引入能在线评阶控制效果的评价函数，以在线选择神经网络PID调节器的学习样本并决定学习强度，使该调节器能够进行自组织地学习。计算机仿真结果表明，本文方法对模型未知的线性或非线性系统具有良好的调节特性。

Self-tuning PID Regulation Based on the Realization of Neural Networks

The self - tuning PID regulation based on the realization of neural networks for discrete systems with unknown models is discussed in this paper. In the new regulation method, an evaluating function which can evaluate the control effect is introduced to decide whether the on-line operate data can be chosen as the learning samples to train the neural net regulator and the learning strength, then the self-organized learning and control is realized. Simulation results show the effectiveness of the method.