BP神经网络可有效地记忆模糊控制规则,并以“联想记忆”方式使用这些经验.然而,现有前向网络学习算法不可避免地存在局部极小问题,同伦连续BP算法可有效地解决BP网络的全局收敛性问题,同时使网络具有很快的收敛速度.为了进一步提高控制系统的精度和抗干扰能力,本文设计了一种参数自调整ANN一PI控制器.实验结果表明,这种控制器动态响应快,控制精度高,抗干扰能力强,对参数变化不敏感,具有一定的鲁棒性. BP neural network can effectively memorize the fuzzy control rules and use these experiences in the form of “associative memory.” However, the existing forward-oriented network learning algorithms inevitably have local minima, and the homotopy continuous BP algorithm can effectively solve the problem of BP In order to further improve the accuracy and anti-interference ability of the control system, a parameter self-adjusting ANN-PI controller is designed in this paper.The experimental results show that this control Fast dynamic response, high control accuracy, anti-interference ability, insensitive to parameter changes, with a certain degree of robustness.