摘要
该文提出了一种串联型模糊神经网络PID控制器的设计方法 ,该方法利用人工神经元网络的聚类功能来对反馈回来的误差输入量进行分类 ,然后串联一个模糊控制器 ,并根据人工神经网络的分类结果来构造模糊规则库 ,使整个控制器既具有PID调节的功能 ,同时避免了神经元网络的发散问题 ,并解决了模糊规则库构造的困难 ,从而实现对PID控制器参数的智能调节。
This paper presents a method to design PID controller with fuzzy and neural network which adopts neural network's clustering function to classify the error input, then link a fuzzy controller in form of series which rules are made through the classified result. The controller with the regulation function of PID can avoids the radiation problem of neural network and difficulty of making the fuzzy rulers so as to implement the intelligence modulation.
出处
《计算机仿真》
CSCD
2002年第4期50-52,共3页
Computer Simulation
