基于模糊BP网络的自适应PID控制

针对经典PID控制的参数不能在线调整的缺陷,提出了一种基于模糊BP神经网络的PID控制算法,采用模糊规则自动地调节BP神经网络训练过程的学习参数,利用神经网络较强的学习能力和模糊控制在模型未知或不精确前提下的控制能力,将其应用到PID控制中1],实现了PID控制参数的在线调整和优化,并对其在非线性离散系统中的应用进行了仿真。实验结果表明该算法性能优良,加快了系统响应速度,减少了超调量,适用于纯滞后非线性系统。

Self-adapting PID controller based on fuzzy BP algorithm

According to the defects that the parameters of classical PID controller can not be adjusted on line,a PID controller based on fuzzy BP algorithm of neural network was presented,by using fuzzy rules to automatically regulate the learning parameters in training of BP neural network,using the powerful self-learning ability of neural network and the fuzzy control ability in the unknown or imprecise model.It was applied in the PID controller and the online adjusting and optimizing for the PID controller parameter were realized.The above algorithm which was applied to the nonlinear discrete-time systems was simulated on Matlab.The experimental results show that the algorithm has a good performance,fast response and small overshoot.It is suitable for pure lag nonlinear systems.