基于PCC的神经网络PID控制器设计

提出了一种基于可编程计算机控制器(PCC)的神经网络PID控制器,实现了以新一代PCC为硬件,利用神经网络逼近任意非线性函数的能力,对PID控制算法中的三个参数K_p,K_i,K_d进行在线调整,并利用神经网络模型对被控对象的输出值进行预测,根据预测值对神经网络各层中的加权系数进行在线修正,同时引入了带死区的控制算法;该控制方案具有调节速度快、适应能力强、可靠性高等优点;实验结果表明,该控制器具有强抗扰、响应快、鲁棒性好等特点。

Design of Neural Network PID Controller Based on PCC

A neural network Controller based on Programmable Computer Controller(PCC)is presented,it is using the neural network's capability to approach any nonlinear function to adjust the three parameters of the PID control method on line,and using the neural network model to predicate the object's outputs,then adjusting the weighting coefficient of the neural network based on the output,it also in- troduces the dead band control algorithm.It has the fast control speed,stronger adaptive ability and higher reliability.The result of the tests shows that this controller has the characteristics of a strong anti-interference,fast response and robustness in the actual application.