摘要
提出一种新型神经网络结构的PID控制器（N－PID）。该控制器将神经网络和PID控制规律融为一体，既具有常规PID控制器结构简单、参数物理意义明确之优点，又具有神经网络自学习、自适应之能力。并给出N－PID控制器的结构、计算公式及二阶对象下系统的仿真结果。
A new type of neural network structure proportional - integral - derivative(N - PID) controller is proposed. The N - PID is a combination of the neural network and the PID rule. It has an input layer, a hidder layer and an output layer, and its hidder layer units are proportional, integral and derivative units.The N - PID has advantages of both neural network and PID algorithm. It is proved by computer simulation program that N - PID controller has very good dynamic and static properties.
出处
《电气传动自动化》
1999年第2期29-32,共4页
Electric Drive Automation
基金
陕西省教委科研基金
