一种基于神经网络算法的非线性PID控制器  

A nonlinear PID controller based on neural network algorithm

作　　者：李桂梅[1] 曾喆昭[2] 

机构地区：[1]湖南商学院计算机与电子工程学院,湖南长沙410205 [2]长沙理工大学电气与信息工程学院,湖南长沙410076

出　　处：《中南大学学报（自然科学版）》2010年第5期1865-1870,共6页Journal of Central South University:Science and Technology

基　　金：湖南省科技计划项目(2010GK3035;2009GK3186);湖南省教育厅重点项目(08A006);长沙市科技计划项目(K0904040-11)

摘　　要：针对非线性、不确定时滞对象,提出一种基于神经网络算法的非线性PID控制器。该控制器将传统PID的比例、积分和微分参数分别构造成关于误差信号的非线性函数,并将非线性比例运算单元、非线性积分运算单元和非线性微分运算单元分别作为隐层神经元的激励函数,从而构造将PID控制与神经网络控制融为一体的智能控制器。研究结果表明:采用此智能控制器有效解决了传统PID难以控制非线性对象的问题以及传统神经网络控制器隐层神经元节点数难以确定的问题,仿真结果验证了该智能控制器的有效性。Aiming at nonlinear and uncertain time-delay objects,a nonlinear PID controller based on neural network algorithm was proposed.The controller used nonlinear proportional,nonlinear integral and nonlinear differential functions on error signal as proportional,integral and differential parameters of traditional PID controller,and used nonlinear proportional operation unit,nonlinear integral operation unit and nonlinear differential operation unit as excitation functions of hidden layer neurons,which consists of PID controller and neural network controller.The results show that the intelligent controller effectively solves the control problem of nonlinear object and the problem of number of neurons of hidden layer and it is difficult for the traditional PID controller to solve and determine.Simulation results show the effectiveness of the intelligent controller.

关 键 词：神经网络 PID控制器 非线性控制 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]