一种基于神经网络的非线性复合PID控制器  

A Nonlinear Composite PID Controller Based on Neural Network Algorithm

作　　者：周旭[1] 曾喆昭[1] 

机构地区：[1]长沙理工大学电气与信息工程学院,湖南长沙410076

出　　处：《工业控制计算机》2013年第2期55-57,共3页Industrial Control Computer

摘　　要：针对非线性、不确定对象难以控制的问题,提出了一种基于神经网络的非线性复合PID控制器,该PID控制器采用一次和二次多项式分别构成的非线性函数来模拟PID的比例、积分和微分参数随误差变化的曲线,通过神经网络算法实时调整三个非线性函数的权值系数。将线性的比例、积分、微分运算单元和非线性比例、积分、微分运算单元一共6个运算单元分别融入到隐层神经元中,从而构造了将复合PID控制与神经网络控制融为一体的智能控制器。经过Matlab仿真验证,该控制系统的超调小,调节时间短,精度高,方法可行。因此,该控制器在工业领域具有广泛的应用前景。For the problem of nonlinear uncertain objcts is difficult to control,this paper proposes a neural network-based nonlinear composite PID controller.The PID controller used the nonlinear function which constitute respectively by first degree and quadratic polynomial to simulating the curve of PID proportional,integral and derivative parameters changing with error.Adjust the weights value of the three nonlinear function coefficient real-time by the neural network algorithm,and put the linear proportional,integral,differential operation unit and nonlinear proportional,integral,differential operation unit for a total of six arithmetic unit into the hidden layer neurons,so as to construct an intelligent controller which composite by PID control and neural network control.

关 键 词：神经网络 非线性复合PID 激励函数 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程] TP183[自动化与计算机技术—控制科学与工程]