摘要
针对工业控制领域中复杂非线性时变系统,提出了基于动态RBF神经网络辨识的单神经元PID控制方法。采用动态RBF神经网络辨识器在线辨识系统模型,获得PID参数在线调整信息,并由单神经元PID控制器完成控制器参数的在线自整定,实现系统的智能控制。仿真结果表明,与常规RBF神经网络辨识的PID控制方法相比,该方法具有控制精度高、响应速度快的优点,并且具备较强的自适应性和鲁棒性。
To complicated systems which are of characteristics of nonlinearity and time-variation in the industrial control fields, a self-adaptive single neuron PID control method was proposed based on the dynamic RBF neural network identification, which identified system model on-line by means of dynamic neural network identifier and acquired on-line tuning information of PID parameters, and the self-tuning of controller parameters was implemented by the single neuron controller, and the intelligence control of system was achieved. The simulation result indicates that the system, compared to PID control method based on the conventional RBF neural network, possesses the advantages of high precision, quick response speed and is of great adaptability and robustness.
出处
《系统仿真学报》
CAS
CSCD
北大核心
2006年第z2期804-807,共4页
Journal of System Simulation
基金
安徽省教育厅自然科学基金项目(2006KJ032B)
作者简介
刘寅虎(1974-),男,安徽池州人,硕士生,研究方向为智能控制在能量回馈系统中的应用; 李绍铭(1965-),男,河南洛阳人,副教授,硕导,研究方向为电力电子技术应用及自动控制.
