基于阻尼最小二乘法的神经网络预测偏差补偿自校正控制器  

SELF-TUNING CONTROLLER FOR NEURAL NETWORK PREDICTIVE DEVIATION COMPENSATION BASED ON DAMPED LEAST SQUARE

作　　者：林茂琼[1] 陈增强[1] 袁著祉[1] 

机构地区：[1]南开大学计算机与系统科学系,天津300071

出　　处：《信息与控制》2000年第1期27-33,共7页Information and Control

基　　金：天津市自然科学基金资助研究!(9836 0 2 11)

摘　　要：本文提出一种神经网络预测偏差补偿自校正控制器 ,用线性模型的预测控制去控制非线性系统 ,其预测偏差用神经网络进行补偿 .线性模型的辨识和神经网络的学习均采用阻尼最小二乘法 .仿真结果表明 ,用这种控制器能有效地控制非线性系统 ,并具有超调小 ,鲁棒性好的特点 .In this paper, we propose a kind of neural network predictive deviation compensation self-tuning controller, using linear model to control nonlinear system. The predictive deviation's compensation is completed by neural network. The damped least square method was applied in both identification of the linear model and study of the neural network. The simulation results show that this kind of controller can control nonlinear system effectively and has small overshoot and good stability.

关 键 词：神经网络 非线性系统 预测控制 自校正控制器 

分 类 号：TP273.2[自动化与计算机技术—检测技术与自动化装置] O231[自动化与计算机技术—控制科学与工程]