摘要
提出了一种神经网络补偿自适应广义预测解耦控制方案,即用神经网络逼近通道间的耦合、非线性及未建模动态,且采用了改进RLS辨识算法及用后能改善辨识效果,从而增进自适应控制的精度与鲁棒性,能解决参数不确定的非线性多变量耦合问题,给出了该算法的实现原理及步骤。理论分析和仿真结果表明,该方案是有效的。
A method for adaptive generalized predictive decoupling controller based on the compensation via a neural network is put forward. Using improved RLS identification algorithm and neural network which could approach passages coupling, nonlinear and unmodeled dynamics could make identification much better. So, control precision and robustness for adaptive control will be improved. It can solve nonlinear uncertain multi-variable coupled problem. Principles and the steps of the algorithm are given. Theory analysis and simulation results show that the algorithm is effective.
出处
《系统仿真学报》
EI
CAS
CSCD
北大核心
2005年第1期178-180,共3页
Journal of System Simulation
关键词
解耦控制
广义预测控制
自适应控制
神经网络补偿
decoupling control
generalized redictive control
adaptive control
neural network compensation
