摘要
研究了一类单输入单输出仿射非线性系统的自适应控制问题。采用反馈线性化方法设计控制器,用神经网络逼近系统中的未知非线性函数,并在神经网络权值的自适应律中引入权值误差的概念,以改善系统的动态性能。同时采用滑模控制方法设计补偿器,提高了系统的鲁棒性。理论分析及仿真结果表明,所设计的控制器,不仅能解决该系统的轨迹跟踪控制问题,而且保证了系统的渐进稳定性。
This paper studies the adaptive control of a class of SISO affine nonlinear system.Here it designs a controller using the feed linear linearization method.The neural networks are used to approximate the unknown nonlinear functions.In order to improve the quality of this system,the approximation errors of the neural networks are introduced to the adaptive law.Theoretica1 analysis and simulations indicate that the strategy can not only solve the tracking problem,but also guarantee the stability of the systems.
出处
《电子科技》
2011年第4期12-14,23,共4页
Electronic Science and Technology
基金
广西自然科学基金资助项目(桂科自0832067)
关键词
神经网络
滑模控制
反馈线性化
鲁棒性
仿射非线性系统
neural networks
sliding mode control
feed linearization
robustness
affine nonlinear system
