基于复合正交神经网络的广义通用模型自适应控制  

Adaptive Control with a General Common Model Based on the Compound Orthogonal Neural Network

作　　者：黄景[1] 郭丙君[1] 

机构地区：[1]华东理工大学信息科学与工程学院,上海200237

出　　处：《华东理工大学学报（自然科学版）》2008年第6期864-867,共4页Journal of East China University of Science and Technology

摘　　要：在自适应逆控制中应用复合正交神经网络具有算法简单、学习收敛速度快等优点,将复合正交神经网络与广义通用模型控制器策略相结合,提出了一种基于神经网络的广义通用模型自适应控制方法。该控制方法中的参考轨迹为一条典型的二阶曲线,控制器参数具有明显的物理意义,参数整定方便。仿真实验验证了该控制策略的有效性。The compound orthogonal neural network is of simple algorithm and fast convergence. By combining a compound orthogonal neural network with a general common model control scheme, the paper presents a kind of adaptive control algorithm based on a neural network. The reference trajectory is a classic second-order curve and the parameters of GCMC are of very clear physical meaning and are easily tuned for the controller. The simulation results show the effectiveness of the proposed control scheme.

关 键 词：广义通用模型控制 复合正交神经网络 二阶系统 自适应逆控制 

分 类 号：TP113[自动化与计算机技术—控制理论与控制工程]