一种基于神经网络的精馏塔自适应控制器设计  

Neural network based adaptive controller design for a distillation column

作　　者：郭淑会[1] 李树荣[1] 

机构地区：[1]中国石油大学信息与控制工程学院,山东东营257061

出　　处：《山东大学学报（工学版）》2005年第3期5-8,共4页Journal of Shandong University（Engineering Science）

摘　　要：针对两输入两输出的隐含非线性系统,设计了一种神经网络自适应控制器,并通过构造Lyapunov函数,得出新的权值变化规律.该方法基于Lyapunov稳定性理论,可证明闭环系统是半全局一致最终有界的(SGUUB).从二元精馏塔奇异摄动简化模型的仿真结果可以看出,这种控制器有良好的跟踪效果.An adaptive neural network controller is designed for a class of implicit nonlinear systems with two inputs and two outputs. A new weight learning algorithm is obtained by choosing Lyapunov function. This method based on Lyapunov theory and the closed-loop system can be proven to be semi-globally uniformly ultimately bounded (SGUUB). It can be seen from the simulation of the singular perturbation model of distillation column that the controller has good performance for implicit systems.

关 键 词：神经网络 自适应控制 非线性系统 精馏塔 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]