论文部分内容阅读
对连续非线性系统，采用连续系统的设计方法，利用神经网络对非线性函数的逼近能力加上用来表征系统动态特性的若干积分器，构造工程上可实现的原系统的神经网络α阶逆系统（将α阶逆系统直接与原系统串接，构成α阶积分伪线性复合系统），并对α阶积分伪线性复合系统设计线性控制器，实现对原非线性系统的有效控制．仿真结果表明，该方法适用于较一般的线性、非线性连续系统，且结构简单，易于工程实现．
For continuous nonlinear systems, a continuous system design method is used. By using the approximation capability of neural network to nonlinear functions and integrators used to characterize the dynamic characteristics of the system, an α-order inverse of the original system can be constructed System (the α-order inverse system is directly connected with the original system to form the α-order integral pseudo-linear complex system), and the linear controller of the α-order integral pseudo-linear complex system is designed to effectively control the original nonlinear system. The simulation results show that this method is suitable for the more general linear and non-linear continuous systems and has the advantages of simple structure and easy implementation.