论文部分内容阅读
研究如何构造神经网络（ＮＮ） α阶时延逆系统，并将其用于ＭＩＭＯ 强耦合非线性离散时间系统的线性化解耦。ＮＮα阶时延逆系统由单个静态神经网络和若干时延因子组成，将其与原系统复合可形成具有最小阶时延的伪线性解耦系统。该方法对被控系统数学模型的先验知识要求很少，不但能有效地实现对原系统的线性化解耦，且结构简单、易于工程实现
This paper studies how to construct the α-order delay inverse system of neural networks (NN) and uses it to linearize the decoupled MIMO strongly coupled nonlinear discrete-time systems. The NN α order delay inverse system consists of a single static neural network and several delay factors, which can be combined with the original system to form a pseudo-linear decoupled system with the smallest order delay. This method has very little priori knowledge of the mathematical model of the controlled system. It not only can effectively decouple the linearization of the original system, but also has the advantages of simple structure and easy implementation