基于循环神经网络的动态模型辨识

对于动态模型一般采用传统的传递函数模型进行辨识,而传递函数模型本质上是线性的,不适用于非线性系统。提出了一种基于循环神经网络的动态模型,除了能辨识线性系统,还能推广到非线性系统,并且在线性条件下,能转化成传递函数模型及现代控制系统中状态空间方程,针对不同的响应,都能得到不错的拟合效果。

In this paper,a dynamic model based on recurrent neural network is proposed,which can not only identify linear systems but also generalize them to nonlinear systems.Under linear conditions,they can be transformed into transfer function models or state-space equation in modern control system.It gets good results responding to different inputs.