简单动态递归神经网络在非线性系统辨识中的应用

Application of simple dynamic recurrent neural network in non-linear system identification

提出了用一种结构非常简单的动态递归神经网络(SRNN)辨识非线性系统的方法。该方法研究了在递归层不加权的网络简单拓扑结构,推导出SRNN的预报误差(RPE)学习算法,并对算法进行了补充和改进。仿真实验结果表明,这种网络需要调整的权系值少,且改进后的学习算法简单、辨识速度快、模型精度高,解决了一般动态递归网络因网络拓扑结构复杂造成的训练算法复杂、收敛速度慢的问题,可以实时应用。

An adaptive identification method of simple dynamic recurrent neural network （SRNN） for nonlinear dynamic systems is presented. This method deduces the reeursive prediction error （RPE） learning algorithm of SRNN,and improves the algorithm by studying topological structure on recursion layer without the weight values. The simulation results indicate that this kind of neural network can be used in real-time control,due to its less weight values, simpler learning algorithm,higher identification speed,and higher precision of model. It solves the problems of intricate in training algorithm and slow rate in convergence caused by the complicated topological structure in usual dynamic recurrent neural network.