【摘要】 建立了一种回归神经网络辩识非线性电液伺服控制系统数学模型的辩识方法,研究了基于回归神经网络内部状态反馈的辩识算法,利用辩识实验获得的过程输入/输出数据动态调整神经网络权值。仿真结果辨明:神经网络描述的电液伺服控制系统数学模型具有较高精度,算法全局逼近能力良好。更多还原

【Abstract】 The method of identifying was built to identify mathematical model of nonlinear electro-hydraulic servo control system. The algorithm of identifying was researched based on inner state feedback of recurrent neural networks. The weights of neural networks were dynamic adjusted by input/output data of process which were acquired by experiments of identifying. The results of simulation show that mathematical model of neural networks of electro-hydraulic servo control system has better precision and the algorithm has ability to approximate error of global.更多还原