基于过程神经网络的非线性动态系统辨识  

Nonlinear Dynamic System Identification Based on Procedure Neural Networks

作　　者：程亮[1] 

机构地区：[1]大庆石油学院计算机与信息技术学院,黑龙江大庆163318

出　　处：《佳木斯大学学报（自然科学版）》2009年第6期828-830,共3页Journal of Jiamusi University：Natural Science Edition

摘　　要：研究了过程神经网络在非线性动态系统辨识方面的应用.针对传统神经网络在解决系统过程式输入和时间顺序依赖性问题时出现的使模型和算法复杂化的弊端,提出了一种时变输入输出的过程神经元网络模型作为系统的辨识模型,采用基于函数基展开的梯度下降算法,以油田井组注采系统为例验证了模型和算法的有效性,进而说明了过程神经元网络对于解决系统过程式输入的非线性动态系统辨识问题的适用性.Procedure neural networks＇ application in system identification was researched in this paper.Aiming at the disadvantages of traditional neural networks making the model and algorithm complicated when it solves the problems of system process inputs and the dependence of time order,a process neural networks model with time-varying inputs and outputs used to system identification model was presented,and the learning algorithm based on function base expanded integrated with grads descending was given.The validity of the model and algorithm was proved by the system of oil fields well group injecting and exploiting.Furthermore,the procedure neural networks＇ applicability in solving system process inputs of nonlinear dynamic system identification was proved.

关 键 词：过程神经网络 非线性动态系统 系统辨识 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]