基于动力学特性聚类多维泰勒网的非线性系统辨识与预测  

Nonlinear system identification and prediction based on dynamics cluster multi-dimensional Taylor network model

作　　者：周博[1] 严洪森[2] 

机构地区：[1]东南大学自动化学院,南京210096 [2]东南大学复杂工程系统测量与控制教育部重点实验室,南京210096

出　　处：《控制与决策》2014年第1期33-38,共6页Control and Decision

基　　金：国家自然科学基金重点项目(60934008);国家自然科学基金项目(50875046)

摘　　要：针对时变非线性系统难以建模的问题,提出了基于动力学特性聚类的多维泰勒网模型,对系统进行辨识与预测.首先讨论了多维泰勒网模型构造方法和非线性系统动力学特性聚类的定义;然后给出基于动力学特性聚类的多维泰勒网自重构算法;最后通过实例说明基于动力学特性聚类多维泰勒网在实际中应用的方法,实例结果验证了该方法的有效性.For the problem of difficulty in modeling of time-varying nonliner system, an approach to identification and prediction of system based on dynamics cluster multi-dimensional Taylor network model is proposed. Firstly, the method of construction of multi-dimensional Taylor network model is discussed, whereby the dynamics cluster is defined. Then, the self-reconfiguration algorithm of the dynamics cluster multi-dimensional Taylor network is given. Finally, an example is given to illustrate the method of the dynamics cluster multi-dimensional Taylor network how to work in the practical applications, and the results show the effectiveness of the proposed method.

关 键 词：多维泰勒网 动力学特性 聚类 非线性系统辨识 预测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]