RBF neural network with optimal selection cluster algorithm and its application

被引：0

作者：

Liu, TN ^{[1
]}

Guan, XZ ^{[1
]}

Liu, ZY ^{[1
]}

Xie, AH ^{[1
]}

Zhang, H ^{[1
]}

机构：

[1] Daqing Petr Inst, Dept Automat & Control Engn, Anda 151400, Heilongjiang, Peoples R China

来源：

PROCEEDINGS OF THE 4TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-4 | 2002年

关键词：

RBF neural network; optimal selection; cluster algorithm; identification; gradient algorithm; recursive least square algorithm;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, it is framed a model of RBF neural network (RBFNN) to solve identification of nonlinear systems. First, it is proposed a kind of optimal selection cluster algorithm. By this algorithm, it is optimally gained the hidden layer node number of RBFNN in terms of input samples. At the same time, it is obtained the initial parameters values of RBF. Then, it is estimated the parameters value of RBF by gradient algorithm with momentum terms, and identified the weights of RBFNN by recursive least square algorithm. With the above two algorithms, it is alternately iterated. By the above hybrid algorithms, it is not only raised identification precision of RBFNN, but also improved generalization property of the net. It is proved the validity of the scheme by its applications.

引用

页码：1408 / 1411

页数：4