Nonlinear modeling and adaptive fuzzy control of MCFC stack

被引：45

作者：

Shen, C ^{[1
]}

Cao, GY ^{[1
]}

Zhu, XJ ^{[1
]}

Sun, XJ ^{[1
]}

机构：

[1] Shanghai Jiao Tong Univ, Inst Fuel Cell, Dept Automat, Shanghai 200030, Peoples R China

来源：

JOURNAL OF PROCESS CONTROL | 2002年 / 12卷 / 08期

基金：

上海市科技启明星计划;

关键词：

molten carbonate fuel cells; radial basis function; modeling; adaptive control; fuzzy control;

D O I：

10.1016/S0959-1524(02)00013-6

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 [计算机科学与技术];

摘要：

To improve availability and performance of fuel cells, the operating temperature of molten carbonate fuel cells (MCFC) stack should be controlled within a specified range. However, the most existing models of MCFC are not ready to be applied in synthesis. In this paper, a radial basis function neural networks identification model of MCFC stack is developed based on the input output sampled data. A novel adaptive fuzzy control procedure for the temperature of MCFC stack is also developed. The parameters of the fuzzy control system are regulated by back-propagation algorithm, and the rule database of the fuzzy system is also adaptively adjusted by the nearest-neighbor-clustering algorithm. Finally using the neural networks model of MCFC stack, the simulation results of the control algorithm are presented. The results show the effectiveness of the proposed modeling and design procedures for MCFC stack based on neural networks identification and the novel adaptive fuzzy control. (C) 2002 Elsevier Science Ltd. All rights reserved.

引用

页码：831 / 839

页数：9

共 19 条

[1]

Nonlinear modelling of a twin rotor mimo system using radial basis function networks [J].

Ahmad, SM ;

Shaheed, MH ;

Chipperfield, AJ ;

Tokhi, MO .

PROCEEDINGS OF THE IEEE 2000 NATIONAL AEROSPACE AND ELECTRONICS CONFERENCE: ENGINEERING TOMORROW, 2000, :313-320

[2]

Al-Amoundi A, 2000, IEE P-GENER TRANSM D, V147, P310, DOI DOI 10.1049/IP-GTD:20000605

[3]

[Anonymous], 1994, STAT NEURAL NETWORKS

[4]

CAO GY, 1991, T JAPAN SOC MECH ENG, V57, P837

[5]

REPRESENTATIONS OF NON-LINEAR SYSTEMS - THE NARMAX MODEL [J].

CHEN, S ;

BILLINGS, SA .

INTERNATIONAL JOURNAL OF CONTROL, 1989, 49 (03) :1013-1032

[6]

ORTHOGONAL LEAST-SQUARES LEARNING ALGORITHM FOR RADIAL BASIS FUNCTION NETWORKS [J].

CHEN, S ;

COWAN, CFN ;

GRANT, PM .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1991, 2 (02) :302-309

[7]

Selecting radial basis function network centers with recursive orthogonal least squares training [J].

Gomm, JB ;

Yu, DL .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (02) :306-314

[8]

Han J., 1994, J AUTOM, V20, P487

[9]

He W, 1999, INT J ENERG RES, V23, P1331, DOI 10.1002/(SICI)1099-114X(199912)23:15<1331::AID-ER558>3.0.CO

[10]

2-Z

← 1 2 →