[1]吴波,吴科,吕剑虹,等.补偿递归模糊神经网络及在热工建模中的应用[J].东南大学学报(自然科学版),2008,38(4):668-673.[doi:10.3969/j.issn.1001-0505.2008.04.024]
 Wu Bo,Wu Ke,Lü Jianhong,et al.Compensation-based recurrent fuzzy neural network and its application in modeling of thermodynamic objects[J].Journal of Southeast University (Natural Science Edition),2008,38(4):668-673.[doi:10.3969/j.issn.1001-0505.2008.04.024]
点击复制

补偿递归模糊神经网络及在热工建模中的应用()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
38
期数:
2008年第4期
页码:
668-673
栏目:
自动化
出版日期:
2008-07-20

文章信息/Info

Title:
Compensation-based recurrent fuzzy neural network and its application in modeling of thermodynamic objects
作者:
吴波 吴科 吕剑虹 向文国
东南大学能源与环境学院, 南京 210096
Author(s):
Wu Bo Wu Ke Lü Jianhong Xiang Wenguo
School of Energy and Environment, Southeast University, Nanjing 210096, China
关键词:
补偿递归模糊神经网络 系统建模 序贯监督策略 改进BP算法 热工对象
Keywords:
compensatory-based recurrent fuzzy neural network system modeling sequential supervisory method improved back propagation algorithm thermodynamic objects
分类号:
TP183;TM611
DOI:
10.3969/j.issn.1001-0505.2008.04.024
摘要:
在传统的模糊神经网络中引入递归环节和补偿环节,构成了一种新型补偿递归模糊神经网络(CRFNN),改善了网络的动态响应特性和学习能力.在此基础上,采用一种新型序贯监督策略对网络进行结构辨识,能够有效地确定模糊规则的条数以及相关参数的初始值.针对CRFNN的结构特点,提出了改进的BP算法,能够对网络的结构参数进行进一步的学习.对典型的热工对象以及复杂的ALSTOM 气化炉进行的建模计算结果表明,提出的CRFNN具有优良的动态响应特性和很强的学习能力,值得在热工建模与控制领域中推广应用.
Abstract:
A novel compensatory-based recurrent fuzzy neural network(CRFNN)is proposed by adding recurrent element and compensatory element to the conventional fuzzy neural network in order to improve the dynamic response ability and learning ability. Based on this, a new sequential supervisory method is introduced for the structure identification of the CRFNN in order to effectively confirm the fuzzy rules and their correlative parameters. Furthermore, the back propagation(BP)algorithm is improved based on the characteristics of the proposed CRFNN to train the network. The results of modeling and prediction of the typical thermodynamic objects and the complicated ALSTOM gasifier show that the proposed CRFNN has excellent dynamic response and strong learning ability and it can be widely used in modeling and control of thermal process.

参考文献/References:

[1] Lin C M,Hsu C F.Identification of dynamic systems using recurrent fuzzy neural network[C] //IFSA World Congress and 20th NAFIPS International Conference.Vancouver,2001:2671-2675.
[2] Lee C H,Teng C C.Identification and control of dynamic systems using recurrent fuzzy neural networks[J].IEEE Trans Fuzzy Syst,2000,8(4):349-365.
[3] Zhang Y Q,Kandel A.Compensatory neural fuzzy systems with fast learning algorithm[J]. IEEE Trans Neural Network,1998,9(1):83-105.
[4] Pang Z H,Zhou Y G.A hybrid approach-based recurrent compensatory neural fuzzy network[C] //Proceedings of the 6th World Congress on Intelligent Control and Automation.Dalian,China,2006:2737-2741.
[5] Lin C J,Chen C H.A compensation-based recurrent fuzzy neural network for dynamic system identification[J]. Eur J Oper Res,2006,172(2):696-715.
[6] Lu C H,Tsai C C.Generalized predictive control using recurrent fuzzy neural networks for industrial processes[J]. J Process Control,2007,17(1):83-92.
[7] Chak C K,Feng G,Ma J.An adaptive fuzzy neural network for MIMO system model approximation in high-dimensional spaces[J].IEEE Trans Syst Man Cybern,Part B:Cybern,1998,28(3):436-446.
[8] 杨戈,吕剑虹,刘志远.一种新型RBF网络序贯学习算法[J].中国科学E辑:工程科学 材料科学,2004,34(7):763-775.
  Yang Ge,Lü Jianhong,Liu Zhiyuan.A new sequential learning algorithm for RBF neural networks[J].Science in China,Ser E:Engineering & Materials Science,2004,34(7):763-775.(in Chinese)
[9] Wigren T.Recursive identification based on nonlinear state space models applied to drum-boiler dynamics with nonlinear output equation[C] //Proceedings of 2005 America Control Conference.Portland,Oregon,USA,2005:5066-5072.
[10] Dixon R,Pike A W.Alstom benchmark challenge Ⅱ on gasifier control[J]. Control Theory and Applications,IEE Proceedings,2006,153(3):254-261.
[11] Dixon R.Benchmark challenge at control 2004[J]. Computing and Control Engineering Journal,2005,15(6):21-23.

备注/Memo

备注/Memo:
作者简介: 吴波(1984—),男,硕士生; 吕剑虹(联系人),男,博士,教授,博士生导师,jhlu_seu@yahoo.com.cn.
基金项目: 国家高技术研究发展计划(863计划)资助项目(2006AA05A107)、江苏省科技成果转化专项资金资助项目(BA2007008).
引文格式: 吴波,吴科,吕剑虹,等.补偿递归模糊神经网络及在热工建模中的应用[J].东南大学学报:自然科学版,2008,38(4):668-673.
更新日期/Last Update: 2008-07-20