[1]张秀玲,李少清,田力勇.Elman神经网络的板形模式识别方法[J].智能系统学报,2010,5(05):449-453.[doi:10.3969/j.issn.1673-4785.2010.05.012]
 ZHANG Xiu-ling,LI Shao-qing,TIAN Li-yong.Research of flatness pattern recognition based on the Elman neural network[J].CAAI Transactions on Intelligent Systems,2010,5(05):449-453.[doi:10.3969/j.issn.1673-4785.2010.05.012]
点击复制

Elman神经网络的板形模式识别方法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第5卷
期数:
2010年05期
页码:
449-453
栏目:
出版日期:
2010-10-25

文章信息/Info

Title:
Research of flatness pattern recognition based on the Elman neural network
文章编号:
1673-4785(2010)05-0449-05
作者:
张秀玲12李少清12田力勇12
1.燕山大学 电气工程学院,河北 秦皇岛 066004; 2.燕山大学 工业计算机控制工程河北省重点实验室,河北 秦皇岛 066004
Author(s):
ZHANG Xiu-ling12 LI Shao-qing12 TIAN Li-yong12
1.College of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China; 2.Key Laboratory of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao 066004, China
关键词:
板形模式识别Elman神经网络动态网络
Keywords:
flatness pattern recognition Elman neural network dynamic network
分类号:
TP183
DOI:
10.3969/j.issn.1673-4785.2010.05.012
文献标志码:
A
摘要:
针对静态网络设计和识别时间模式的能力弱、泛化能力差、学习速度慢等缺点,建立了一个基于Elman神经网络的板形模式识别系统.该系统由于考虑到了神经网络的过学习或过拟合问题,且通过经验公式和对比实验来确定神经网络的隐层节点数,具有简单、有效的优点.系统通过对6种基本板形模式及其组合模式的学习,具有了一定的泛化能力.经仿真验证,实际输出的误差均小于0.1,识别效果良好,可以证明基于Elman动态网络的系统,其板形识别能力要强于BP网络构成的系统.
Abstract:
Due to the presently poor level of designing and recognizing time patterns and generalizations of static neural networks, as well as the fact that learning speed is slow, a flatness pattern recognition system based on the Elman neural network was presented. The system is simple and efficient, because of its philosophy of over-learning or over-fitting a neural network and determining the number of the hidden nodes with experiential formulas and contrasting experiments. This system has generalization capability through learning the six basic flatness patterns and their combinations. The simulation shows that each error of actual output is less than 0.1, giving a good result, and that the capability of the system based on the Elman dynamic network pattern recognition is better than the system based on a BP network.

参考文献/References:

[1]王国栋.板形控制和板形理论[M].北京:冶金工业出版社, 1980: 1-11.
[2]魏剑平,李华德,余达太,等.基于回归神经网络的复杂工业对象的建模[J].北京科技大学学报, 1999, 21(4): 406-408.
WEI Jianping, LI Huade, YU Datai, et al. Modeling for a complicated industrial object based on recurrent neural network[J]. Journal of University of Science and Technology Beijing, 1999, 21(4): 406-408.
[3]GE Hongwei, QIAN Feng, LIANG Yanchun, et al. Identification and control of nonlinear systems by a dissimilation particle swarm optimizationbased Elman neural network[J]. Nonlinear Analysis: Real World Applications, 2008, 9: 1345-1360.
[4]张秀玲.冷带轧机板形智能识别与智能控制研究[D].秦皇岛:燕山大学, 2002: 36-39.
ZHANG Xiuling. Research on intelligent control and recognition of flatness for cold strip mill [D]. Qinhuangdao: Yanshan University, 2002: 36-39.
[5]周会峰.板形识别预测和控制仿真的智能方法研究[D].秦皇岛:燕山大学, 2005: 38-39.
ZHOU Huifeng. Research on intelligent methods of flatness recognition prediction and control simulation[D]. Qinhuangdao: Yanshan University, 2005: 38-39.
[6]谢庆国,万淑芸,赵金.一种 Elman 回归网络的设计方法[J].华中科技大学学报:自然科学版, 2002, 30(3): 22-24.
XIE Qingguo, WAN Shuyun, ZHAO Jin. A systemic design for Elman recurrent network[J]. Journal of Huazhong University of Science and Technology: Nature Science Edition, 2002, 30(3): 22-24.
[7]HAGIWARA K, FUKUMIZU K. Relation between weight size and degree of over-fitting in neural network regression[J]. Neural Networks, 2008, 21: 48-58.
[8]魏海坤.神经网络结构设计的理论与方法[M].北京:国防工业出版社, 2005: 97-99.
[9]陈跃华,曹广益,朱新坚. PEMFC的 Elman 神经网络建模与模糊神经网络控制[J].能源技术, 2005, 26(4): 146-149.
CHEN Yuehua, CAO Guangyi, ZHU Xinjian. Elman neural network modeling and adaptive fuzzy control of PEMFC [J]. Energy Technology, 2005, 26(4): 146-149.

相似文献/References:

[1]张俊玲,陈增强,张青.基于粒子群优化的Elman神经网络无模型控制[J].智能系统学报,2016,11(1):49.[doi:10.11992/tis.201507025]
 ZHANG Junling,CHEN Zengqiang,ZHANG Qing.Elman model-free control method based on particle swarm optimization algorithm[J].CAAI Transactions on Intelligent Systems,2016,11(05):49.[doi:10.11992/tis.201507025]

备注/Memo

备注/Memo:
收稿日期:2009-12-31.
基金项目:国家自然科学基金资助项目(50675186).
通信作者:张秀玲. E-mail: zxlysu@yahoo.com.cn.
作者简介:
张秀玲,女,1968年,教授、博士,主要研究方向为神经网络智能控制.获国家科技进步二等奖1项,省部级科技进步一等奖、二等奖各1项,发表学术论文60余篇.
李少清,男,1984年生,硕士研究生,主要研究方向为Elman神经网络板形识别.
田力勇,男,1985年生,硕士研究生,主要研究方向为智能控制.
更新日期/Last Update: 2010-11-26