自组织递归区间二型模糊神经网络在动态时变系统辨识中的应用

李迪; 陈向坚; 续志军; 杨帆; 牛文达

doi:10.3788/OPE.20111906.1406

您当前的位置：

首页 >

文章列表页 >

自组织递归区间二型模糊神经网络在动态时变系统辨识中的应用

信息科学 | 更新时间：2020-08-12

- 自组织递归区间二型模糊神经网络在动态时变系统辨识中的应用
- Type-II fuzzy neural networks with self-organizing recurrent intervals for dynamic time-varying system identification
- 光学精密工程 2011年19卷第6期页码：1406-1413
- 作者机构：
  
  中国科学院长春光学精密机械及物理研究所,吉林长春,130033
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No.50905174)()
- DOI：10.3788/OPE.20111906.1406
  中图分类号： TP391.4
- 收稿日期：2010-11-04，
  
  修回日期：2011-02-15，
  
  网络出版日期：2011-06-25，
  
  纸质出版日期：2011-06-25
- 稿件说明：
移动端阅览
李迪, 陈向坚, 续志军, 杨帆, 牛文达. 自组织递归区间二型模糊神经网络在动态时变系统辨识中的应用[J]. 光学精密工程, 2011,19(6): 1406-1413

LI Di, CHEN Xiang-jian, XU Zhi-jun, YANG Fan, NIU Wen-da. Type-II fuzzy neural networks with self-organizing recurrent intervals for dynamic time-varying system identification[J]. Editorial Office of Optics and Precision Engineering, 2011,19(6): 1406-1413
李迪, 陈向坚, 续志军, 杨帆, 牛文达. 自组织递归区间二型模糊神经网络在动态时变系统辨识中的应用[J]. 光学精密工程, 2011,19(6): 1406-1413 DOI： 10.3788/OPE.20111906.1406.

LI Di, CHEN Xiang-jian, XU Zhi-jun, YANG Fan, NIU Wen-da. Type-II fuzzy neural networks with self-organizing recurrent intervals for dynamic time-varying system identification[J]. Editorial Office of Optics and Precision Engineering, 2011,19(6): 1406-1413 DOI： 10.3788/OPE.20111906.1406.

摘要

针对动态时变系统辨识过程中存在噪声干扰的问题

本文将区间二型模糊集结合到递归神经网络中

提出了自组织递归区间二型模糊神经网络以增强动态时变系统的抗噪能力。该自组织递归区间二型模糊神经网络由前件和后件两部分构成:前件为区间二型模糊集模型

用于将每个规则的激活强度反馈到自身构成内反馈回路

其参数学习采用梯度下降算法;后件为带有区间权值的Takagi-Sugeno-Kang(TSK)模型

其参数学习采用有序规则卡尔曼滤波算法

且网络初始规则数为零。所有规则均通过结构学习和前后件参数同时在线学习来产生

其网络结构学习采用的是在线区间二型模糊群集。为验证提出的神经网络的优越性

将其应用到单输入单输出动态时变系统的辨识中。实验结果表明

相对于前馈一型/二型模糊神经网络、递归一型模糊神经网络

该神经网络的辨识能力强

即使在存在白噪声的条件下

也能减小测试及训练误差。

Abstract

To solve the noise interference issue for the dynamic time-varying system identification processing

a type-II Fuzzy Neural Network (FNN) with self-organizing recurrent intervals is proposed to enhance the system robustness against the noise. This type-II fuzzy neural network is composed of two parts. The antecedent part takes the type-II fuzzy-set model to form the feedback-loop internally by feeding the acting strength of each rule

and it uses an algorithm of gradient-descent method for parameter learning. The consequent part takes the Takagi-Sugeno-Kang (TSK) model and uses an rule-ordered Karman filtering method for parameter learning in no initial network rules. All rules are generated from the simultaneous on-line parameter learning from both parts above

in which the network structural learning takes the on-line interval type-II fuzzy-set. To verify its advantages in performance

the proposed neural network is compared with the feed forward type-I/type-II FNNs and recurrent type-I FNN in applications of the single-in-single-out dynamic time-variant system identification. The experiment results indicate that the type-II fuzzy neural network (FNN) with self-organizing recurrent intervals has strong identification ability

and can reduce the errors of the training and test in the present of various white noises.

关键词

Keywords

references

MASTORCOSTAS P A,THEOCHARIS J B. A recurrent fuzzy-neural model for dynamic system identification[J]. IEEE Trans. Syst., Man and Cyber. Part B: Cybernetics.,2002,32(2):176-190.[2] JUANG C F. A TSK-type recurrent fuzzy network for dynamic systems processing by neural network and genetic algorithm[J]. IEEE Trans. Fuzzy Systems, 2002,10(2):155-170.[3] 郑晓虎,朱荻. 模糊神经网络在UV-LIGA工艺优化中的应用[J]. 光学精密工程,2006,14(1):139-144. ZHENG X H,ZHU D. Application of fuzzy neural network to optimizing UV-LIGA process[J].Opt. Precision Eng., 2006,14(1):139-144. (in Chinese)[4] 张玲瑄 ,贾振元. 微细电火花加工放电状态逐级映射检测[J]. 光学精密工程,2010,18(3):663-669. ZHANG L X, JIA ZH Y. Successive mapping detection of micro EDM discharge state[J]. Opt. Precision Eng., 2010,18(3):663-669. (in Chinese)[5] 李勇,王珂,张立保,等. 多断层融合的肺CT肿瘤靶区超分辨率重建[J]. 光学精密工程,2010,18(5):1213-1218. LI Y,WANG K,ZHANG L B,et al..Super-resolution reconstruction of pulmonary nodules based on CT multi-section fusion[J]. Opt. Precision Eng., 2010,18(5):1213-1218. (in Chinese)[6] 张友旺. 基于动态递归模糊神经网络的自适应电液位置跟踪系统[J]. 控制理论与应用,2005,22(4):551-555. ZHANG Y W.Adaptive electro_bydraulic position tracking system based on dynamic recurrent fuzzy neural network[J].Control Theory and Applications,2005,22(4):551-555. (in Chinese)[7] KARNIK N N,MENDEL J M,LIANG Q.Type-2 fuzzy logic systems[J]. IEEE Trans. Fuzzy Systems, 1999,7(6):643-658.[8] MENDEL J M. Type-2 fuzzy sets made simple[J]. IEEE Trans. Fuzzy Systems, 2002,10(2):117-127.[9] JOHN R,COUPLAND S. Type-2 fuzzy logic: A historical view[J]. IEEE Comput.Intell.Mag.,2007,2(1):57-62.[10] ZENG J, LIU Z Q. Type-2 fuzzy hidden Markov models and their application to speech recognition[J]. IEEE Trans. Fuzzy Syst., 2006,14(3):454-467.[11] JUANG C F,CHIU S H,CHANG S W. A Self-organizing TS-type fuzzy network with support vector learning and its application to classification problems[J]. IEEE Trans, Fuzzy Syst, 2007,15(5):998-1008.[12] JUANG CH F. A self-Evolving Internal Type-2 Fuzzy Neural Network With Online Structure and Parameter learning[J]. IEEE Trans,Fuzzy Syst, 2008,16(6):1411-1424.

浏览量

766

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据