TRAINING ELMAN NEURAL NETWORK FOR DYNAMIC SYSTEM IDENTIFICATION USING AN ADAPTIVE LOCAL SEARCH ALGORITHM

被引:0
作者
Zhang, Zhiqiang [1 ,2 ]
Tang, Zheng [1 ]
Gao, Shangce [1 ]
Yang, Gang [1 ]
机构
[1] Toyama Univ, Fac Engn, Toyama 9308555, Japan
[2] NST Inc, Dept Res & Dev, Tokyo, Japan
来源
INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL | 2010年 / 6卷 / 05期
关键词
Elman neural networks (ENN); Back propagation; Adaptive local search (ALS); Dynamical system identification (DSI); TIME-SERIES PREDICTION; GRAMMATICAL INFERENCE; NONLINEAR-SYSTEMS; FAULT-DETECTION; RECURRENT;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recurrent neural networks, especially for Elman Neural Network, have attracted the attention of researchers in the fields of Dynamic System Identification (DSI) since they took the memory unit through the context delay. In this paper, we propose an Adaptive Local Search (ALS) algorithm to train Elman Neural Network (ENN) for Dynamic Systems Identification (DSI) from a new angle instead of traditional Back Propagation (BP) based gradient descent technique. Experimental results show that the proposed algorithm has greatly effective performances in the identification of linear and nonlinear dynamic systems in comparison with BP based algorithms. The results also demonstrate that the proposed algorithm is an alternative means of training ENN when the gradient-based methods fail to find an acceptable solution. So the proposed algorithm can be regarded as a new tool or identification approach to identify dynamical systems for the auto-control systems.
引用
收藏
页码:2233 / 2243
页数:11
相关论文
共 34 条
[1]  
[Anonymous], 1995, NEURAL NETWORKS IDEN, DOI DOI 10.1007/978-1-4471-3244-8
[2]  
CHAGRA, 1998, P IEEE INT C SYST MA, V4, P3759
[3]   RECURRENT NEURAL NETWORKS AND ROBUST TIME-SERIES PREDICTION [J].
CONNOR, JT ;
MARTIN, RD ;
ATLAS, LE .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02) :240-254
[4]  
CORYN AL, 1999, NETWORK COMPUTATION, V1
[5]   FINDING STRUCTURE IN TIME [J].
ELMAN, JL .
COGNITIVE SCIENCE, 1990, 14 (02) :179-211
[6]  
Fekih A, 2007, INT J INNOV COMPUT I, V3, P1073
[7]  
GAO, 1996, P IEEE INT REF SYST, V2, P1376
[8]   Genetic Algorithm training of Elman neural network in motor fault detection [J].
Gao, XZ ;
Ovaska, SJ .
NEURAL COMPUTING & APPLICATIONS, 2002, 11 (01) :37-44
[9]   A modified particle swarm optimization-based dynamic recurrent neural network for identifying and controlling nonlinear systems [J].
Ge, Hong-Wei ;
Liang, Yan-Chun ;
Marchese, Maurizio .
COMPUTERS & STRUCTURES, 2007, 85 (21-22) :1611-1622
[10]   Noisy time series prediction using recurrent neural networks and grammatical inference [J].
Giles, CL ;
Lawrence, S ;
Tsoi, AC .
MACHINE LEARNING, 2001, 44 (1-2) :161-183