Identification using ANFIS with intelligent hybrid stable learning algorithm approaches and stability analysis of training methods

被引:97
作者
Shoorehdeli, Mahdi Aliyari [1 ]
Teshnehlab, Mohammad [1 ]
Sedigh, Ali Khaki [1 ]
Khanesar, M. Ahmadieh [1 ]
机构
[1] KN Toosi Univ Technol, Tehran, Iran
关键词
Learning rate; Hybrid learning algorithm; Intelligent optimization; Gradient based; Recursive least square and particle swarm optimization; Fuzzy systems; Fuzzy neural networks; ANFIS; Lyapunov theory; Identification; Stability analysis; PARTICLE SWARM OPTIMIZATION; FUZZY NEURAL-NETWORKS; LEAST-SQUARES; CONVERGENCE; SYSTEM; POWER;
D O I
10.1016/j.asoc.2008.11.001
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper proposes a novel hybrid learning algorithm with stable learning laws for Adaptive Network based Fuzzy Inference System (ANFIS) as a system identifier and studies the stability of this algorithm. The new hybrid learning algorithm is based on particle swarm optimization (PSO) for training the antecedent part and forgetting factor recursive least square (FFRLS) for training the conclusion part. Two famous training algorithms for ANFIS are the gradient descent (GD) to update antecedent part parameters and using GD or recursive least square (RLS) to update conclusion part parameters. Lyapunov stability theory is used to study the stability of the proposed algorithms. This paper, also studies the stability of PSO as an optimizer in training the identifier. Stable learning algorithms for the antecedent and consequent parts of fuzzy rules are proposed. Some constraints are obtained and simulation results are given to validate the results. It is shown that instability will not occur for the leaning rate and PSO factors in the presence of constraints. The learning rate can be calculated on-line and will provide an adaptive learning rate for the ANFIS structure. This new learning scheme employs adaptive learning rate that is determined by input-output data. Also, stable learning algorithms for two common methods are proposed based on Lyapunov stability theory and some constraints are obtained. (C) 2008 Elsevier B. V. All rights reserved.
引用
收藏
页码:833 / 850
页数:18
相关论文
共 68 条
[1]  
ALIYARI M, 2006, P AM CONTR C JUN
[2]  
ALIYARI MS, 2007, P IEEE INT FUZZ SYS
[3]   Using selection to improve particle swarm optimization [J].
Angeline, PJ .
1998 IEEE INTERNATIONAL CONFERENCE ON EVOLUTIONARY COMPUTATION - PROCEEDINGS, 1998, :84-89
[4]  
[Anonymous], INT J APPROXIMATE RE
[5]   CONVERGENCE AND EXPONENTIAL CONVERGENCE OF IDENTIFICATION ALGORITHMS WITH DIRECTIONAL FORGETTING FACTOR [J].
BITTANTI, S ;
BOLZERN, P ;
CAMPI, M .
AUTOMATICA, 1990, 26 (05) :929-932
[6]  
CAO L, 1999, P AM CONTR C, P1334
[7]   An optimized Takagi-Sugeno type neuro-fuzzy system for modeling robot manipulators [J].
Chatterjee, A ;
Watanabe, K .
NEURAL COMPUTING & APPLICATIONS, 2006, 15 (01) :55-61
[8]  
CHEN MS, 1999, IEEE C SYST MAN CYBE, V3, P40
[9]   Use of intelligent-particle swarm optimization in electromagnetics [J].
Ciuprina, G ;
Ioan, D ;
Munteanu, I .
IEEE TRANSACTIONS ON MAGNETICS, 2002, 38 (02) :1037-1040
[10]  
Clerc M, 1999, P C EV COMP, DOI DOI 10.1109/CEC.1999.785513