Diagonal recurrent neural network based identification of nonlinear dynamical systems with Lyapunov stability based adaptive learning rates

被引：50

作者：

Kumar, Rajesh ^{[1
]}

Srivastava, Smriti ^{[2
]}

Gupta, J. R. P. ^{[2
]}

Mohindru, Amit ^{[3
]}

机构：

[1] Bharati Vidyapeeths Coll Engn, Dept Instrumentat & Control Engn, A-4, New Delhi 110063, India

[2] Netaji Subhas Inst Technol, Div Instrumentat & Control Engn, Sect 3, New Delhi 110078, India

[3] Indraprastha Inst Informat Technol, Dept Elect & Commun Engn, New Delhi 110020, India

来源：

NEUROCOMPUTING | 2018年 / 287卷

关键词：

Diagonal recurrent neural network; Nonlinear system identification; Radial basis function network; Multi-layer feed forward neural network; Robustness; Lyapunov stability based dynamic learning rate; ONLINE IDENTIFICATION;

D O I：

10.1016/j.neucom.2018.01.073

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 diagonal recurrent neural network (DRNN) based identification model for approximating the unknown dynamics of the nonlinear plants. The proposed model offers deeper memory and a simpler structure. Thereafter, we have developed a dynamic back-propagation learning algorithm for tuning the parameters of DRNN. Further, to guarantee the faster convergence and stability of the overall system, dynamic (adaptive) learning rates are developed in the sense of Lyapunov stability method. The proposed scheme is also compared with multi-layer feed forward neural network (MLFFNN) and radial basis function network (RBFN) based identification models. Numerical experiments reveal that DRNN has performed much better in approximating the dynamics of the plant and have also shown more robustness toward system uncertainties. (C) 2018 Elsevier B.V. All rights reserved.

引用

页码：102 / 117

页数：16

共 37 条

[21]

Isidori A., 2013, NONLINEAR CONTROL SY

[22] Online modeling and adaptive control of robotic manipulators using Gaussian radial basis function networks [J].

Kumar, Rajesh ;

Srivastava, Smriti ;

Gupta, J. R. P. .

NEURAL COMPUTING & APPLICATIONS, 2018, 30 (01) :223-239

[23] The Chebyshev-Polynomials-Based unified model neural networks for function approximation [J].

Lee, TT ;

Jeng, JT .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1998, 28 (06) :925-935

[24] On-line identification of nonlinear systems using Volterra polynomial basis function neural networks [J].

Liu, GP ;

Kadirkamanathan, V ;

Billings, SA .

NEURAL NETWORKS, 1998, 11 (09) :1645-1657

[25] Predicting a chaotic time series using a fuzzy neural network [J].

Maguire, LP ;

Roche, B ;

McGinnity, TM ;

McDaid, LJ .

INFORMATION SCIENCES, 1998, 112 (1-4) :125-136

[26]

Narendra K S, 1990, IEEE Trans Neural Netw, V1, P4, DOI 10.1109/72.80202

[27] Universal Approximation Using Radial-Basis-Function Networks [J].

Park, J. ;

Sandberg, I. W. .

NEURAL COMPUTATION, 1991, 3 (02) :246-257

[28] Particle Filter based Neural Network Modeling of Nonlinear Systems for State Space Estimation [J].

Rajesh, M. V. ;

Archana, R. ;

Unnikrishnan, A. ;

Gopikakaumari, R. .

CCDC 2009: 21ST CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1-6, PROCEEDINGS, 2009, :1477-+

[29] Intelligent modeling and identification of aircraft nonlinear flight [J].

Roudbari, Alireza ;

Saghafi, Fariborz .

CHINESE JOURNAL OF AERONAUTICS, 2014, 27 (04) :759-771

[30]

Rubio JDJ, 2005, IEEE DECIS CONTR P, P2562

← 1 2 3 4 →