A Tunable Radial Basis Function Model for Nonlinear System Identification Using Particle Swarm Optimisation

被引:1
作者
Chen, S. [1 ]
Hong, X. [3 ]
Luk, B. L. [2 ]
Harris, C. J. [1 ]
机构
[1] Univ Southampton, Sch Elect & Comp Sci, Southampton SO17 1BJ, Hants, England
[2] City Univ Hong Kong, Dept Mfg Engn & Engn Management, Hong Kong, Hong Kong, Peoples R China
[3] Univ Reading, Sch Syst Engn, Reading, Berks RG6 6AY, England
来源
PROCEEDINGS OF THE 48TH IEEE CONFERENCE ON DECISION AND CONTROL, 2009 HELD JOINTLY WITH THE 2009 28TH CHINESE CONTROL CONFERENCE (CDC/CCC 2009) | 2009年
关键词
ORTHOGONAL LEAST-SQUARES; PREDICTION-ERROR; ALGORITHM; PARAMETERS; NETWORKS; SIZE;
D O I
10.1109/CDC.2009.5399687
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A tunable radial basis function (RBF) network model is proposed for nonlinear system identification using particle swarm optimisation (PSO). At each stage of orthogonal forward regression (OFR) model construction, PSO optimises one RBF unit's centre vector and diagonal covariance matrix by minimising the leave-one-out (LOO) mean square error (MSE). This PSO aided OFR automatically determines how many tunable RBF nodes are sufficient for modelling. Compared with the-state-of-the-art local regularisation assisted orthogonal least squares algorithm based on the LOO MSE criterion for constructing fixed-node RBF network models, the PSO tuned RBF model construction produces more parsimonious RBF models with better generalisation performance and is computationally more efficient.
引用
收藏
页码:6762 / 6767
页数:6
相关论文
共 30 条
[11]   PARALLEL RECURSIVE PREDICTION ERROR ALGORITHM FOR TRAINING LAYERED NEURAL NETWORKS [J].
CHEN, S ;
COWAN, CFN ;
BILLINGS, SA ;
GRANT, PM .
INTERNATIONAL JOURNAL OF CONTROL, 1990, 51 (06) :1215-1228
[12]  
Cherkassky V, 1997, IEEE Trans Neural Netw, V8, P1564, DOI 10.1109/TNN.1997.641482
[13]   Self-generation RBFNs using evolutional PSO learning [J].
Feng, Hsuan-Ming .
NEUROCOMPUTING, 2006, 70 (1-3) :241-251
[14]   Multiobjective evolutionary optimization of the size, shape, and position parameters of radial basis function networks for function approximation [J].
González, J ;
Rojas, I ;
Ortega, J ;
Pomares, H ;
Fernández, J ;
Díaz, AF .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (06) :1478-1495
[15]   Multi-step ahead nonlinear identification of Lorenz's chaotic system using radial basis neural network with learning by clustering and particle swarm optimization [J].
Guerra, Fabio A. ;
Coelho, Leandro dos S. .
CHAOS SOLITONS & FRACTALS, 2008, 35 (05) :967-979
[16]  
Guru SM, 2005, PROCEEDINGS OF THE 2005 INTELLIGENT SENSORS, SENSOR NETWORKS & INFORMATION PROCESSING CONFERENCE, P319
[17]  
Kennedy J, 1995, 1995 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS PROCEEDINGS, VOLS 1-6, P1942, DOI 10.1109/icnn.1995.488968
[18]  
Kennedy J., 2001, Swarm Intelligence
[19]   PSO-based multiobjective optimization with dynamic population size and adaptive local archives [J].
Leong, Wen-Fung ;
Yen, Gary G. .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2008, 38 (05) :1270-1293
[20]   Estimation of elliptical basis function parameters by the EM algorithm with application to speaker verification [J].
Mak, MW ;
Kung, SY .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (04) :961-969