Neural network design and model reduction approach for black box nonlinear system identification with reduced number of parameters

Authors:
Hector M. Romero Ugalde;Jean-Claude Carmona;Victor M. Alvarado;Juan Reyes-Reyes
Affiliations:
Laboratoire des Sciences de l'Information et des Systemes, UMR CNRS 7296, ENSAM, 13100 Aix en Provence, France and Centro Nacional de Investigacion y Desarrollo Tecnologico, CENIDET, 62490 Cuernav ...;Laboratoire des Sciences de l'Information et des Systemes, UMR CNRS 7296, ENSAM, 13100 Aix en Provence, France;Centro Nacional de Investigacion y Desarrollo Tecnologico, CENIDET, 62490 Cuernavaca, Mor., Mexico;Instituto Tenologico de Zacatepec, Calzada Tecnologico, ITZ, 62780 Zacatepec, Mor., Mexico
Venue:
Neurocomputing
Year:
2013

Citing 17
Cited 1

System identification (2nd ed.): theory for the user

System identification (2nd ed.): theory for the user
Handbook of Neural Computation

Handbook of Neural Computation
Neural Networks for Optimization and Signal Processing

Neural Networks for Optimization and Signal Processing
Theme Editor's Introduction: Neural Networks in Computational Science and Engineering

IEEE Computational Science & Engineering
Identification of Dynamical Systems

Identification of Dynamical Systems
Identification and control of nonlinear systems by a time-delay recurrent neural network

Neurocomputing
Nonlinear system identification using optimized dynamic neural network

Neurocomputing
A combined backstepping and small-gain approach to robust adaptive fuzzy output feedback control

IEEE Transactions on Fuzzy Systems
Design of fuzzy wavelet neural networks using the GA approach for function approximation and system identification

Fuzzy Sets and Systems
A differential evolution based neural network approach to nonlinear system identification

Applied Soft Computing
Robust identification of nonlinear complex systems using low complexity ANN and particle swarm optimization technique

Expert Systems with Applications: An International Journal
Nonlinear systems identification using dynamic multi-time scale neural networks

Neurocomputing
Identification and control of dynamical systems using neural networks

IEEE Transactions on Neural Networks
Hybrid Multiobjective Evolutionary Design for Artificial Neural Networks

IEEE Transactions on Neural Networks
Pruning algorithms-a survey

IEEE Transactions on Neural Networks
Adaptive Neural Network Decentralized Backstepping Output-Feedback Control for Nonlinear Large-Scale Systems With Time Delays

IEEE Transactions on Neural Networks
Structure optimization of neural network for dynamic system modeling using multi-objective genetic algorithm

Neural Computing and Applications - Special Issue on LSMS2010 and ICSEE 2010

Letters: A generalized indirect adaptive neural networks backstepping control procedure for a class of non-affine nonlinear systems with pure-feedback prototype

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper a dedicated recurrent neural network design and a model reduction approach are proposed in order to improve the balance between complexity and quality of black box nonlinear system identification models. The proposed neural network design, based on a three-layers architecture, helps to reduce the number of parameters of the model after the training phase without any significant loss of estimation accuracy. Nevertheless, the proposed architecture remains sufficiently general to provide a wide range of models among the most encountered in the literature. This reduction, achieved by a convenient choice of the activation functions and the initial conditions of the synaptic weights, is developed in two steps. The first step is to train the proposed architecture under two reasonable assumptions. Then the recurrent three-layers neural network is transformed into a representation of two-layer with less number of neurons, that is, a significant reduced number of parameters. The constructed architecture provided models with reasonable reduced number of parameters with a convenient estimation accuracy. To validate the proposed approach, we identify the Wiener-Hammerstein benchmark nonlinear system proposed in SYSID2009 [1].