Identification of an Experimental Process by B-spline Neural Network Using Improved Differential Evolution Training

Abstract

B-spline neural network (BSNN), a type of basis function neural network, is trained by gradient-based methods, which may fall into local minimum during the learning procedure. To overcome the problems encountered by the conventional learning methods, differential evolution (DE)  an evolutionary computation methodology  can provide a stochastic search to adjust the control points of a BSNN are proposed. DE incorporates an efficient way of self-adapting mutation using small populations. The potentialities of DE are its simple structure, easy use, convergence property, quality of solution and robustness. In this paper, we propose a modified DE using chaotic sequence based on logistic map to train a BSNN. The numerical results presented here indicate that the chaotic DE is effective in building a good BSNN model for nonlinear identification of an experimental nonlinear yo-yo motion control system.

4 Figures and Tables

Cite this paper

@inproceedings{Coelho2006IdentificationOA, title={Identification of an Experimental Process by B-spline Neural Network Using Improved Differential Evolution Training}, author={Leandro dos Santos Coelho and Fabio Alessandro Guerra and Leandro Borges dos Santos}, year={2006} }