A new algorithm for developing dynamic radial basis function neural network models based on genetic algorithms

Abstract

A new algorithm for extracting valuable information from industrial data is presented in this paper. The proposed methodology produces dynamic Radial Basis Function (RBF) neural network models and uses Genetic Algorithms (GAs) to auto-configure the structure of the networks. The effectiveness of the method is illustrated through the development of a dynamical model for a chemical reactor, used in pulp and paper industry.