Combined Approach of Rbf Neural Nework, Genetic Algorithm and Local Search and Its Application in Identification of a Nonlinear Process

The identification of nonlinear systems by artificial neural networks has been successfully applied in many applications. In this context, the radial basis function neural network (RBF-NN) is a powerful approach for nonlinear identification. A RBF neural network has an input layer, a hidden layer and an output layer. The neurons in the hidden layer contain Gaussian transfer functions whose outputs are inversely proportional to the distance from the center of the neuron. In this paper, a combined approach including RBF-NN neural network with training based on genetic algorithm (GA) and local search is presented. During the identification procedure, the GA with local search aims to optimize the parameters of RBF-NN and the optimum values are regarded as the initial values of the RBF-NN parameters. The validity and accuracy of identification of RBF-NN model are tested by simulations, whose results reveal that it is feasible to establish a good model for a nonlinear process of pH neutralization.