RBF Neural Network Identifier Based on Optimal Selection Cluster Algorithm and PSO Algorithm and its Application

A model of RBF neural network (RBFNN) is framed to solve the problem of identification of nonlinear system. In order to realize the structure identification of RBFNN, a kind of hybrid parameter optimization algorithm is proposed based on optimal selection cluster algorithm and PSO. By this algorithm, it is optimally gained the hidden layer node number of RBFNN in terms of input samples. Then the structure and parameters optimization problem of RBFNN are solved using PSO. The algorithm is used in oilfield volcanic thickness modeling and prediction, results shows the validity of the algorithm.