Study on Intelligent Hybrid Algorithm

The radial basis function (RBF), which is well known dynamic neural network, has been improved to easily apply in dynamic systems identification. However, the RBF weights and thresholds, which are trained by the gradient descent method, will be fixed after the training completing. The adaptive ability is bad. To improve RBF performance of dynamic identification, a self-adaptive particle swarm optimization (SAPSO), which is a stochastic search algorithm, is employed to train and adjust RBF structure parameter online. The simulation experiments show that SAPSO-NN has less adjustable parameters, faster convergence speed and higher precision in the nonlinear function identification.