Rbf Neural Network Based On Genetic Algorithm In System Identification Applications

System identification is the basis of control theory. The traditional identification algorithms are usually based on the linear system theory and it is difficult for them to be applied in nonlinear system identification. Due to their powerful ability of approximating nonlinear functions, and with the characteristics of adaptive learning, parallel and distributed processing ability, strong robustness and fault tolerance, neural networks have been an effective approach to model and control the unknown and uncertain nonlinear systems.RBF neural network is a new and effective neural network .It has the best and universal approximation property, simple structure and fast training speed. So it has particular advantages when applied in system identification. The choice f quantity and position of hidden layer radial basis functions is very important and directly affects the goodness of fit of overall network approximation capabilities. In this paper, a new optimization algorithm based on genetic algorithm for RBF neural network is presented after traditional algorithms are thoroughly researched.In the algorithm of this paper, genetic algorithm is applied to auto-configure the networks and obtain the model parameters. It avoids the disadvantage of traditional algorithms which are often trapped to local minima. Another advantage of the method is that it isn't required to designate the network structure in advance by experience or plenty of trials. According to the simulation, the method has higher optimization precision.Finally, the network based on this algorithm is applied on nonlinear system identification. According to simulation, the method has higher precision and good generalization ability.