Support vector machine (SVM)resembles Radius basis function (RBF) neural networks in structure. Considering their resemblance, a new optimization algorithm based on support vector machine and genetic algorithm for RBF neural network is presented, in which GA is used to choose the SVM model parameter and SVM is used to help constructing the RBF. The network based on this algorithm is applied to nonlinear system identification. Simulation results show that the network based on this algorithm has higher precision and better generalization ability.