For a chaotic system with nonlinear ity and uncertainty, it is difficult to obtain the satisfactory performance using general control methods. A least square support vector marchine (LSSVM) control method based on particle swarm optimigation(PSO), is proposed for chaos control. Optimizing two parameters of LSSVM model by PSO abilities of the fast convergence and whole optimization, thus aroiding the blindness of man-made choice, the LSSVM-PSO model can enhance the capability of forecasting. The proposed method does not need any analytic model, and it is still effective in the presence of measurement noises. Simulation results with a Logistic mapping and Henon attractor show the effectiveness and feasibility of this method.