A direct adaptive predictive control based on T-S fuzzy model was proposed. The structure parameters of T-S fuzzy model were identified online using the weighted recursive least squares method. The identified parameters of fuzzy model were used to directly receive the model predicted output with direct iterative for the T-S model. The algorithm is a good way to resolve the two major problems, modeling and optimization, and provide a guarantee for high-precision control of nonlinear systems. Simulation result shows that the proposed algorithm is an effective control strategy with excellent tracing ability.