An Hinfin robust controller based on local feedback recurrent neural network (RNN) is proposed for the position tracking control of the permanent magnet linear synchronous motor (PMLSM). The proposed local feedback RNN with a simple-architecture is employed to estimate dynamic mapping of lumped element uncertainty. Based on the result of RNN, the quadric form function of the Hinfin robust controller is chosen and the performance index stabilizing the closed loop is obtained. The simulated results show that the PMLSM control system with large parameter changes and external disturbances has good robustness and control performances