A nonlinear neural network adaptive backstepping control method is proposed to improve the performance of the magnetic levitation control system of the electrically excited linear synchronous motor (EELSM). The structure and operation mechanism of EELSM are studied. The state equation and mathematical model of EELSM magnetic levitation system are established. In order to overcome the uncertain disturbance existing in the operation of EELSM magnetic levitation platform, a nonlinear neural network adaptive backstepping controller is designed to estimate the disturbance. The stability of the system is proved by constructing the Lyapunov function. The MATLAB software is used to perform computer simulation on the control system, and the simulation results verify the effectiveness of the proposed method.