Aimed at the problem that the control system for a primary permanent magnet linear motor (PPMLM) is susceptible to uncertain factors such as load disturbance and parameter change, an action-dependent heuristic dynamic programming control algorithm is used to improve the control performance and anti-disturbance capability of the system while reducing the thrust force fluctuation. First, the mathematical model of the direct thrust force control system for PPMLM is constructed. Second, the speed tracking problem is transformed into an optimal control problem, which is further transformed into a problem of solving the Hamilton-Jacobi-Bellman equation by minimizing the performance index function and the speed tracking error. The numerical solution of the Bellman equation is obtained by using a strategy iteration algorithm based on the Bellman criterion. Finally, an accurate tracking of speed is achieved. To solve the problem that the BP neural network is easy to fall into local optimum, an adaptive learning rate is designed. In addition, in view of the problem of approximate error existing in the BP neural network, a robust compensation term is added to the control law to improve the accuracy of speed tracking. Afterwards, the stability of the closed-loop system is analyzed. Simulation results show that the proposed control strategy can improve the speed tracking performance of the system, reduce the thrust force fluctuation and restrain load disturbance and other nonlinear factors.