Automatic control of high-speed trains, especially fault-tolerant control tracking, has become a research hotspot in recent years. This paper proposes an adaptive fault-tolerant controller based on fast non-singular terminal sliding mode control for the longitudinal dynamics model of the high-speed train. The controller utilizes nonlinear disturbance observer and Radial Basis Function Neural Networks to address unknown nonlinear dynamics and disturbances in train system. Firstly, an unknown nonlinear dynamics model, considering time-varying actuator faults, is established for the high-speed train using a multi-mass dynamics model. Then, the adaptive fast non-singular terminal sliding mode fault-tolerant controller is designed based on the multi-mass dynamics model. The radial basis function neural networks approximate the unknown nonlinear dynamics of the system, while the nonlinear disturbance observer observes the unknown disturbances. Finally, the stability of the controller is verified through Lyapunov function and its derivative. Simulation results show the effectiveness of the proposed method, exhibiting precise control and fast tracking speed.