For the vertical vibration problems of virtual track train, an active suspension control strategy is designed based on wheelbase preview principle. Firstly, the vertical vibration model of the train coupled with the stochastic uneven road is established, where the road is treated as the timedomain excitation of road unevenness in the linear filter white noise method. Secondly, the active suspension controller of the train is developed using the linear quadratic Gaussian (LQG) control theory based on the train wheelbase preview information. The adaptive particle swarm optimization (APSO) is used to optimize the weighting coefficients of the developed controller. Finally, the vertical dynamics of the train under the excitation of random and pulse roads is studied. The simulation results show that the control strategy reduces the vertical vibration of each vehicle body of the train under road excitations, and has good robustness against with different road grades and train speeds, and the ride comfort of the train is improved.