Abstract: The vehicle-bridge coupling system is inevitably affected by the parameter uncertainty of systems. To investigate the influence of parameter uncertainty on vehicle-bridge coupling system, the polynomial chaos expansions and autoregressive moving-average with exogenous inputs (PC-ARMAX) model, that can consider the parameter uncertainty of dynamic time-varying system, was proposed. The surrogate models under different system parameters were established by ARMAX model, and the parameters of surrogate models were expanded by polynomial chaos expansions method. Without considering the influence of random track irregularity, the effect of parameter uncertainty, such as the car body mass, the stiffness and damping of the secondary suspension, on vehicle-bridge response was discussed. Then the influence of random track irregularity and parameter uncertainty was further considered. The results show that the predictions by the PC-ARMAX model are consistent with the reference responses obtained by Monte Carlo simulation (MCS), and the maximum error is only 2%. The efficiency can be improved by 2 to 3 orders of magnitude compared with that of MCS method. The mass parameter has the greatest effect on response of vehicles, and the influence of parameter uncertainty cannot be ignored in vehicle-bridge coupled vibration analysis, and it is necessary that the parameter uncertainty of systems and randomness of track irregularity are considered simultaneously.