Considering the influence of the uncertainty of design variables on the optimization design, the robust optimization design theory was used to build a robust model for the powertrain mounting system of automobiles. In this model, decoupling of energy distribution was taken as the target, the stiffness parameters of the mounting was taken as a design variable, and the mean and standard deviation of the target results were considered. Aiming at the problem that the particle swarm algorithm was easy to fall into a local optimal solution, a hybrid particle swarm algorithm was adopted to optimize the stiffness of the mounting of the powertrain mounting system, and the Monte Carlo method was used to analyze the optimized results to examine the influence of the variety of design values on the objective function. The results show that the method can improve the robustness of the mounting system effectively.