In order to solve the problem that it is difficult to choose the weighting coefficient objectively when using the optimal control of vehicle suspension, an optimal control method of semiactive suspension based on genetic algorithm was proposed. In the MATLAB/Simulink environment, the models of 1/4 semiactive suspension, 1/4 passive suspension and random road were established. Secondly, the calibration test of magnetorheological damper was carried out, and the displacement and velocity curves of the damper under different working conditions were obtained. By using the parameter fitting toolbox and BP neural network, the modified Dahl parameterized forward and reverse models were fitted and verified. Thirdly, on the basis of optimal control theory, the weight coefficient of semi-active suspension evaluation index was selected by using genetic algorithm, and the genetic optimal controller was established. Finally, the simulation verification and analysis were carried out. The results show that by using the genetic algorithm to determine the weighting coefficient of the optimal controller, the ride comfort of the vehicle can be improved.