Multi-objective optimization of the dynamic performance of a suspended monorail vehicle based on an effective surrogate model

This work presents the multi-objective optimization (MOO) of the dynamic performance of a suspended monorail vehicle (SMV) moving on a curved bridge, based on an effective surrogate model. First, the vehicle-bridge dynamic interaction features are analysed through a dynamic model. Then, an MOO method is developed based on an effective surrogate model. In this method, the accuracy and stability of the radial basis function are enhanced by proposing an innovative improvement strategy and adopting the particle swarm optimization algorithm. The proposed method is validated by a few numerical tests. Based on this verification, the MOO model between key parameters and several optimization objectives is formulated, and the optimization solution set of the vehicle key parameters is obtained using the non-dominated sorting genetic algorithm II. Finally, the optimization effects are revealed by comparing the dynamic performance of the vehicle obtained from the original values and the optimal solution set.