Multi-objective optimization design of motor train unit truck frame based on hybrid addition Kriging surrogate model
WANG Weiqi
SONG Yubo
WANG Ying
Abstract：To enhance the computational efficiency of structural lightweight design for complex structures,a structural lightweight design method based on the Kriging surrogate model is proposed.The proposed method incorporates a hybrid addition strategy and a sample deletion strategy considering a distance threshold,aiming to rapidly improve the fitting accuracy of the Kriging surrogate model.This model was then applied to a multi-objective lightweight design model of the truck frame,with the optimization objectives of minimizing frame mass and maximum stress.Subsequently,the multi-objective lightweight model was solved using the non-dominated sorting genetic algorithm-II(NSGA-II).The results demonstrate that the proposed hybrid addition strategy and sample deletion strategy considering the distance threshold effectively enhance the update process of the Kriging surrogate model.The structural lightweight design method based on the Kriging surrogate model exhibits significant advantages in both computational efficiency and lightweight performance.
Keywords：Structural lightweightTruck frameKriging surrogate modelHybrid addition strategy
Publication Date：2025-10-15
Online Publishing Date：2026-09-12(First online date of this platform, not the publication date of the document)
Pages：9( 139-147 )