Citation

Qian L, Yu L, Huang Y, Jiang P, Gu X. Int. J. Crashworthiness 2023; 28(2): 202-216.

Copyright

(Copyright © 2023, Informa - Taylor and Francis Group)

DOI

10.1080/13588265.2022.2074705

PMID

unavailable

Abstract

Whale optimization algorithm (WOA) is a novel-innovative swarm-based meta-heuristic algorithm with excellent performance, but it may still be trapped into local extremum for troublesome problems. To this end, an improved multi-objective whale optimization algorithm (IMOWOA) is proposed to cover the shortages. Firstly, in the search stage of WOA, individual difference is considered to strengthen the exploration ability, and evolution operators are introduced to regenerate the stagnated population to prevent premature convergence. Next, the performance of IMOWOA is compared with MOWOA and other classical optimization algorithms, and a series of multi-objective test functions are used. The results on the convergence and diversity of Pareto front confirm that IMOWOA has better feasibility and competitiveness. Finally, integrated with the least squares support vector regression (LSSVR) model, IMOWOA is applied to the deterministic optimization of vehicle structural crashworthiness. The conclusion testified the efficiency of IMOWOA in the field of vehicle crashworthiness.

Language: en

Keywords

evolution operators; Improved multi-objective whale optimization; individual difference; vehicle structural crashworthiness