The spacecra equipment layout optimization design (SELOD) problems with complicated performance constraints and diversity are studied in this paper. The previous literature uses the gradient-based algorithm to obtain optimized non-overlap layout schemes from randomly initialized cases e ectively. However, these local optimal solutions are too di cult to jump out of their current relative geometry relationships, signi cantly limiting their further improvement in performance indicators. Therefore, considering the geometric diversity of layout schemes is put forward to alleviate this limitation. First, similarity measures, including modi ed cosine similarity and gaussian kernel function similarity, are introduced into the layout optimization process. Then the optimization produces a set of feasible layout candidates with the most remarkable di erence in geometric distribution and the most representative schemes are sampled. Finally, these feasible geometric solutions are used as initial solutions to optimize the physical performance indicators of the spacecra , and diversi ed layout schemes of spacecra equipment are generated for the engineering practice. The validity and e ectiveness of the proposed methodology are demonstrated by two SELOD applications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.