Latent Crossover for Data-Driven Multifidelity Topology Design
Journal of Mechanical Design · 01.05.2024 · 146 (5)
DOI: 10.1115/1.4064979 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Mechanical Design, online erschienen am 28.03.2024. Verfasst von Taisei Kii und 4 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science.
Abstract (Originalsprache)
Topology optimization is one of the most flexible structural optimization methodologies. However, in exchange for its high level of design freedom, typical topology optimization cannot avoid multimodality, where multiple local optima exist. This study focuses on developing a gradient-free topology optimization framework to avoid being trapped in undesirable local optima. Its core is a data-driven multifidelity topology design (MFTD) method, in which the design candidates generated by solving low-fidelity topology optimization problems are updated through a deep generative model and high-fidelity evaluation. As its key component, the deep generative model compresses the original data into a low-dimensional manifold, i.e., the latent space, and randomly arranges new design candidates over the space. Although the original framework is gradient free, its randomness may lead to convergence variability and premature convergence. Inspired by a popular crossover operation of evolutionary algorithms (EAs), this study merges the data-driven MFTD framework and proposes a new crossover operation called latent crossover. We apply the proposed method to a maximum stress minimization problem in 2D structural mechanics. The results demonstrate that the latent crossover improves convergence stability compared to the original data-driven MFTD method. Furthermore, the optimized designs exhibit performance comparable to or better than that in conventional gradient-based topology optimization using the P-norm measure.
Förderung
- Japan Society for the Promotion of Science
Zitieren
APA
Kii, T., Yaji, K., Fujita, K., Sha, Z., & Seepersad, C. C. (2024). Latent Crossover for Data-Driven Multifidelity Topology Design. Journal of Mechanical Design, 146(5). https://doi.org/10.1115/1.4064979
Vancouver
Kii T, Yaji K, Fujita K, Sha Z, Seepersad CC. Latent Crossover for Data-Driven Multifidelity Topology Design. Journal of Mechanical Design. 2024;146(5). doi:10.1115/1.4064979
BibTeX
@article{Kii2024,
author = {Kii, Taisei and Yaji, Kentaro and Fujita, Kikuo and Sha, Zhenghui and Seepersad, Carolyn Conner},
title = {Latent Crossover for Data-Driven Multifidelity Topology Design},
journal = {Journal of Mechanical Design},
year = {2024},
volume = {146},
number = {5},
doi = {10.1115/1.4064979}
}
EUVIMED