Data-driven topology design with persistent homology for enhancing population diversity

Kii, Taisei; Yaji, Kentaro; Teramoto, Hiroshi; Fujita, Kikuo

doi:https://doi.org/10.1016/j.ijmecsci.2025.110493

Data-driven topology design with persistent homology for enhancing population diversity

Kii, Taisei; Yaji, Kentaro; Teramoto, Hiroshi et al.

International Journal of Mechanical Sciences, 2025, 301, 110493

アクセス数:6件（2025-09-03 21:28 集計）

固定URL: https://hdl.handle.net/11094/102626

閲覧可能ファイル

ファイル	フォーマット	利用条件	サイズ	閲覧回数	利用開始日	説明	information
IntJMechSci_301	pdf	なし	2.01 MB	7	2025.08.29

Creative Commons : 表示

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	Data-driven topology design with persistent homology for enhancing population diversity
著者	ORCID 0009-0001-8856-2467 0009-0001-8856-2467 Scopus Author ID 58753546300 58753546300 著者名 Kii, Taisei
	NRID 1000090779373 1000090779373 ORCID 0000-0002-4309-2043 0000-0002-4309-2043 researchmap permalink yajiken0609 yajiken0609 Scopus Author ID 55787947500 55787947500 著者名 Yaji, Kentaro
	NRID 1000090463728 1000090463728 著者名 Teramoto, Hiroshi
	NRID 1000010228992 1000010228992 ORCID 0000-0002-2197-1012 0000-0002-2197-1012 researchmap permalink read0014111 read0014111 Scopus Author ID 7404057902 7404057902 著者名 Fujita, Kikuo
キーワード等	Data-driven design
	Evolutionary algorithm
	Persistent homology
	Population diversity
	Topology optimization
	Wasserstein distance
内容	Kii T., Yaji K., Teramoto H., et al. Data-driven topology design with persistent homology for enhancing population diversity. International Journal of Mechanical Sciences 301, 110493 (2025); https://doi.org/10.1016/j.ijmecsci.2025.110493.
抄録	This paper proposes a selection strategy for enhancing population diversity in data-driven topology design (DDTD), a topology optimization framework based on evolutionary algorithms (EAs) using a deep generative model. While population diversity is essential for global search with EAs, conventional selection operators that preserve diverse solutions based on objective values may still lead to a loss of population diversity in topology optimization problems due to the high dimensionality of design variable space and strong nonlinearity of evaluation functions. Motivated by the idea that topology is what characterizes the inherent diversity among material distributions, we employ a topological data analysis method called persistent homology. As a specific operation, a Wasserstein distance sorting between persistence diagrams is introduced into a selection algorithm to maintain the intrinsic population diversity. We apply the proposed selection operation incorporated into DDTD to a stress-based topology optimization problem as a numerical example. The results confirm that topological features extracted via persistent homology can be appropriately quantified using the Wasserstein distance, and incorporating them into the selection operation significantly enhances the search performance of DDTD.
出版者	Elsevier Ltd
収録物名	International Journal of Mechanical Sciences
巻(号)	301
ページ	110493
刊行年月	2025-06-28
言語	英語
ハンドルURL	https://hdl.handle.net/11094/102626
PISSN	00207403
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1016/j.ijmecsci.2025.110493
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution 4.0 International License.
出版タイプ	Version of Record
カテゴリ	学術雑誌論文 Journal Article

資源タイプ	学術雑誌論文
ローカル資源タイプ	学術雑誌論文
DCMI資源タイプ	text
DCTERMS.bibliographicCitation	International Journal of Mechanical Sciences. 2025, 301, p. 110493
DC.title	Data-driven topology design with persistent homology for enhancing population diversity
DC.creator	Kii, Taisei
	Yaji, Kentaro
	Teramoto, Hiroshi
	Fujita, Kikuo
DC.publisher	Elsevier Ltd
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-06-28
DC.identifier	https://doi.org/10.1016/j.ijmecsci.2025.110493
DC.subject	Data-driven design
	Evolutionary algorithm
	Persistent homology
	Population diversity
	Topology optimization
	Wasserstein distance
DC.description	Kii T., Yaji K., Teramoto H., et al. Data-driven topology design with persistent homology for enhancing population diversity. International Journal of Mechanical Sciences 301, 110493 (2025); https://doi.org/10.1016/j.ijmecsci.2025.110493.
DCTERMS.abstract	This paper proposes a selection strategy for enhancing population diversity in data-driven topology design (DDTD), a topology optimization framework based on evolutionary algorithms (EAs) using a deep generative model. While population diversity is essential for global search with EAs, conventional selection operators that preserve diverse solutions based on objective values may still lead to a loss of population diversity in topology optimization problems due to the high dimensionality of design variable space and strong nonlinearity of evaluation functions. Motivated by the idea that topology is what characterizes the inherent diversity among material distributions, we employ a topological data analysis method called persistent homology. As a specific operation, a Wasserstein distance sorting between persistence diagrams is introduced into a selection algorithm to maintain the intrinsic population diversity. We apply the proposed selection operation incorporated into DDTD to a stress-based topology optimization problem as a numerical example. The results confirm that topological features extracted via persistent homology can be appropriately quantified using the Wasserstein distance, and incorporating them into the selection operation significantly enhances the search performance of DDTD.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	102626
citation_title	Data-driven topology design with persistent homology for enhancing population diversity
citation_author	Kii, Taisei
	Yaji, Kentaro
	Teramoto, Hiroshi
	Fujita, Kikuo
citation_publisher	Elsevier Ltd
citation_language	英語
citation_date	2025-06-28
citation_journal_title	International Journal of Mechanical Sciences
citation_volume	301
citation_firstpage	110493
citation_doi	https://doi.org/10.1016/j.ijmecsci.2025.110493
citation_public_url	https://hdl.handle.net/11094/102626

Data-driven topology design with persistent homology for enhancing population diversity

閲覧可能ファイル

論文情報

論文詳細を表示