Data-Driven Morphological Exploration and Shape Optimization for Turbulent Pipe Systems

Urata, Kazuya; Tsumoto, Ryo; Yaji, Kentaro; Fujita, Kikuo

doi:https://doi.org/10.1115/1.4068984

Data-Driven Morphological Exploration and Shape Optimization for Turbulent Pipe Systems

Urata, Kazuya; Tsumoto, Ryo; Yaji, Kentaro et al.

Journal of Mechanical Design, 2025, 147(9), 091704

アクセス数:7件（2025-11-19 01:36 集計）

固定URL: https://hdl.handle.net/11094/102927

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
JMechDes_147_9_091704	pdf	なし	1.96 MB	7	2025.10.31

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 Morphological Exploration and Shape Optimization for Turbulent Pipe Systems
著者	著者名 Urata, Kazuya
	著者名 Tsumoto, Ryo
	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 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
	data-driven topology design
	deep clustering
	design optimization
	generative design
	multi-objective optimization
	shape optimization
	structural optimization
	topology optimization
	turbulence problem
内容	Urata K., Tsumoto R., Yaji K., et al. Data-Driven Morphological Exploration and Shape Optimization for Turbulent Pipe Systems. Journal of Mechanical Design 147, 091704 (2025); https://doi.org/10.1115/1.4068984.
抄録	Optimal arrangements of turbulent pipe systems strongly depend on branch patterns, and turbulence fields typically cause involved multimodality in the solution space. These features hinder gradient-based structural optimization frameworks from finding promising solutions for turbulent pipe systems. In this article, we propose a multi-stage framework that integrates data-driven morphological exploration and evolutionary shape optimization to address the challenges posed by the complexity of turbulent pipe systems. Our framework begins with data-driven morphological exploration, aiming to find promising morphologies. It results in the shapes for selecting a reasonable number of candidates for the next shape refinement stage. Herein, we employ data-driven topology design, a gradient-free, and multi-objective optimization methodology incorporating a deep generative model and the concept of evolutionary algorithms to generate promising arrangements. Subsequently, a deep clustering strategy extracts representative shapes. The final stage involves refining these shapes through shape optimization using a genetic algorithm. Applying the framework to a two-dimensional turbulent pipe system with a minimax objective shows its effectiveness in delivering high-performance solutions for the turbulent flow optimization problem with branching.
出版者	American Society of Mechanical Engineers (ASME)
収録物名	Journal of Mechanical Design
巻(号)	147(9)
ページ	091704
刊行年月	2025-07-21
言語	英語
ハンドルURL	https://hdl.handle.net/11094/102927
PISSN	10500472
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1115/1.4068984
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	Journal of Mechanical Design. 2025, 147(9), p. 091704
DC.title	Data-Driven Morphological Exploration and Shape Optimization for Turbulent Pipe Systems
DC.creator	Urata, Kazuya
	Tsumoto, Ryo
	Yaji, Kentaro
	Fujita, Kikuo
DC.publisher	American Society of Mechanical Engineers (ASME)
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-07-21
DC.identifier	https://doi.org/10.1115/1.4068984
DC.subject	data-driven design
	data-driven topology design
	deep clustering
	design optimization
	generative design
	multi-objective optimization
	shape optimization
	structural optimization
	topology optimization
	turbulence problem
DC.description	Urata K., Tsumoto R., Yaji K., et al. Data-Driven Morphological Exploration and Shape Optimization for Turbulent Pipe Systems. Journal of Mechanical Design 147, 091704 (2025); https://doi.org/10.1115/1.4068984.
DCTERMS.abstract	Optimal arrangements of turbulent pipe systems strongly depend on branch patterns, and turbulence fields typically cause involved multimodality in the solution space. These features hinder gradient-based structural optimization frameworks from finding promising solutions for turbulent pipe systems. In this article, we propose a multi-stage framework that integrates data-driven morphological exploration and evolutionary shape optimization to address the challenges posed by the complexity of turbulent pipe systems. Our framework begins with data-driven morphological exploration, aiming to find promising morphologies. It results in the shapes for selecting a reasonable number of candidates for the next shape refinement stage. Herein, we employ data-driven topology design, a gradient-free, and multi-objective optimization methodology incorporating a deep generative model and the concept of evolutionary algorithms to generate promising arrangements. Subsequently, a deep clustering strategy extracts representative shapes. The final stage involves refining these shapes through shape optimization using a genetic algorithm. Applying the framework to a two-dimensional turbulent pipe system with a minimax objective shows its effectiveness in delivering high-performance solutions for the turbulent flow optimization problem with branching.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	102927
citation_title	Data-Driven Morphological Exploration and Shape Optimization for Turbulent Pipe Systems
citation_author	Urata, Kazuya
	Tsumoto, Ryo
	Yaji, Kentaro
	Fujita, Kikuo
citation_publisher	American Society of Mechanical Engineers (ASME)
citation_language	英語
citation_date	2025-07-21
citation_journal_title	Journal of Mechanical Design
citation_volume	147
citation_issue	9
citation_firstpage	091704
citation_doi	https://doi.org/10.1115/1.4068984
citation_public_url	https://hdl.handle.net/11094/102927

Data-Driven Morphological Exploration and Shape Optimization for Turbulent Pipe Systems

閲覧可能ファイル

論文情報

論文詳細を表示