Computational Technology Resources - CCC

Y. Wang¹, W. Zhang¹, X. Guo¹ and S.-K. Youn²

¹Department of Engineering Mechanics, Dalian University of Technology, China
²Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea

doi:10.4203/ccc.9.3.1

Y. Wang, W. Zhang, X. Guo, S.-K. Youn, "Text-Guided Bio-Architectured Materials Library Building and Application to Structural Design", in P. Iványi, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Fifteenth International Conference on Computational Structures Technology", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 9, Paper 3.1, 2024, doi:10.4203/ccc.9.3.1

Keywords: deep learning, topology optimization, structural genes, text inversion, bio-inspired design, materials library.

Abstract

Advancements in deep learning techniques have not only enhanced intuitive data analysis in structural design but have also facilitated the transfer of deep-level information. The microstructural features of biomaterials, termed "structural genes," inspire engineering design with their uniqueness and complexity, containing a wealth of potential optimization resources. Structural genes are categorized into three main groups based on their functions: structure and mechanical properties, fluid dynamics and substance exchange, and energy management and interaction. The construction of a deep information database founded on these structural genes adds a new dimension to materials science research and revitalizes structural optimization methods. This study refines the text-to-image model to construct a biomaterials database, integrating it into the topology optimization design. This integration allows the design process to incorporate nature's optimization strategies, generating engineering structures that meet mechanical requirements and possess bio-inspired characteristics. Experimental validation presented in this paper showcases a novel paradigm for functional biomimetic design.

download the full-text of this paper (PDF, 9 pages, 1112 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 9 PROCEEDINGS OF THE FIFTEENTH INTERNATIONAL CONFERENCE ON COMPUTATIONAL STRUCTURES TECHNOLOGY Edited by: P. Iványi, J. Kruis and B.H.V. Topping Paper 3.1 Text-Guided Bio-Architectured Materials Library Building and Application to Structural Design Y. Wang¹, W. Zhang¹, X. Guo¹ and S.-K. Youn² ¹Department of Engineering Mechanics, Dalian University of Technology, China ²Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea doi:10.4203/ccc.9.3.1 Full Bibliographic Reference for this paper Y. Wang, W. Zhang, X. Guo, S.-K. Youn, "Text-Guided Bio-Architectured Materials Library Building and Application to Structural Design", in P. Iványi, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Fifteenth International Conference on Computational Structures Technology", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 9, Paper 3.1, 2024, doi:10.4203/ccc.9.3.1 Keywords: deep learning, topology optimization, structural genes, text inversion, bio-inspired design, materials library. Abstract Advancements in deep learning techniques have not only enhanced intuitive data analysis in structural design but have also facilitated the transfer of deep-level information. The microstructural features of biomaterials, termed "structural genes," inspire engineering design with their uniqueness and complexity, containing a wealth of potential optimization resources. Structural genes are categorized into three main groups based on their functions: structure and mechanical properties, fluid dynamics and substance exchange, and energy management and interaction. The construction of a deep information database founded on these structural genes adds a new dimension to materials science research and revitalizes structural optimization methods. This study refines the text-to-image model to construct a biomaterials database, integrating it into the topology optimization design. This integration allows the design process to incorporate nature's optimization strategies, generating engineering structures that meet mechanical requirements and possess bio-inspired characteristics. Experimental validation presented in this paper showcases a novel paradigm for functional biomimetic design. download the full-text of this paper (PDF, 9 pages, 1112 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions