Design Space Exploration of Initial Structural Design Alternatives via Artificial Neural Networks

Design Space Exploration of Initial Structural Design Alternatives via Artificial Neural Networks

Yetkin, Ozan; Sorguç, Arzu Gönenç

Article:

Increasing implementation of digital tools within a design process generatesexponentially growing data in each phase, and inevitably, decision making withina design space with increasing complexity will be a great challenge for thedesigners in the future. Hence, this research aimed to seek potentials of captureddata within a design space and solution space of a truss design problem forproposing an initial novel approach to augment capabilities of digital tools byartificial intelligence where designers are allowed to make a wise guess withinthe initial design space via performance feedbacks from the objective space.Initial structural design and modelling phase of a truss section was selected as amaterial of this study since decisions within this stage affect the whole processand performance of the end product. As a method, a generic framework wasproposed that can help designers to understand the trade-offs between initialstructural design alternatives to make informed decisions and optimizationsduring the initial stage. Finally, the proposed framework was presented in a casestudy, and future potentials of the research were discussed.

Increasing implementation of digital tools within a design process generatesexponentially growing data in each phase, and inevitably, decision making withina design space with increasing complexity will be a great challenge for thedesigners in the future. Hence, this research aimed to seek potentials of captureddata within a design space and solution space of a truss design problem forproposing an initial novel approach to augment capabilities of digital tools byartificial intelligence where designers are allowed to make a wise guess withinthe initial design space via performance feedbacks from the objective space.Initial structural design and modelling phase of a truss section was selected as amaterial of this study since decisions within this stage affect the whole processand performance of the end product. As a method, a generic framework wasproposed that can help designers to understand the trade-offs between initialstructural design alternatives to make informed decisions and optimizationsduring the initial stage. Finally, the proposed framework was presented in a casestudy, and future potentials of the research were discussed.

Palavras-chave:

DOI: 10.5151/proceedings-ecaadesigradi2019_308

Referências bibliográficas

• [1]

Como citar:

Yetkin, Ozan; Sorguç, Arzu Gönenç; "Design Space Exploration of Initial Structural Design Alternatives via Artificial Neural Networks", p-55-60. In: Proceedings of 37 eCAADe and XXIII SIGraDi Joint Conference, “Architecture in the Age of the 4Th Industrial Revolution”, Porto 2019, Sousa, José Pedro; Henriques, Gonçalo Castro; Xavier, João Pedro (eds.). São Paulo: Blucher, 2019.
ISSN 23186968, DOI 10.5151/proceedings-ecaadesigradi2019_308