Predicting and steering performance in architectural materials

Predicting and steering performance in architectural materials

Thomsen, Mette; Nicholas, Paul; Tamke, Martin; Gatz, Sebastian; Sinke, Yuliya

:

This paper presents the prototyping of new methods by which functionally gradedmaterials can be specified and produced. The paper presents a case studyexploring how machine learning can be used to train a model in order to predictfabrication files from formalised design requirements. By using knit as a modelfor material fabrication, the paper outlines the making of new cyclical designmethods employing machine learning in which simpler prototypical materials actsas input for more complex graded materials. A case study - Ombre - showcasesthe implementation of this workflow and results and perspectives are discussed.

This paper presents the prototyping of new methods by which functionally gradedmaterials can be specified and produced. The paper presents a case studyexploring how machine learning can be used to train a model in order to predictfabrication files from formalised design requirements. By using knit as a modelfor material fabrication, the paper outlines the making of new cyclical designmethods employing machine learning in which simpler prototypical materials actsas input for more complex graded materials. A case study - Ombre - showcasesthe implementation of this workflow and results and perspectives are discussed.

Palavras-chave:

DOI: 10.5151/proceedings-ecaadesigradi2019_150

Referências bibliográficas

• [1]

Como citar:

Thomsen, Mette; Nicholas, Paul; Tamke, Martin; Gatz, Sebastian; Sinke, Yuliya; "Predicting and steering performance in architectural materials", p-485-494. 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_150