kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Generative structural design for rapid embodied carbon evaluation
KTH, School of Architecture and the Built Environment (ABE), Civil and Architectural Engineering, Concrete Structures.
2025 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

The art and science of structural engineering have played a vital role in shaping the built environment, often relying on methodologies that are far from optimal. Parametric design has become a widely used method among structural engineers for design exploration and better collaboration with architects in the early design stages. Combined with the increasing integration of Artificial Intelligence into everyday applications, this approach others the potential to enhance the current methodologies and make the use of finite element software more accesible.In this thesis, a parametric finite element model has been developed to generate a wide range of structural topologies to train a machine learning regression model capable of predicting material quantities in terms of embodied carbon. The parameterized algorithm focuses on frame-core wall structural systems of arbitrary 2D shapes, though the model is trained with a limited set of shape variations.The main algorithm enables rapid finite element model creation based on simple geometric inputs and allows for the identification of potential material optimization. Despite some simplifications, such as simplified wall distribution and uniform core cross-sections, the analytical approach taken achieves reasonable accuracy and provides significant value in the design exploration in early stages. Meanwhile, the prediction results demonstrate the potential of using machine learning to estimate embodied carbon despite inconsistencies in the results, highlighting the quasi-linear nature of the problem due to the aforementioned simplifications and the potential for data-driven insights.The study successfully provides a foundation for further exploration of embodied carbon prediction using artificial intelligence, offering a pathway toward more efficient design practices.

 

Place, publisher, year, edition, pages
2025.
Series
TRITA-ABE-MBT ; 2535
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-360090OAI: oai:DiVA.org:kth-360090DiVA, id: diva2:1938329
External cooperation
Tyréns Sverige AB
Supervisors
Examiners
Available from: 2025-02-18 Created: 2025-02-18

Open Access in DiVA

fulltext(7356 kB)87 downloads
File information
File name FULLTEXT01.pdfFile size 7356 kBChecksum SHA-512
5f19787146acc8614f110d3525b49dd41e045c20402fc2931a824d0f0e1a630f7022c6fe2c9eb3b967981700e2f23712b85b5d67c75cdb2548fd316d07e5dddf
Type fulltextMimetype application/pdf

By organisation
Concrete Structures
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 87 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 385 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf