Conceptual design of structures using machine learning
Dr. Kanyilmaz and his team in Politecnico di Milano developed and validated a computer-assisted tool based on Non-dominated Sorted Genetic Algorithm II (NSGA-II) that can be used to analyse a wide range of safe, economical and ecological options for the conceptual design of buildings.
The design space starts from a design brief (with only a little information about the site characteristics and project objectives). The solutions are explored with the material, grid size, floor type, lateral resistance, and foundation system variables. In a short computational time (< 2 min per run), users are provided with a Pareto graph of a large set of feasible solutions (in terms of cost, embodied CO2 emissions and free space) that an engineer would not be typically able to evaluate within a traditional conceptual design process. More details can be read in the following articles:
Image classification using conventional neural networks
Dr. Kanyilmaz and his team have been developing a convolutional neural network tool that is capable of assessing the images for several criteria i.e. corrosion, damage, connection type. The objective of the tool is to support the engineers and architects while giving re-use/recycle decisions.
More details can be read in the following articles:
22 January 2024
In today’s Global Construction Review article, Dr. Kanyilmaz challenges the oversimplified views on sustainable construction. His team’s AI-powered tool emphasized that sustainability depends on multiple factors, including building design and material sourcing. Notably, reused steel is identified as exceptionally sustainable, surpassing traditional materials like timber and
25 September 2023
Kanyilmaz, A., Birhane, M., Fishwick, R., Castillo C.. Reuse of Steel in the Construction Industry: Challenges and Opportunities. Int J Steel Struct (2023). https://doi.org/10.1007/s13296-023-00778-4. In this article, we presented the current barriers for the re-use of steel in construction indsutry, and proposed solutions to them by leveraging the digital technologies and artificial intelligence.
27 April 2022
Our MSc student Van Hoi Dang discussed successfully his thesis “Conceptual Design of Mass Timber Structures using Genetic Algorithms“. Full mark for him, grateful for his co-supervisor PhD candidate Aleksei Kondratenko, and thanks to Sustainability Director (Skanska) Tolga Tutar for the industry cooperation.
25 March 2021 11:30 CET Speaker in AI in AEC conference: “A multi-criteria conceptual design method using genetic algorithms to optimize structures’ cost and environmental impacts”
Dr. Kanyilmaz presented their latest research, where his team developed an AI-based computer-assisted design tool to assist structural engineers in the decision-making process of building design. The tool is