This project introduces a computer-aided design framework for the generation of non-standard structural forms in static equilibrium that takes advantage of the interaction between human and machine intelligence. The design framework relies on the implementation of a series of operations (generation, clustering, evaluation, selection) that allow creating multiple design options and navigating through the design space according to objective and subjective criteria defined by the human designer.
Within the proposed framework, two main algorithms are used:
- Combinatorial Equilibrium Modeling (https://github.com/OleOhlbrock/CEM)
- Self-Organizing Map (https://github.com/sevamoo/SOMPY)
The work presented here is a further development of a research project started in 2018 as a collaboration between the Chair of Digital Architectonics (Karla Saldana Ochoa, Vahid Moosavi) and the Chair of Structural Design (Pierluigi D'Acunto, Patrick Ole Ohlbrock) at ETH Zurich (https://github.com/sakarla/Beyond-typologies-beyond-optimization). The scripts and tools included in this repository were developed for the workshop "Structural Form-Finding with Machine Learning" at the Advances in Architectural Geometry (AAG) 2020 (https://www.aag2020.com/form-finding-machine-learning).
SDML is developed by:
- Pierluigi D'Acunto Technical University of Munich, Professorship of Structural Design
- Patrick Ole Ohlbrock ETH Zurich, Chair of Structural Design
- Karla Saldana Ochoa University of Florida, School of Architecture
- Vahid Moosavi SwissRe, Zurich
If you use the scripts in SDML, please reference the official GitHub repository:
@Misc{sdml2021,
author = {D'Acunto, Pierluigi and Ohbrock, Patrick Ole and Saldana Ochoa, Karla and Moosavi, Vahid},
title = {{SDML: Structural Design supported by Machine Learning}},
year = {2021},
url = {https://github.com/pierluigidacunto/SDML},
}
To use SDML, please make sure that the Python distribution platform Anaconda3 is installed on your computer.
Publications related to the SDML project include:
- Karla Saldana Ochoa, Ohlbrock,Patrick Ole Ohlbrock, Pierluigi D′Acunto, Vahid Moosavi: Beyond typologies, beyond optimization, International Journal of Architectural Computing, 9(3), 466–490, 2021
- Federico Bertagna, Pierluigi D'Acunto, Patrick Ole Ohlbrock, Vahid Moosavi: Holistic Design Explorations of Build-ing Envelopes Supported by Machine Learning. Journal of Facade Design and Engineering, 9(1), 31-46, 2021
- Patrick Ole Ohlbrock, Pierluigi D′Acunto: A Computer-aided Approach to Equilibrium Design based on Graphic Statics and Combinatorial Variations, Computer-Aided Design, Volume 121, 102802, 2020
- Lukas Fuhrimann, Vahid Moosavi, Patrick Ole Ohlbrock, Pierluigi D′Acunto: Data-Driven Design: Exploring new Structural Forms using Machine Learning and Graphic Statics, Proceedings of the IASS Symposium 2018 - Creativity in Structural Design, Boston, 2018