AI strategies for space frame design
The involvement of machine intelligence carries the process of design into a new association between two species which continuously influence each other during the search for an ideal design solution. Such design methodology is of high importance for a more integrated information rich and creative design thinking.
Looking for an emergent result of this collaborative design process, the workshop will concentrate on the generation, optimisation and fabrication of freeform space frame structures with the focus on optimisation of these using Finite Element Analysis and Machine Learning. The participants will be introduced to Machine Learning using a multiple criteria search tool developed by Zeynep Aksoz . In order to train the Machine Learning algorithm, the Finite Element Analysis framework Karamba developed by Clemens Preisinger will be introduced to the participants.
The promising fact about using artificial neural networks is the scalability of locally learned rules to a global system. In this case within a small patch, local rules can be developed, analysed and optimised. These locally learned rules can then be applied to a much larger and complex system. The result is neither completely controlled by the user nor by the computer. It becomes an emergent outcome of the collaboration between two different intelligences.
Zeynep Aksöz, M.Arch is a Marie Curie Fellow, Research Associate and PhD Candidate at the University of Applied Arts in Vienna and she is a partner in Vienna based design studio OpenFields. She received her master’s degree in architecture at the Architectural Association from the Emergent Technologies and Design Program and a Master of Science Degree at the Technical University of Vienna. Recently she is pursuing her research as an Early Stage Researcher within the international Training Network Innochain with the EU Horizon 2020 Grant. Through her ongoing research, teaching and practice Zeynep explores generative design processes through the collaboration between human and machine intelligence.
Clemens Preisinger, D.I. Dr. is a structural engineer and researcher. He started his career as a researcher at the Institute for Structural Concrete at the Technical University Vienna. Since 2008 Clemens is working for the structural engineering company Bollinger–Grohmann. During that time he contributed to several research projects at the University of Applied Arts Vienna. There he currently heads the department 'Digital Simulation' which investigates possibilities to bring computational modelling techniques into early stage architectural design. Since 2010 Clemens is developing the parametric, interactive Finite Element program ‘Karamba’ as a freelancer. He holds a PhD in Structural Engineering from the Technical University Vienna.