Form Finding and Evaluating Through Machine Learning: The Prediction of Personal Design Preference in Polyhedral Structures

  • Hao ZhengEmail author
Conference paper


3D Graphic Statics (3DGS) is a geometry-based structural design and analysis method, helping designers to generate 3D polyhedral forms by manipulating force diagrams with given boundary conditions. By subdividing 3D force diagrams with different rules, a variety of forms can be generated, resulting in more members with shorter lengths and richer overall complexity in forms. However, it is hard to evaluate the preference toward different forms from the aspect of aesthetics, especially for a specific architect with his own scene of beauty and taste of forms. Therefore, this article proposes a method to quantify the design preference of forms using machine learning and find the form with the highest score based on the result of the preference test from the architect. A dataset of forms was firstly generated, then the architect was asked to keep picking a favorite form from a set of forms several times in order to record the preference. After being trained with the test result, the neural network can evaluate a new inputted form with a score from 0 to 1, indicating the predicted preference of the architect, showing the possibility of using machine learning to quantitatively evaluate personal design taste.


Machine learning Form finding 3DGS Generative design 


  1. 1.
    Akbarzadeh, M.: 3D graphic statics using polyhedral reciprocal diagrams. Ph.D. thesis (2016). ETH Zürich, Zürich, SwitzerlandGoogle Scholar
  2. 2.
    Akbarzadeh, M., Van Mele, T., Block, P.: Three-dimensional graphic statics: initial explorations with polyhedral form and force diagrams. Int. J. Space Struct. 31, 217–226 (2016)CrossRefGoogle Scholar
  3. 3.
    Bolhassani, M., Ghomi, A.T., Nejur, A., Furkan, M., Bartoli, I., Akbarzadeh, M.: Structural behavior of a cast-in-place funicular polyhedral concrete: applied 3D graphic statics. In: Proceedings of the International Association for Shell and Spatial Structures (IASS) Symposium 2018. MIT, USA, Boston (2018)Google Scholar
  4. 4.
    Culmann, C.: Bericht an den hohen schweizerischen Bundesrath über die Untersuchung der schweiz. Wildbäche: vorgenommen in den Jahren 1858, 1859, 1860 und 1863. Zürcher und Furrer (1864)Google Scholar
  5. 5.
    Ghomi, A.T., Bolhassani, M., Nejur, A., Akbarzadeh, M.: The effect of subdivision of force diagrams on the local buckling, load-path and material use of founded forms. In: Proceedings of IASS Symposium 2018. MIT, Boston, USA (2018)Google Scholar
  6. 6.
    Huang, W., Zheng, H.: Architectural drawings recognition and generation through machine learning. In: Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture, Mexico City, Mexico (2018)Google Scholar
  7. 7.
    Newton, D.: Multi-objective qualitative optimization (MOQO) in architectural design. In: Proceedings of the 36th International Conference on Education and Research in Computer Aided Architectural Design in Europe, Poland (2018)Google Scholar
  8. 8.
    Sjoberg, C., Beorkrem, C., Ellinger, J.: Emergent syntax. In: Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture, Boston, United States (2017)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.School of DesignUniversity of PennsylvaniaPhiladelphiaUSA

Personalised recommendations