Construction Research Congress 2020
Classification of a Free-Form Surface by Parametric Design and Machine Learning
Publication: Construction Research Congress 2020: Project Management and Controls, Materials, and Contracts
ABSTRACT
The main issue of free-form construction is how to realize a geometric complex design at a reasonable cost. Usually, free-form surfaces are built with straight members and flat panels, because curved elements result in higher costs. However, in order to realize the surfaces as close as the original design, it is essential to use curved panels. Thus, it is important to balance between the realization of design intents and cost reduction. This study is conducted with the aim of optimizing free-form surface modeling from the aspect of cost reduction and meeting the original design intents. First of all, it is required for this purpose to classify a free-form surface into a variety of surface types by multiple attributes. This research proposes a framework to classify a free-form surface by integrating parametric design and machine learning.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Asl, M. R., Stoupine, A. Zarrinmehr, S., and Yan, W. (2015). “Optimo: A BIM-based multi-objective optimization tool utilizing visual programming for high performance building design.”
Carrasco, O., C. (2019). “Gaussian Mixture Models Expleained.” Towards Data Science, https://towardsdatascience.com/gaussian-mixture-models-explained-6986aaf5a95 (Jun. 3, 2019).
Chire (2010). “Cluster Analysis Mouse.”, https://commons.wikimedia.org/wiki/File:ClusterAnalysis_Mouse.svg#filehistory (Sep. 20, 2019).
Fang, Y. (2017). “Optimization of daylighting and energy performance using parametric design, simulation modeling, and genetic algorithms.”
Li, S. Z. (2009). “Encyclopedia of Biometrics: I-Z. (Vol. 2). Springer Science & Business Media.
Lee, C., and Issa, R. R. (2019). “Free-form surface modeling for parametric designs.” Proceedings of 2019 European Conference on Computing in Construction (EC3 2019), Chania, Crete, Greece.
Roudsari, M. S., Pak, M., and Smith, A. (2013, August). “Ladybug: a parametric environmental plugin for grasshopper to help designers create an environmentally-conscious design.” In Proceedings of the 13th international IBPSA conference held in Lyon, France Aug.
Shahbazi, Y., Heydari, M., and Haghparast, F. (2019). “An early-stage design optimization for office buildings’ façade providing high-energy performance and daylight.” Indoor and Built Environment, 1420326X19840761.
Welle, B., Haymaker, J., and Rogers, Z. (2011, December). “ThermalOpt: A methodology for automated BIM-based multidisciplinary thermal simulation for use in optimization environments.” In Building Simulation (Vol. 4, No. 4, pp. 293-313). Tsinghua Press.
Suyoto, W., Indraprastha, A., and Purbo, H. W., (2015). “Parametric approach as a tool for decision-making in planning and design process. Case study: office tower in Kebayoran Lama.” Procedia-Social and Behavioral Sciences, 184, 328-337.
Yi, Y. K. (2019). “Building façade multi-objective optimization for daylight and aesthetical perception.” Building and Environment, 156, 178-190.
Zhu, L., Liu, Y., Yang, Y., and Chen, S. (2019). “Multi-objective optimization of solar curved surface based on parametric design.” Energy Procedia, 158, 446-452.
Information & Authors
Information
Published In
Construction Research Congress 2020: Project Management and Controls, Materials, and Contracts
Pages: 777 - 783
Editors: David Grau, Ph.D., Arizona State University, Pingbo Tang, Ph.D., Arizona State University, and Mounir El Asmar, Ph.D., Arizona State University
ISBN (Online): 978-0-7844-8288-9
Copyright
© 2020 American Society of Civil Engineers.
History
Published online: Nov 9, 2020
Published in print: Nov 9, 2020
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.