CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

id acadia16_72
authors Harrison, Paul
year 2016
title What Bricks Want: Machine Learning and Iterative Ruin
source ACADIA // 2016: POSTHUMAN FRONTIERS: Data, Designers, and Cognitive Machines [Proceedings of the 36th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-77095-5] Ann Arbor 27-29 October, 2016, pp. 72-77
summary Ruin has a bad name. Despite the obvious complications, failure provides a rich opportunity—how better to understand a building’s physicality than to watch it collapse? This paper offers a novel method to exploit failure through physical simulation and iterative machine learning. Using technology traditionally relegated to special effects, we can now understand collapse on a granular level: since modern-day physics engines track object-object collisions, they enable a close reading of the spatial preferences that underpin ruin. In the case of bricks, that preference is relatively simple—to fall. By idealizing bricks as rigid bodies, one can understand the effects of gravitational force on each individual brick in a masonry structure. These structures are sometimes able to ‘settle,’ resulting in a stable equilibrium state; in many cases, it means that they will simply collapse. Analyzing ruin in this way is informative, to be sure, but it proves most useful when applied in series. The evolutionary solver described in this paper closely monitors the performance of constituent bricks and ensures that the most successful structures are emulated by later generations. The tool consists of two parts: a user interface for design and the solver itself. Once the architect produces a potential design, the solver performs an evolutionary optimization; after a few hundred iterations, the end result is a structurally sound version of the unstable original. It is hoped that this hybrid of top-down and bottom-up design strategies offers an architecture that is ultimately strengthened by its contingencies.
keywords rigid body analysis, machine learning, multi-agent structural optimization, sensate systems
series ACADIA
type paper
email ph.harrison@mail.utoronto.ca
full text file.pdf (777,837 bytes)
references Content-type: text/plain
details citation check to select
100%; open (2013) Find in CUMINCAD Aggregate Architecture: Simulation Models for Synthetic Non-convex Granulates , Adaptive Architecture: Proceedings of the 33rd Annual Conference of the Association for Computer Aided Design in Architecture, edited by Philip Beesley, Omar Kahn, and Michael Stacey. Cambridge, ON: ACADIA. 301–310.
100%; open Dierichs, Karola, and Achim Menges (2012) Find in CUMINCAD Material and Machine Computation of Designed Granular Matter: Rigid-Body Dynamics Simulations as a Design Tool for Robotically-Poured Aggregate Structures Consisting of Polygonal Concave Particles. , Digital Physicality: Proceedings of the 30th eCAADe Conference, vol. 2, edited by Henri Achten, Jiri Pavlicek, Jaroslav Hulin, and Dana Matejovska. Prague: eCAADe. 711–719
100%; open Dillenburger, Benjamin, Markus Braach, and Ludger Hovestadt (2009) Find in CUMINCAD Building Design as Individual Compromise Between Qualities and Costs: A General Approach for Automated Building Generation Under Permanent Cost and Quality Control , Joining Languages, Cultures, and Visions–Proceedings of the 13th International CAAD Futures Conference, edited by Temy Tifadi and Tomás Dorta. Montreal, QC: CAAD. 458–471
100%; open Grodecki, Louis (1978) Find in CUMINCAD Gothic Architecture , New York: Harry N. Abrams
100%; open Heyman, Jacques (1999) Find in CUMINCAD The Stone Skeleton: Structural Engineering of Masonry Architecture , Cambridge, UK: Cambridge University Press
100%; open King, Ross (2000) Find in CUMINCAD Brunelleschi’s Dome: The Story of the Great Cathedral in Florence , London: Chatto & Windus
100%; open Meredith, Michael, and Hilary Sample (2013) Find in CUMINCAD Everything All at Once: The Software, Videos and Architecture of MOS , New York: Princeton Architectural Press
100%; open Raymond, Eric S. (1999) Find in CUMINCAD The Cathedral and the Bazaar: Musings on Linux and Open Source by an Accidental Revolutionary , Sebastopol, CA: O’Reilly Media
100%; open Rippmann, Matthias, Lorenz Lachauer, and Phillipe Block (2012) Find in CUMINCAD Interactive Vault Design , International Journal of Space Structures 27 (4): 219–230
100%; open Rosenman, M. A. (1996) Find in CUMINCAD The Generation of Form Using an Evolutionary Approach , Artificial Intelligence in Design ‘96, edited by John S. Gero and Fay Sudweeks. Boston, MA: Kluwer Academic Publishers. 643–662
100%; open von Buelow, Peter (2002) Find in CUMINCAD Using Evolutionary Algorithms to Aid Designers of Architectural Structures , Creative Evolutionary Systems, edited by Peter J. Bentley and David W. Corne. San Francisco, CA: Morgan Kaufmann. 315–336.
100%; open Wolfram, Steven (2002) Find in CUMINCAD New Kind of Science , Champaign, IL: Wolfram Media

last changed 2016/10/24 11:12
HOMELOGIN (you are user _anon_37257 from group guest) Works Powered by SciX Open Publishing Services 1.002