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

PDF papers

Hits 1 to 5 of 5

_id caadria2016_383
id caadria2016_383
authors Beorkrem, C.; J. Ellinger, P. Bernstein and A. Hauck
year 2016
title Multivariate Schematic Design Tooling
source Living Systems and Micro-Utopias: Towards Continuous Designing, Proceedings of the 21st International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2016) / Melbourne 30 March–2 April 2016, pp. 383-394
summary This paper will examine the results from a research collaboration between (BIM Software Manufacturer) and (School), whose problem statement focused on supporting robust interoperability by defining goals focused on multivariate conceptual design tools. The collaboration included design faculty, students and software professionals, the latter providing access to a broad range of design simulation tools either commercially available or currently in development. The tools were developed first through case studies and background research, followed by the design and implementation of novel computational methods advancing the architectural design workflow by seeking to create comparative tools which allow a designer to connect multiple data typologies in a single model. With advanced computational tools employed both as standalone resources and embedded in parametric loops, we sought to provide immediate feedback on design goals.
keywords Building information modelling; simulation and prediction; education; optimization; scripting
series CAADRIA
last changed 2016/03/11 09:21

_id acadia12_109
id acadia12_109
authors Comodromos, Demetrios A ; Ellinger, Jefferson
year 2012
title Material Intensities
source ACADIA 12: Synthetic Digital Ecologies [Proceedings of the 32nd Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-1-62407-267-3] San Francisco 18-21 October, 2012), pp. 109-113
summary As host organizers of the Smartgeometry 2012 Conference, professors of Architecture, and as principals in design firms, our work aims to use as a productive resistance the notion of Material Intensity described below as both a foil and measure to current concepts of simulation and intensive modeling in architectural computation. The holding of SG 2012 aimed to stage this resistance in the form of workshop, round-table discussions, lectures and symposia, with the outcome attempting to define a new synthetic notion of material intensities in modes of architectural production. This paper aims to form the basis of a continued exploration and development of this work. In summary we focused on: 1-Intensive thinking as derived from the material sciences as an actual and philosophical framework that emphasizes qualitative attributes, which is likened to behavior, simulation, and dynamic modeling. Extensive attributes lead to analytical, representational and static modeling. 2-Material practices can also be formed and as a result of this method of thinking. As demonstrated by the glasswork of Evan Douglis, ‘paintings’ by Perry Hall—the managed complexity possible by working with materials during intensive states of change allow for scalar, morphological and performative shifts according to a designer’s criteria. 3- Although both are necessary and actually complement each other, architects need to ‘catch-up’ to intensive thinking in process and modeling strategies. Our methods rely on static modeling that yield often complicated frameworks and results, wherein accepting methods of dynamic modeling suggests the capacity to propose complex and nuanced relationships and frameworks.
keywords Material Intensities , Intensive Thinking , Material Practice
series ACADIA
type panel paper
last changed 2013/01/09 10:06

_id acadia19_370
id acadia19_370
authors Mohammad, Ali; Beorkrem, Christopher; Ellinger, Jefferson
year 2019
title Hybrid Elevations using GAN Networks
source ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 370-379
summary This project is an attempt to develop and test a method for generating one-sided hybrid exterior building elevations using designer’s base criteria and design rule sets as inputs in an advanced artificial intelligence network. Architects are using computational design to expedite the iteration process in an efficient manner. Optimization techniques utilizing genetic solvers allow designers to explore broad sets of iterations within a predefined subset. However, with the application of artificial intelligence networks these fields of exploration can be expanded upon to develop ranges of exploration which can explore iterations outside of typical ranges. This paper explores the use of Generative Adversarial Networks (GAN) to explore and demonstrate their possible capabilities to typical design problems. In this instance we are exploring their application in the development of architectural elevations.
series ACADIA
type normal paper
last changed 2019/12/18 08:03

_id acadia17_552
id acadia17_552
authors Sjoberg, Christian; Beorkrem, Christopher; Ellinger, Jefferson
year 2017
title Emergent Syntax: Machine Learning for the Curation of Design Solution Space
source ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 552- 561
summary The expanding role of computational models in the process of design is producing exponential growth in parameter spaces. As designers, we must create and implement new methods for searching these parameter spaces, considering not only quantitative optimization metrics but also qualitative features. This paper proposes a methodology that leverages the pattern modeling properties of artificial neural networks to capture designers' inexplicit selection criteria and create user-selection-based fitness functions for a genetic solver. Through emulation of learned selection patterns, fitness functions based on trained networks provide a method for qualitative evaluation of designs in the context of a given population. The application of genetic solvers for the generation of new populations based on the trained network selections creates emergent high-density clusters in the parameter space, allowing for the identification of solutions that satisfy the designer’s inexplicit criteria. The results of an initial user study show that even with small numbers of training objects, a search tool with this configuration can begin to emulate the design criteria of the user who trained it.
keywords design methods; information processing; AI; machine learning; generative system
series ACADIA
last changed 2017/10/17 09:13

_id acadia17_610
id acadia17_610
authors Thariyan, Elizabeth; Beorkrem, Christopher; Ellinger, Jefferson
year 2017
title Buildable Performance Envelopes: Optimizing Sustainable Design in a Pre-Design Phase
source ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 610- 619
summary The growing consciousness regarding ecologically conscious architecture mandates a deeper understanding of the strategies that may be adopted by designers towards achieving this goal. With the advent of building information modelling (BIM) and the associated paradigm shift in the design process, it has become increasingly possible to make informed decisions earlier on in the design process. Despite this advancement, the architectural realm continues to lack computational resources that are capable of providing formal guidelines, through a generative process, that serve as a starting point for sustainable design. Towards overcoming this limitation, this paper will describe a computational tool that generates buildable performance envelopes in response to aspects of a site that are influential in designing sustainably: climate and context. These envelopes are created in a generative manner through the utilization of a voxel (three-dimensional pixel) matrix, which continually updates itself based on formal elements created by the user. Facilitating the process of making ecologically conscious design decisions at the earliest stages of design, which is the primary goal of this tool, more substantially increases the achieved energy optimization. Illustrative building designs presented in the paper resulting from the testing of this tool in contrasting climate zones, such as Miami, Florida (ASHRAE Zone 01) and Aspen, Colorado (ASHRAE Zone 07), confirms the assertion that the performance envelopes generated with this tool serve only as a guideline for optimized sustainable design, and not as the final form of the building itself.
keywords design methods; information processing; BIM; simulation & optimization; form finding
series ACADIA
last changed 2017/10/17 09:13

No more hits.

HOMELOGIN (you are user _anon_456675 from group guest) CUMINCAD Papers Powered by SciX Open Publishing Services 1.002