Cumincad : CUMINCAD Papers : Search Results

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
References

Hits 1 to 3 of 3

Reformat results as: short short into frame detailed detailed into frame

_id	caadria2019_126
id	caadria2019_126
authors	Ng, Jennifer Mei Yee, Khean, Nariddh, Madden, David, Fabbri, Alessandra, Gardner, Nicole, Haeusler, M. Hank and Zavoleas, Yannis
year	2019
title	Optimising Image Classification - Implementation of Convolutional Neural Network Algorithms to Distinguish Between Plans and Sections within the Architectural, Engineering and Construction (AEC) Industry
doi	https://doi.org/10.52842/conf.caadria.2019.2.795
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 795-804
summary	Modern communication between built environment professionals are governed by the effective exchange of digital models, blueprints and technical drawings. However, the increasing quantity of such digital files, in conjunction with inconsistent filing systems, increases the potential for human-error upon their look-up and retrieval. Further, current methods are manual, thus slow and resource intensive. Evidently, the architectural, engineering and construction (AEC) industry lacks an automated classification system capable of systematically identifying and categorising different drawings. To intercede, we aim to investigate artificially intelligent solutions capable of automatically identifying and retrieving a wide set of AEC files from a company's resource library. We present a convolutional neural network (CNN) model capable of processing large sets of technical drawings - such as sections, plans and elevations - and recognise their individual patterns and features, ultimately minimising laboriousness.
keywords	Convolutional Neural Network; Artificial Intelligence; Machine Learning; Classification; Filing architectural drawings.
series	CAADRIA
email
last changed	2022/06/07 07:58

_id	caadria2019_173
id	caadria2019_173
authors	Ng, Jonathan Ming-En, Ho, Samuel Yu De, Ng, Truman Wei Cheng, Soh, Jia Ying and Dritsas, Stylianos
year	2019
title	Fabrication of Ultra-Lightweight Parametric Glass Fiber Reinforced Shell Assemblies
doi	https://doi.org/10.52842/conf.caadria.2019.1.013
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 1, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 13-22
summary	We present an experimental form-finding technique for ultra-thin glass fiber reinforced concrete components and assemblies. The objective is to challenge conventional concrete use in construction, often perceived as a massive and compressive structural material. Instead, we targeted production of fine shell assemblies principally operating in tension. To achieve thin profile components, we use a compliant molding technique where premixed GFRC is cast in polyethylene bags. Subsequently, a robotic arm system pins the bags on a substrate plate and the setup is inverted whereby gravity induces a curvature to components while concrete cures. Use of parametric modeling, computer simulation and statistical experimental methods allowed us to understand the behavior of the material process and translate computationally modeled designs into physical artifacts. We discuss the opportunity for digital fabrication methods to fuse with traditional form-finding techniques, contrast the use of computational modeling techniques and present a series of prototypes created through our process.
keywords	Digital Fabrication; Glass Fibre Reinforced Concrete; Form-Finding
series	CAADRIA
email
last changed	2022/06/07 07:58

_id	ecaadesigradi2019_024
id	ecaadesigradi2019_024
authors	Wit, Andrew John and Ng, Rashida
year	2019
title	cloudMAGNET - A prototype for climatically active light-weight skins
doi	https://doi.org/10.52842/conf.ecaade.2019.2.627
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 627-636
summary	This paper describes a potential for the integration of micro-encapsulated phase change material (mircoPCM) into lightweight skins as a means of regulating internal climatic conditions of volumetric objects. Viewed through the lens of the recently completed series of quarter-scale cloudMAGNET prototypes tested in the cloud forests of Monteverde, Costa Rica, this research utilized a wound, flexible carbon fiber framework and a lightweight fabric skin coated with varying densities of microPCM. The prototypes were monitored using real-time collection of climate data throughout the testing. In this paper we will demonstrate how climatic variables such as temperature, humidity, and pressure can be passively manipulated by varying the form and energy storage properties of materials without the use of active mechanical systems. Produced to bring awareness to the rising cloud levels within the Monteverde cloud forest, this research is intended to explore the fundamental relationships of material, energy and form. Beyond these objectives, the paper will also illustrate how these methods can be more broadly applied to the development of thermal-regulating lightweight tensile structures. Such innovations could be utilized as a method for the reimagining the architectural design and production processes allowing for the emergence of new typologies of environmentally self-mediating architecture.
keywords	material performance; phase change material; carbon fiber reinforced polymers; computation
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:57

No more hits.