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 20 of 1728

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

_id	ijac202018304
id	ijac202018304
authors	Aagaard, Anders Kruse and Niels Martin Larsen
year	2020
title	Developing a fabrication workflow for irregular sawlogs
source	International Journal of Architectural Computing vol. 18 - no. 3, 270-283
summary	In this article, we suggest using contemporary manufacturing technologies to integrate material properties with architectural design tools, revealing new possibilities for the use of wood in architecture. Through an investigative approach, material capacities and fabrication methods are explored and combined towards establishing new workflows and architectural expressions, where material, fabrication and result are closely interlinked. The experimentation revolves around discarded, crooked oak logs, doomed to be used as firewood due to their irregularity. This project treats their diverging shapes differently by offering unique processing to each log informed by its particularities. We suggest here a way to use the natural forms and properties of sawlogs to generate new structures and spatial conditions. In this article, we discuss the scope of this approach and provide an example of a workflow for handling the discrete shapes of natural sawlogs in a system that involve the collection of material, scanning/digitisation, handling of a stockpile, computer analysis, design and robotic manufacturing. The creation of this specific method comes from a combination of investigation of wood as a material, review of existing research in the field, studies of the production lines in the current wood industry and experimentation through our in-house laboratory facilities. As such, the workflow features several solutions for handling the complex and different shapes and data of natural wood logs in a highly digitised machining and fabrication environment. This up-cycling of discarded wood supply establishes a non-standard workflow that utilises non-standard material stock and leads to a critical articulation of today’s linear material economy. The project becomes part of an ambition to reach sustainable development goals and technological innovation in global and resource-intensive architecture and building industry.
keywords	Natural wood, robotic fabrication, computation, fabrication, research by design
series	journal
email
last changed	2020/11/02 13:34

_id	caadria2020_443
id	caadria2020_443
authors	Abuzuraiq, Ahmed M. and Erhan, Halil
year	2020
title	The Many Faces of Similarity - A Visual Analytics Approach for Design Space Simplification
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 1, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 485-494
doi	https://doi.org/10.52842/conf.caadria.2020.1.485
summary	Generative design methods may involve a complex design space with an overwhelming number of alternatives with their form and design performance data. Existing research addresses this complexity by introducing various techniques for simplification through clustering and dimensionality reduction. In this study, we further analyze the relevant literature on design space simplification and exploration to identify their potentials and gaps. We find that the potentials include: alleviating the choice overload problem, opening up new venues for interrelating design forms and data, creating visual overviews of the design space and introducing ways of creating form-driven queries. Building on that, we present the first prototype of a design analytics dashboard that combines coordinated and interactive visualizations of design forms and performance data along with the result of simplifying the design space through hierarchical clustering.
keywords	Visual Analytics; Design Exploration; Dimensionality Reduction; Clustering; Similarity-based Exploration
series	CAADRIA
email
last changed	2022/06/07 07:54

_id	ecaade2020_064
id	ecaade2020_064
authors	Agirbas, Asli
year	2020
title	Building Energy Performance of Complex Forms - Test simulation of minimal surface-based form optimization
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 1, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 259-268
doi	https://doi.org/10.52842/conf.ecaade.2020.1.259
summary	Many optimization tools are developed in line with the form-energy relationship to ensure energy efficiency in buildings. However, such studies with complex forms are very limited. Therefore, the MSO-2 model was developed. In this model, on the roof of the conceptual form, minimal surface is used, thus complex forms can be created. In this model, the conceptual form can be optimized (for one day) according to these objectives: increasing daylight in the space with maximum value limitation, reducing radiation on the roof, and enlarging floor surface area of the conceptual form with minimum value limitation. A test simulation was performed with this model. Thus, in order to find the most optimized form in multi-objective optimization, more generations could be produced in a short time and optimized conceptual forms, which were produced, could be tested for energy efficiency.
keywords	Multi-Objective Optimization; Radiation Analysis; Building energy performance; Daylighting Analysis
series	eCAADe
email
last changed	2022/06/07 07:54

_id	sigradi2020_217
id	sigradi2020_217
authors	Arbeláez-Ochoa, Elsie; Torreblanca-Díaz, David A.; Rodríguez-Castrillon, Karen; Munoz-Noriega, Daniela
year	2020
title	Methodology for the abstraction and morphological experimentation of nature’s patterns: an application case of morphology research subject in Industrial Design program
source	SIGraDi 2020 [Proceedings of the 24th Conference of the Iberoamerican Society of Digital Graphics - ISSN: 2318-6968] Online Conference 18 - 20 November 2020, pp. 217-222
summary	Forms in nature have been emerging in response to different requirements, in a complex and dynamic ecosystem. Architects and designers have usually used references from nature for their projects; in industrial design education, the use of nature’s referents allows to expand the morphological possibilities for product design and systems. In this paper, a methodological proposal for the abstraction and morphological transformation of nature’s patterns is presented, highlighting the advantages of parametric design and additive manufacturing technologies for morphological experimentation, in the context of the first application case of morphology research subject in the Industrial Design program at Universidad Pontificia Bolivariana.
keywords	Bio-inspired design, Morphology, Experimental morphology, Additive manufacturing technologies, Industrial design education
series	SIGraDi
email
last changed	2021/07/16 11:48

_id	sigradi2020_60
id	sigradi2020_60
authors	Asmar, Karen El; Sareen, Harpreet
year	2020
title	Machinic Interpolations: A GAN Pipeline for Integrating Lateral Thinking in Computational Tools of Architecture
source	SIGraDi 2020 [Proceedings of the 24th Conference of the Iberoamerican Society of Digital Graphics - ISSN: 2318-6968] Online Conference 18 - 20 November 2020, pp. 60-66
summary	In this paper, we discuss a new tool pipeline that aims to re-integrate lateral thinking strategies in computational tools of architecture. We present a 4-step AI-driven pipeline, based on Generative Adversarial Networks (GANs), that draws from the ability to access the latent space of a machine and use this space as a digital design environment. We demonstrate examples of navigating in this space using vector arithmetic and interpolations as a method to generate a series of images that are then translated to 3D voxel structures. Through a gallery of forms, we show how this series of techniques could result in unexpected spaces and outputs beyond what could be produced by human capability alone.
keywords	Latent space, GANs, Lateral thinking, Computational tools, Artificial intelligence
series	SIGraDi
email
last changed	2021/07/16 11:48

_id	acadia20_526
id	acadia20_526
authors	Bruce, Mackenzie; Clune, Gabrielle; Culligan, Ryan; Vansice, Kyle; Attraya, Rahul; McGee, Wes; Yan Ng, Tsz
year	2020
title	FORM{less}
source	ACADIA 2020: Distributed Proximities / Volume I: Technical Papers [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95213-0]. Online and Global. 24-30 October 2020. edited by B. Slocum, V. Ago, S. Doyle, A. Marcus, M. Yablonina, and M. del Campo. 526-535
doi	https://doi.org/10.52842/conf.acadia.2020.1.526
summary	Form{less} focuses on the creation of complex thin-shell concrete forms using robotically thermoformed plastic molds. Typically, similar molds would be created using the vacuum forming process, producing direct replications of the pattern. Creating molds with this process is not only time- and material-intensive but also costly if customization is involved. Thin-shell concrete forms often require a labor-intensive process of manually finishing the open-face surface. The devised process of thermoforming two nested molds allows the concrete to be cast in between, with finished surfaces on both sides. Molds made with polyethylene terephthalate glycol (PETG) allow the formwork to be reused and recycled. The research and fabrication work include the development of heating elements and the creation of the robotic process for forming the PETG. The PETG is manipulated via a robotic arm, with a custom magnetic end effector. The integration of robotics not only enables precision for manufacturing but also allows for replicability with unrestricted threedimensional deformation. The repeatable process allows for rapid prototyping and geometric customization. Design options are then simulated computationally using SuperMatterTools, enabling further design exploration of this process without the need for extensive physical prototyping. This research aims to develop a process that allows for the creation of complex geometries while reducing the amount of material waste used for concrete casting. The novelty of the process created by dynamically forming PETG allows for quick production of formwork that is both customizable and replicable. This method of creating double-sided building components is simulated at various scales of implementation.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ecaade2020_253
id	ecaade2020_253
authors	Buš, Peter
year	2020
title	User-driven Configurable Architectural Assemblies - Towards artificial intelligence-embedded responsive environments
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 2, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 483-490
doi	https://doi.org/10.52842/conf.ecaade.2020.2.483
summary	The paper theoretically elaborates the idea of individual users' customisation activities to create and configure responsive spatial scenarios by means of reconfigurable interactive adaptive assemblies. It reflects Gordon Pask's concept of human and device interaction based on its unpredictable notion speculating a potential to be enhanced by artificial intelligence learning approach of an assembly linked with human activator's participative inputs. Such a link of artificial intelligence, human agency and interactive assembly capable to generate its own spatial configurations by itself and users' stimuli may lead to a new understanding of humans' role in the creation of spatial scenarios. The occupants take the prime role in the evolution of spatial conditions in this respect. The paper aims to position an interaction between the human agents and artificial devices as a participatory and responsive design act to facilitate creative potential of participants as unique individuals without pre-specified or pre-programmed goal set by the designer. Such an approach will pave a way towards true autonomy of responsive built environments, determined by an individual human agent and behaviour of the spatial assemblies to create authentic responsive built forms in a digital and physical space.
keywords	deployable systems; responsive assemblies; embedded intelligence; Learning-to-Design-and-Assembly method; Conversation Theory
series	eCAADe
email
last changed	2022/06/07 07:54

_id	sigradi2020_180
id	sigradi2020_180
authors	Cavalcanti, Isabella Eloy; Mendes, Leticia Teixeira
year	2020
title	Form and urban life in Christopher Alexander's work: translation of patterns for parametric code
source	SIGraDi 2020 [Proceedings of the 24th Conference of the Iberoamerican Society of Digital Graphics - ISSN: 2318-6968] Online Conference 18 - 20 November 2020, pp. 180-187
summary	Computational design, specifically parametric modeling, has played important role in reaching complex forms, optimizations and automations of design processes. In addition to using parametric technology as a tool to generate form, this article aims to discuss the potential of parametric design as a connection between theory and design activity, both in practice and in the teaching activity. To illustrate that, this paper will present results of a bigger research that used the work of the architect Christopher Alexander as a basis for the development of decision-making instruments that deal with the complexity between form and urban life.
keywords	Urban design, Parametric modeling, Computational design, Christopher Alexander
series	SIGraDi
email
last changed	2021/07/16 11:48

_id	ecaade2020_261
id	ecaade2020_261
authors	Dimopoulos, Georgios, Kontaxakis, Dimitris, Symeonidou, Ioanna and Tsinikas, Nikos
year	2020
title	From Analog to Digital: Double Curved Lightweight Structures in Architectural Design Education
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 2, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 181-188
doi	https://doi.org/10.52842/conf.ecaade.2020.2.181
summary	The paper describes an architectural design studio for 5th year students at the Department of Architecture of the Aristotle University in Thessaloniki, Greece. The educational objective of the studio is the design of double curved lightweight structures, employing a creative methodology which instrumentalizes the study of nature as a source of inspiration. The objective of the course is to familiarize the students with curves and form-finding (analogue and digital) with the aim to design forms that display structural stability. The paper will highlight the educational gains from a hybrid design methodology which employs both analog (physical) form-finding tools and digital modeling for the design of double curvature surfaces.
keywords	Lightweight structures; Form-finding; Dynamic models; Tensile structures; Architecture education
series	eCAADe
email
last changed	2022/06/07 07:55

_id	artificial_intellicence2019_147
id	artificial_intellicence2019_147
authors	Ding Wen Bao, Xin Yan, Roland Snooks, and Yi Min Xie
year	2020
title	Bioinspired Generative Architectural Design Form-Finding and Advanced Robotic Fabrication Based on Structural Performance
source	Architectural Intelligence Selected Papers from the 1st International Conference on Computational Design and Robotic Fabrication (CDRF 2024)
doi	https://doi.org/https://doi.org/10.1007/978-981-15-6568-7_10
summary	Due to the potential to generate forms with high efficiency and elegant geometry, topology optimization is widely used in architectural and structural designs. This paper presents a working flow of form-finding and robotic fabrication based BESO (Bi-directional Evolutionary Structure Optimization) optimization method. In case there are some other functional requirements or condition limitations, some useful modifications are also implemented in the process. With this kind of working flow, it is convenient to foreknow or control the structural optimization direction before the optimization process. Furthermore, some fabrication details of the optimized model will be discussed because there are also many notable technical points between computational optimization and robotic fabrication.
series	Architectural Intelligence
email
last changed	2022/09/29 07:28

_id	caadria2020_132
id	caadria2020_132
authors	DÄ…browska-Å»Ã³Å‚tak, Karolina, Wojtowicz, Jerzy and Wrona, Stefan
year	2020
title	Robotown
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 2, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 413-422
doi	https://doi.org/10.52842/conf.caadria.2020.2.413
summary	The potential robotization of architecture, its fabrication and assembly impacts design education today. In the near future it will contribute to the emergence of the new forms of urbanization. Our design research is focusing on the small scale urban conditions and build fragments that make up intelligent city. It is undertaken by the multidisciplinary team of architects and mechatronics engineers in academic context. The ROBOtown is understood as an urban structure containing intelligent town fragments. It has to consider the participatory design process involving architecture, mechatronic, robotics and lessons derived from Industry 4.0.
keywords	Design; Internet of Things; Architectronics; Mechatronics; Robotics
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	acadia20_594
id	acadia20_594
authors	Farahbakhsh, Mehdi; Kalantar, Negar; Rybkowski, Zofia
year	2020
title	Impact of Robotic 3D Printing Process Parameters on Bond Strength
source	ACADIA 2020: Distributed Proximities / Volume I: Technical Papers [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95213-0]. Online and Global. 24-30 October 2020. edited by B. Slocum, V. Ago, S. Doyle, A. Marcus, M. Yablonina, and M. del Campo. 594-603.
doi	https://doi.org/10.52842/conf.acadia.2020.1.594
summary	Additive manufacturing (AM), also known as 3D printing, offers advantages over traditional construction technologies, increasing material efficiency, fabrication precision, and speed. However, many AM projects in academia and industrial institutions do not comply with building codes. Consequently, they are not considered safe structures for public utilization and have languished as exhibition prototypes. While three discrete scales—micro, mezzo, and macro—are investigated for AM with paste in this paper, structural integrity has been tackled on the mezzo scale to investigate the impact of process parameters on the bond strength between layers in an AM process. Real-world material deposition in a robotic-assisted AM process is subject to environmental factors such as temperature, humidity, the load of upper layers, the pressure of the nozzle on printed layers, etc. Those factors add a secondary geometric characteristic to the printed objects that was missing in the initial digital model. This paper introduces a heuristic workflow for investigating the impacts of three selective process parameters on the bond strength between layers of paste in the robotic-assisted AM of large-scale structures. The workflow includes a method for adding the secondary geometrical characteristic to the initial 3D model by employing X-ray computerized tomography (CT) scanning, digital image processing, and 3D reconstruction. Ultimately, the proposed workflow offers a pattern library that can be used by an architect or artificial intelligence (AI) algorithms in automated AM processes to create robust architectural forms.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	sigradi2020_9
id	sigradi2020_9
authors	Felipe, Bárbara L.; Nome, Carlos
year	2020
title	Digital Fabrication Techniques: A systematic literature review
source	SIGraDi 2020 [Proceedings of the 24th Conference of the Iberoamerican Society of Digital Graphics - ISSN: 2318-6968] Online Conference 18 - 20 November 2020, pp. 9-16
summary	The materialization of architectural forms uses new processes aided by digital manufacturing techniques (FD). Five FD techniques stand out: sectioning (serial planes), tessellation, folding, contouring, and forming. This article's objective is to characterize the state of the art of these techniques, from 2009 to 2020 in national and international research bases. The Systematic Literature Review is used from three stages and nine protocol phases. The results indicate the techniques, methods, computer simulations, and applicability in more recurrent materials.
keywords	Digital Fabrication techniques, Digital Fabrication, Algorithmic Architecture; Parametric Design.
series	SIGraDi
email
last changed	2021/07/16 11:48

_id	caadria2020_315
id	caadria2020_315
authors	Feng, Shiyu, Du, Mengzeshan, Wang, Weiyi, Lu, Heng, Park, Daekwon and Ji, Guohua
year	2020
title	3D Printed Monolithic Joints - A Mechanically Bistable Joint
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 1, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 173-182
doi	https://doi.org/10.52842/conf.caadria.2020.1.173
summary	This paper describes the design and fabrication process of an adaptive joint using 3D printed mono-material bistable mechanisms. The proposed joint deforms when external forces are applied, achieving two stable states. An x-shaped microstructure (simul-SLE) is designed for the connection portion of the bistable structure inside the joint. 3D-Printing experiments is conducted to explore the possibility of various forms of simul-SLE, which realize bistable by a single material. The experiment primarily solved two problems, namely the selection of materials and how to make the rigid 3D printed material acquires properties of flexibility and softness. Finally, practical applications are shown to prove the future of this joint.
keywords	3D printing; adaptive joint; mechanically-bistable joint
series	CAADRIA
email
last changed	2022/06/07 07:50

_id	caadria2020_361
id	caadria2020_361
authors	Geht, Alexander, Weizmann, Michael, Grobman, Yasha Jacob and Tarazi, Ezri
year	2020
title	Horizontal Forming in Additive Manufacturing: Design and Architecture Perspective
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 1, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 203-212
doi	https://doi.org/10.52842/conf.caadria.2020.1.203
summary	Extrusion based three-dimensional additive manufacturing technology forms objects by driving the material through a nozzle depositing a linear structure through vector-building blocks called roads. In a common 3-axis system, the roads are stacked layer upon layer for forming the final object. However, forming overhanging geometry in this way requires additional support structures increasing material usage and effective printing time. The paper presents a novel Horizontal forming (HF) approach and method for forming overhanging geometry, HF is a new extrusion-based AM approach that allows rapid and stable forming of horizontal structures without additional support in 3-axis systems. This approach can provide new design and manufacturing possibilities for extrusion AM, with emphasis on medium and large-scale AM. HF can affect the outcome's aesthetic and mechanical properties. Moreover, it can significantly accelerate the production process and reduce material waste. The present paper maps the influence of various parameters employed in the HF method, providing a deeper understanding of the printing process. Additionally, it explores and demonstrates the potential functional and aesthetic characteristics that can be achieved with HF for industrial design and architectural products.
keywords	Additive manufacturing; Support; Horizontal forming (HF); Extrusion-based system; Fused granulate forming (FGF)
series	CAADRIA
email
last changed	2022/06/07 07:51

_id	ecaade2020_408
id	ecaade2020_408
authors	Grasser, Alexander, Parger, Alexandra and Hirschberg, Urs
year	2020
title	Pervasive Collaboration and Tangible Complexity in Realtime Architecture
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 1, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 393-400
doi	https://doi.org/10.52842/conf.ecaade.2020.1.393
summary	This paper reports on an ongoing experiment in design collaboration: an open collaborative realtime environment that enables participatory design activities in spatially distributed teams. The project builds on online platforms and open source ways of sharing design ideas, but also on recent advances in shared augmented reality enabled by game engine technology. Furthermore it focuses on combinatorial design of collaborative objects: the models shared in this way are not just geometric forms, but informed systems of parts with a procedural or combinatorial logic, an assembly strategy. By pooling and aggregating such intelligent assembly systems in a shared online realtime design space we are trying to move towards pervasive collaboration in architecture. Authors taking part in the project are united in a shared persistent design space and can design collectively. They experience what we refer to as tangible complexity: a playful mode of aggregating and combining design ideas of different authors. We argue that this pervasive collaboration can lead to novel types of complexity: an architecture of socially augmented formations.
keywords	Collaborative Objects; Realtime Architecture; Tangible Complexity
series	eCAADe
email
last changed	2022/06/07 07:51

_id	cdrf2019_297
id	cdrf2019_297
authors	H. Mohamed, D. W. Bao, and R. Snooks
year	2020
title	Super Composite: Carbon Fibre Infused 3D Printed Tectonics
source	Proceedings of the 2020 DigitalFUTURES The 2nd International Conference on Computational Design and Robotic Fabrication (CDRF 2020)
doi	https://doi.org/https://doi.org/10.1007/978-981-33-4400-6_28
summary	This research posits an innovative process of embedding carbon fibre as the primary structure within large-scale polymer 3D printed intricate architectural forms. The design and technical implications of this research are explored and demonstrated through two proto-architectural projects, Cloud Affects and Unclear Cloud, developed by the RMIT Architecture Snooks Research Lab. These projects are designed through a tectonic approach that we describe as a super composite – an approach that creates a compression of tectonics through algorithmic selforganisation and advanced manufacturing. Framed within a critical view of the lineage of polymer 3D printing and high tech fibres in the field of architectural design, the research outlines the limitations of existing robotic processes employed in contemporary carbon fibre fabrication. In response, the paper proposes an approach we describe asInfused Fibre Reinforced Plastic (IFRP) as a novel fabrication method for intricate geometries. This method involves 3D printing of sacrificial formwork conduits within the skin of complex architectural forms that are infused with continuous carbon fibre structural elements. Through detailed observation and critical review of Cloud Affects and Unclear Cloud (Fig. 2), the paper assesses innovations and challenges of this research in areas including printing, detailing, structural analysis and FEA modelling. The paper notes how these techniques have been refined through the iterative design of the two projects, including the development of fibre distribution mapping to optimise the structural performance.
series	cdrf
email
last changed	2022/09/29 07:51

_id	cdrf2019_159
id	cdrf2019_159
authors	Hang Zhang and Ye Huang
year	2020
title	Machine Learning Aided 2D-3D Architectural Form Finding at High Resolution
source	Proceedings of the 2020 DigitalFUTURES The 2nd International Conference on Computational Design and Robotic Fabrication (CDRF 2020)
doi	https://doi.org/https://doi.org/10.1007/978-981-33-4400-6_15
summary	In the past few years, more architects and engineers start thinking about the application of machine learning algorithms in the architectural design field such as building facades generation or floor plans generation, etc. However, due to the relatively slow development of 3D machine learning algorithms, 3D architecture form exploration through machine learning is still a difficult issue for architects. As a result, most of these applications are confined to the level of 2D. Based on the state-of-the-art 2D image generation algorithm, also the method of spatial sequence rules, this article proposes a brand-new strategy of encoding, decoding, and form generation between 2D drawings and 3D models, which we name 2D-3D Form Encoding WorkFlow. This method could provide some innovative design possibilities that generate the latent 3D forms between several different architectural styles. Benefited from the 2D network advantages and the image amplification network nested outside the benchmark network, we have significantly expanded the resolution of training results when compared with the existing form-finding algorithm and related achievements in recent years
series	cdrf
email
last changed	2022/09/29 07:51

_id	artificial_intellicence2019_207
id	artificial_intellicence2019_207
authors	Hao Zheng
year	2020
title	Form Finding and Evaluating Through Machine Learning: The Prediction of Personal Design Preference in Polyhedral Structures
source	Architectural Intelligence Selected Papers from the 1st International Conference on Computational Design and Robotic Fabrication (CDRF 2025)
doi	https://doi.org/https://doi.org/10.1007/978-981-15-6568-7_13
summary	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.
series	Architectural Intelligence
email
last changed	2022/09/29 07:28

_id	caadria2020_369
id	caadria2020_369
authors	Heckmann, Oliver, Budig, Michael, Xuereb Conti, Zack, Cheng, Ray Chern Xi and Lo Tian Tian, Sky
year	2020
title	User-driven Parcellation of High-rise Units for Future Urban Habitation - Participatory Computational Design Tools for Future Urban Habitation
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 1, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 751-760
doi	https://doi.org/10.52842/conf.caadria.2020.1.751
summary	Most residential high-rise apartments currently built to satisfy growing demands for housing, are predetermined and thus, are unable to respond to the increasingly diversifying forms of co-habitation. This research pursues alternative flexible approaches by building on Habraken's 'Open Building' paradigm, where permanent, polyvalent 'Support System' layouts are strategically designed to accommodate highly adaptable, user-driven 'Infill systems'. In this context, we adopt the participatory decision-making approach, by means of a computational framework that facilitates user-driven parcellations of entire buildings into apartments segments. The means is an algorithm that allocates numerous user-preference regarding size and position simultaneously - by searching for parcel permutations through a graph-syntax representation of floor plans. The research forms part of a larger project that aims to evaluate the resilience of mass housing for future uncertain demands.
keywords	participatory; generative; mass housing; open building
series	CAADRIA
email
last changed	2022/06/07 07:49

For more results click below: