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 13 of 13

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

_id	caadria2023_100
id	caadria2023_100
authors	Liu, Yuxuan and Xu, Wenzhao
year	2023
title	A Data-Driven Approach for Interpreting Human Preference in Urban Public Spaces: A Case Study in London
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 625–634
doi	https://doi.org/10.52842/conf.caadria.2023.1.625
summary	Sound, an often easily overlooked part of the urban composition, plays a crucial role in urban studies regarding how people perceive urban acoustic environments. Influenced by variable natural and artificial acoustic elements, the multi-level nature of urban soundscapes reflects multidimensional urban characteristics and thus demands thorough investigations. Unravelling the acoustic complexity and understanding its influence on public spaces' popularity will benefit the interpretation of urban soundscapes and help to build a more vibrant public life. In this paper, we utilize DepthMapX and QGIS to select specimen sites for further investigation. The behavioural analysis is performed through principle components analysis (PCA) and K-Means analysis based on data obtained within the city of London. This project seeks to develop digital strategies to investigate the relationship between urban public spaces and their soundscapes: to infer the correlation between people's emotions and the richness of urban environments. Through integrating machine-learning analytic approaches into visualizing how citizens perceive or experience the urban sound environment, our research aims to positively assist and inform urban practitioners in planning and designing more benign acoustic environments.
keywords	Urban Soundscape, Data-driven Analysis, Machine Learning, Multidimensional Data visualization
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	cdrf2023_125
id	cdrf2023_125
authors	Yubo Liu, Zhilan Zhang, Kai Hu, Qiaoming Deng
year	2023
title	Graph Constrained Multiple Schemes Generation for Campus Layout
source	Proceedings of the 2023 DigitalFUTURES The 5st International Conference on Computational Design and Robotic Fabrication (CDRF 2023)
doi	https://doi.org/https://doi.org/10.1007/978-981-99-8405-3_11
summary	The campus layout is a major stage in the early stages of campus planning and design. When assessing the feasibility of a campus site in stage, we usually compare multiple campus layout schemes, which consumes a lot of time. The design process can be accelerated if multiple campus planning schemes can be generated quickly to meet the desired requirements. This study aims to explore the possibility of using graph neural networks (GNN) to generate multiple campus layouts. We use a step-by-step generation method. The first step is generating campus functional zonings based on user constraints. The second step is generating campus building layouts based on the functional zonings. Ultimately the machine is able to quickly generate multiple campus layout schemes by user input of graph constraints such as the number of functional zonings, the type of functions and their adjacency. In the experiment, we trained 200 campus layout samples and verified the validity and accuracy of the experiment after qualitative and quantitative analysis.
series	cdrf
email
last changed	2024/05/29 14:04

_id	ecaade2023_466
id	ecaade2023_466
authors	Liu, Zidong, Li, Han, Koehler, Daniel and Li, Yan
year	2023
title	Predicting Non-functional Nodes of Floorplan via Graph Neural Network (GNN)
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 529–538
doi	https://doi.org/10.52842/conf.ecaade.2023.2.529
summary	This paper presents an innovative approach to automating the floorplan generation process by employing Graph Neural Networks (GNN) to facilitate the transition from functional assignment lists to bubble diagrams and eventually to floorplan graphs. In recent years, there have been many studies on the interconversion of floorplan graph and layout design. However, these studies usually mix up floorplan graph and bubble diagram, despite their distinct roles in representing spatial and functional relationships, respectively. To address this disparity, we introduce a research framework comprising three main steps. First, we generate the CubiBubble5k dataset, which encompasses bubble diagrams and functional lists, drawing on the existing CubiCasa5k and CubiGraph5k datasets. Next, we train a GNN to transform design assignments into structured graph data, utilizing functional lists as input and bubble diagrams as output. Subsequently, we train another GNN that predicts and inserts non-functional spaces, such as corridors and anterooms, into purely functional bubble diagrams, using bubble graphs as input and floorplan graphs as output. We assess the performance of both GNNs and, by integrating our framework with the established graph2plan study, successfully demonstrate the generation of real-world floorplans from project task books. Lastly, we conduct case studies to validate the feasibility of our proposed framework. We use the existing graph2plan platform to visualize the impact of our algorithm on the final layout.
keywords	Floorplan Automation, Bubble Diagram, Graph Restructure, Graph Neural Network
series	eCAADe
email
last changed	2023/12/10 10:49

_id	caadria2023_141
id	caadria2023_141
authors	Zhu, Guanqi, Zhou, Xinyi, Zhang, Jun, Liu, Guogang, Hao, Shimeng and Luo, Dan
year	2023
title	Automatic Robotic Construction for Customisable Rammed Earth Walls
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 109–118
doi	https://doi.org/10.52842/conf.caadria.2023.2.109
summary	Rammed earth construction has long been operated as a manual process involving unsaturated loose soil compacted inside a formwork. Earth soil is a type of highly sustainable naturalistic raw material decomposable with minimum environmental impact, with diverse colour and properties along by default. In addition, the high thermal resistance and moisture-absorbing quality of rammed earth walls significantly benefit the passive environmental comfort of the established environment. However, the manual process of rammed earth construction is excessively time and labour-intensive and highly dependent on skilled workers. More importantly, the visual effects on the vertical surface have long been overlooked by designers and builders, which has the potential to fulfil the aesthetic variety of facades. However, distributing the earth material with various colours to the specific position hinges upon the advanced fabrication accuracy and skilled workers. This process is similar to working in a black box, where it is hard to evaluate and detect the fabrication situation. Therefore, to tap into the potential of rammed earth construction, this research aims to develop an automatic robotic system capable of constructing rammed walls with a customisable distribution of different soil layers precisely.
keywords	robotic fabrication, rammed earth construction, automatic construction, material research
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	acadia23_v1_166
id	acadia23_v1_166
authors	Chamorro Martin, Eduardo; Burry, Mark; Marengo, Mathilde
year	2023
title	High-performance Spatial Composite 3D Printing
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 1: Projects Catalog of the 43rd Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9860805-8-1]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 166-171.
summary	This project explores the advantages of employing continuum material topology optimization in a 3D non-standard lattice structure through fiber additive manufacturing processes (Figure 1). Additive manufacturing (AM) has gained rapid adoption in architecture, engineering, and construction (AEC). However, existing optimization techniques often overlook the mechanical anisotropy of AM processes, resulting in suboptimal structural properties, with a focus on layer-by-layer or planar processes. Materials, processes, and techniques considering anisotropy behavior (Kwon et al. 2018) could enhance structural performance (Xie 2022). Research on 3D printing materials with high anisotropy is limited (Eichenhofer et al. 2017), but it holds potential benefits (Liu et al. 2018). Spatial lattices, such as space frames, maximize structural efficiency by enhancing flexural rigidity and load-bearing capacity using minimal material (Woods et al. 2016). From a structural design perspective, specific non-standard lattice geometries offer great potential for reducing material usage, leading to lightweight load-bearing structures (Shelton 2017). The flexibility and freedom of shape inherent to AM offers the possibility to create aggregated continuous truss-like elements with custom topologies.
series	ACADIA
type	project
email
last changed	2024/04/17 13:58

_id	acadia23_v2_508
id	acadia23_v2_508
authors	Koehler, Daniel; liu, Zidong
year	2023
title	Exploring Building Typologies and their Socioeconomic Contexts: Compositional Insights from Large-Scale-Text-to-Image Models
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 2: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9860805-9-8]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 508-517.
summary	This study utilizes large-scale-text-to-image (LLI) models to investigate possibilities to describe building types data-centric. With the introduction of ""data-centric typologies"" we hope to challenge traditional architectural classification systems, while reviving type as an architectural strategy to link socio-economic contexts to the physical form of a place. By examining artificial intelligence (AI)-generated images of various city buildings, the research explores compositional characteristics, realism, and model limitations. We generated and segmented a synthetic dataset of 15,000 images into individual building segments, conducting a statistical analysis of compositional features across 500 cities. Despite dataset biases and limitations, our results indicate that synthetic databases provide a deeper analytical basis than traditional methods. The generated dataset alone paints forensic landscapes of locales that are not typically showcased. Particularly from a pedagogical perspective, data-centric investigations can serve as a valuable tool for illustrating the diversity of cities and living modes. The findings show that socio-economic attributes, like quality of life, are more closely tied to neighborhoods or projects than entire cities. Consequently, architectural typologies are most effective at a human-ori- ented scale, interfacing city with architecture.
series	ACADIA
type	paper
email
last changed	2024/04/17 13:59

_id	acadia23_v1_110
id	acadia23_v1_110
authors	Scelsa, Jonathan; Sheward, Gregory; Birkeland, Jennifer; Liu, Jemma; Lin, Yun Jou
year	2023
title	Centripetal Clay Printing : Six-Axis Prints for Habitat Column
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 1: Projects Catalog of the 43rd Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9860805-8-1]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 110-115.
summary	Gottfried Semper, in his 1851 text The Four Elements of Architecture, famously classifies architecture into four elemental parts: the hearth, the roof, the enclosure, and the mound, describing the role of the last three to be the “defenders of the hearth’s flame against the three hostile elements of nature (Semper 2011).” Modernity has witnessed the role of enclosure evolve to that of a sealed envelope, or one which meticulously separates the ‘natural environment,’ from the internally regulated environment as part of modern comfort. The post-modern advent of the rain-screen has further separated the layer of exteriorized cultural expression from the structuring envelope, removing the ornamental aspect of Semper’s enclosure, from the enclosing layer. This habit of casting the natural processes out of our building envelopes has resulted in the rapid depletion of space for biodiversity within our cities. Joyce Hwang in her essay “Living Among Pests,” has suggested that the needed reconnection of biodiversity with our urban buildings will force a re-examination of “facade articulation to take on more responsibilities. Ornament will become performative” (Hwang 2013).
series	ACADIA
type	project
email
last changed	2024/04/17 13:58

_id	acadia23_v2_482
id	acadia23_v2_482
authors	Wan, Linxiaoyi; Liu, Jingyang; Bard, Joshua; Cupkova, Dana
year	2023
title	Towards Adaptive Additive Manufacturing: Image-based Monitoring for Binder Jet 3D Printing of Coarse Composite Concrete Powders
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 2: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9860805-9-8]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 482-492.
summary	In the context of concrete 3D printing, this study explores the possibility of image-based monitoring for quality evaluation and improvement in powder-based binder jetting proce- dures for the use of coarse powders. The project's main goal is to create an integrated feedback loop that incorporates an image-based monitoring system into the printing process. This allows for real-time analysis for quality control and simultaneous incorpo- ration of coarse, composite powders. The overarching goal is to expand the possibility of binder jetting towards more diverse powder sources that would enable a circular economy and material reuse. This study investigates how coarser concrete powder and composite mixing ratios affect the printing process, thus laying the groundwork for the future use of hybrid materials instead of just using homogeneous standard powders. In this framework, image-based monitoring aids in more adaptive printing processes in addi- tive manufacturing, which will ultimately help us create 3D-printed structures that are produced with higher accuracy and sustainablility. These developments will also signifi- cantly impact 3D concrete printing in building applications, encouraging innovation and better performance in the additive manufacturing sector.
series	ACADIA
type	paper
email
last changed	2024/04/17 13:59

_id	acadia23_v1_214
id	acadia23_v1_214
authors	Yu, Lei; Zheng, Xi; Liu, Zhe
year	2023
title	Reversed 3D Printing with Robotic Technology for Structure Nodes
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 1: Projects Catalog of the 43rd Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9860805-8-1]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 214-219.
summary	This research focuses on the creation of complex structure nodes using a reversed robotic 3D printing technique (Figure 1 and 2), specifically utilizing FDM (Fused Deposition Modeling) technology. Traditional 3D printing involves building objects layer by layer on a stationary platform. Robotic 3D printing employs a similar method, with a plastic extruder as the end effector of a 6-axis robot. Compared to a conventional 3-axis 3D printer, a robotic 3D printer offers greater flexibility due to its inverse kinematics. For example, a 6-axis robot can directly build models on curved surfaces with varying layer thicknesses based on the geometry. However, when it comes to creating structure nodes with branches splitting in different directions, both work modes have certain drawbacks:
series	ACADIA
type	project
email
last changed	2024/04/17 13:58

_id	sigradi2023_189
id	sigradi2023_189
authors	Liu, Yiyun, Dai, Sida, Kleiss, Michael, Alani, Mostafa and Pebryani, Nyoman
year	2023
title	Manufacturing Methodology for Precast Concrete Tiles with Morphing Shapes
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 67–78
summary	This study presents a novel, sustainable method for producing diverse concrete tiles with a reusable mould, addressing the waste issue associated with traditional tile moulds. Our digital manufacturing system, composed of a Rhino Grasshopper-based design system and an electric actuator-based kinetic mechanism, simplifies the construction process and lowers costs. The effectiveness of this method is showcased through six case studies, demonstrating its adaptability in diverse morphing tile designs, including the reinterpretation of traditional Islamic pattern. This approach opens new possibilities for the cost-effective, sustainable, and versatile use of concrete tiles in architecture.
keywords	Additive Manufacturing, Concrete, Actuated Mould, Morph, Tessellation Tile
series	SIGraDi
email
last changed	2024/03/08 14:06

_id	cdrf2023_139
id	cdrf2023_139
authors	Fuyuan Liu, Min Chen, Lizhe Wang, Zhouyi Xiang, Songhua Huang
year	2023
title	Lightweight and Customized Design via Conformal Parametric Lattice Driven by Stress Fields
source	Proceedings of the 2023 DigitalFUTURES The 5st International Conference on Computational Design and Robotic Fabrication (CDRF 2023)
doi	https://doi.org/https://doi.org/10.1007/978-981-99-8405-3_12
summary	Additive manufacturing has opened up new opportunities for material-based design and optimization, with lattice materials being a key area of interest. Lattice materials can exhibit superb physical properties, such as high thermal conductivity and excellent energy absorption, and be designed to meet specific design objectives. However, optimizing the use of these materials requires considering geometric constraints and loading conditions. This research explores stress-driven multi-agent system (MAS) to achieve high-performance lattice infilling. The von Mises stress and principal stress are investigated as the infilling environments as they are typical failure evaluation criteria. The feasibility of these approaches is demonstrated through a case study of sport helmet design, where MAS is used to generate conformal lattice structures that meet functional and fabrication requirements. The density distribution and arrangement direction of lattice units are effectively controlled in physical fields. The results demonstrate that both von Mises stress field and principal stress field-driven methods can improve the stiffness of helmets compared to the method that only considers geometrical conformity under the same mass. The paper concludes that stress-driven lattice infilling has the potential to revolutionize material-based design and optimization in additive manufacturing.
series	cdrf
email
last changed	2024/05/29 14:04

_id	cdrf2023_78
id	cdrf2023_78
authors	Mengman Liu, Chuhua Ding, Hui Wang
year	2023
title	An Exploration on the Form Design of Movable Structures Based on Uniform Convex Polyhedral Expansion
source	Proceedings of the 2023 DigitalFUTURES The 5st International Conference on Computational Design and Robotic Fabrication (CDRF 2023)
doi	https://doi.org/https://doi.org/10.1007/978-981-99-8405-3_7
summary	5 kinds of regular polyhedra and 13 kinds of semi-regular polyhedra are taken as the main research objects in this paper to explore the form design method of polyhedral expansion through the rotation of polygon. Firstly, the expandable range of uniform convex polyhedra is defined and divided into two types of expansion. Then three solutions are proposed, namely, discarding polygonal faces, constructing rigid-foldable origami mechanisms and constructing scissor-like elements, so that the prior unexpandable uniform convex polyhedron can be expanded. These methods extend the range of expandable uniform convex polyhedron, and can provide new form design ideas for frontier fields such as movable furniture (toys), movable art installations, 3D kinetic facades and space architecture.
series	cdrf
email
last changed	2024/05/29 14:04

_id	cdrf2023_11
id	cdrf2023_11
authors	Yubo Liu, Han Li, Qiaoming Deng, Kai Hu
year	2023
title	Diffusion Probabilistic Model Assisted 3D Form Finding and Design Latent Space Exploration: A Case Study for Taihu Stone Spacial Transformation
source	Proceedings of the 2023 DigitalFUTURES The 5st International Conference on Computational Design and Robotic Fabrication (CDRF 2023)
doi	https://doi.org/https://doi.org/10.1007/978-981-99-8405-3_2
summary	Taihu stone is an important landscape element in Chinese Private Garden on Southern Yangtze river, which is known for its profound cultural and aesthetic significance. In this paper, we intend to introduce the 3D spacial character of Taihu stone into architectural forms and spaces using machine learning, trying to explore the possibilities of AI-assisted 3D form finding and design latent space exploration. Existing spacial transformation of Taihu stone is mainly demonstrated by continuous section slicing, which cannot directly analyze and generate 3D space, thus cannot learn the most characteristic internal space of Taihu stone. This paper used the latest 3D point cloud probabilistic diffusion model to achieve 3D form generation and interpolation of Taihu stone and architectural massing through latent space exploration. Experiments show that a sufficiently trained diffusion model can generate 3D point clouds of Taihu stone and building massing, as well as generate interpolations between them. The latent vector can be manipulated to generate outputs that are more oriented towards the Taihu stone or the building massing, to meet the different needs of designers. Generated point clouds can be reconstructed into triangle meshes or voxelized, as a morphological prototype for further design implementation. Generated forms are capable to provide inspiration and reference for the designers to create free forms, showing the potential of the diffusion model to assist architecture design in conceptual phases.
series	cdrf
email
last changed	2024/05/29 14:04

No more hits.