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 15106

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

_id	caadria2020_115
id	caadria2020_115
authors	Zhong, Jia Ding, Chao, Sara, Ming Chun and Tsou, Jin Yeu
year	2020
title	Establishing a Prediction Model for Better Decision Making Regarding Urban Green Planning in a High-density Urban Context
doi	https://doi.org/10.52842/conf.caadria.2020.1.517
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. 517-526
summary	This paper presents a prototype of a prediction model. The model helps to improve decision making regarding urban green patch planning. This process is achieved by the model predicting the response of thermal comfort conditions in an urban green patch to different planning decisions. This process is demonstrated via an investigation of variations in urban density. The model features a surface temperature mapping approach, which assigns surface temperature data acquired through field-measurement to solid surfaces in CFD simulations based on the shading state. Besides, trees are simulated in a systematic way, and the model combines CFD simulations with PET values, the processes of which are also demonstrated in this paper.
keywords	Urban Green Planning; Decision Making; Thermal Comfort; CFD
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	ecaade2022_153
id	ecaade2022_153
authors	Zhong, Ximing, Fricker, Pia, Yu, Fujia, Tan, Chuheng and Pan, Yuzhe
year	2022
title	A Discussion on an Urban Layout Workflow Utilizing Generative Adversarial Network (GAN) - With a focus on automatized labeling and dataset acquisition
doi	https://doi.org/10.52842/conf.ecaade.2022.2.583
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 2, Ghent, 13-16 September 2022, pp. 583–592
summary	Deep Learning (DL) has recently gained widespread attention in the automation of urban layout processes. This study proposes a rule-based and Generative Adversarial Network (GAN) workflow to automatically select and label urban datasets to train customized GAN models for the generation of urban layout proposals. The developed workflow automatically collects and labels urban typology samples from open-source maps. Furthermore, it controls the results of the GAN process with labels and provides real-time urban layout suggestions based on a co-design process. The conducted case study shows that the average value of the GAN results, trained from an automatically generated dataset, meets the site's requirements. The developed co-design strategy allows the architect to control the GAN process and perform iterations on urban layouts. The research addresses the research gap in GAN applications in the field of urban design and planning. Many studies have demonstrated that training the (GAN) model by labeling enables machines to learn urban morphological features and urban layout logic. However, two research gaps remain: (1) The manual filtering of GAN urban sample datasets to fit site-specific design requirements is very time-consuming. (2) Without a suitable data labeling method, it is difficult to manage the GAN process in such a manner to facilitate the meeting of overriding design requirements.
keywords	Deep Learning, Generative Adversarial Network (GAN), Urban Layout Process, Automatic Dataset Construction, Co-design
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2023_166
id	ecaade2023_166
authors	Zhong, Ximing, Koh, Immanuel and Fricker, Pia
year	2023
title	Building-GNN: Exploring a co-design framework for generating controllable 3D building prototypes by graph and recurrent neural networks
doi	https://doi.org/10.52842/conf.ecaade.2023.2.431
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. 431–440
summary	This paper discusses a novel deep learning (DL) framework named Building-GNN, which combines the Graph Neural Network (GNN) and the Recurrent neural network (RNN) to address the challenge of generating a controllable 3D voxel building model. The aim is to enable architects and AI to jointly explore the shape and internal spatial planning of 3D building models, forming a co-design paradigm. While the 3D results of previous DL methods, such as 3DGAN, are challenging to control in detail and meet the constraints and preferences of architects' inputs, Building-GNN allows for reasoning about the complex constraint relationships between each voxel. In Building-GNN, the GNN simulates and learns the graph structure relationship between 3D voxels, and the RNN captures the complex interplaying constraint relationships between voxels. The training set consists of 4000 rule-based generated 3D voxel models labeled with different degrees of masking. The quality of the 3D results is evaluated using metrics such as IoU, Fid, and constraint satisfaction. The results demonstrate that adding RNN enhances the accuracy of 3D model shape and voxel relationship prediction. Building-GNN can perform multi-step rational reasoning to complete the 3D model layout planning in different scenarios based on the architect's precise control and incomplete input.
keywords	Deep learning, Graph Neural Networks, 3D Building Layout, Co-design Recurrent Neural Networks, Multi-step Reasoning
series	eCAADe
email
last changed	2023/12/10 10:49

_id	caadria2024_378
id	caadria2024_378
authors	Zhong, Ximing, Liang, Jiadong, Pia, Fricker and Liu, Shengyu
year	2024
title	A Framework for Fine-Tuning Urban Gans Using Design Decision Data Generated by Architects Through Gans Applications
doi	https://doi.org/10.52842/conf.caadria.2024.2.019
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 2, pp. 19–28
summary	Recent studies have utilized Generative Adversarial Networks (GANs) to learn from existing urban layouts for urban design tasks. We define these GANs as Urban-GAN. However, urban layouts generated by Urban-GAN lack specificity and often require multiple modifications by architects to meet specific design requirements, making the process inefficient and non-customizable. Inspired by the concept of fine-tuning language models, we propose a stacked GAN model framework that fine-tunes Urban-GAN using data generated by architects in solving specific design tasks, forming AD-Urban-GAN. Our results indicate that layouts produced by AD-Urban-GAN more effectively emulate architects' design morphology decisions, enhancing Urban-GAN’s adaptability and efficiency in handling design tasks. Furthermore, AD-Urban-GAN enhances the customizability of Urban-GAN models for specific urban design tasks, generating layouts that accurately understand and meet the requirements of specific tasks. AD-Urban-GAN significantly streamlines the process of generating design prototypes for specific task types, enabling precise quantitative control over urban layout results. This workflow establishes a data acquisition and training loop that strengthens the customizability of existing GANs. The design decision data generated by architects can improve the adaptability and customization of GANs models, facilitating efficient collaborative work between architects and artificial intelligence.
keywords	architect design decisions, Fine-tuning, GANs, Stack-GANs, adaptability, customizability
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	ecaade2024_199
id	ecaade2024_199
authors	Zhong, Ximing; Liang, Jiadong; Li, Yingkai
year	2024
title	Building-Agent: A 3D generation agent framework integrating large language models and graph-based 3D generation model
doi	https://doi.org/10.52842/conf.ecaade.2024.2.291
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 2, pp. 291–300
summary	Large language models (LLMs) possess powerful intelligence, demonstrating unprecedented potential in AI-driven architectural design. While LLMs can understand design tasks, they lack the reasoning capability from language to three-dimensional (3D) architectural models. This paper proposes a novel 3D building generative agent framework, Building-Agent, which combines LLMs' decision-making capabilities with Graph Neural Networks (GNNs) generative abilities. Experiments utilize real design briefs and site constraints to test the building agent's task-processing capabilities. The results demonstrate that the Building-Agent can accurately predict different site layout outcomes and achieve high task completion rates. Furthermore, it enables interactive 3D building layout iteration through multi-step natural language instructions. The Building-Agent's ability to comprehend and reason about 3D spatial layouts, based on the graph representations of 3D models in the modeling engine and the requirements of natural language inputs, showcases its potential to accomplish tasks with initial proficiency. Compared to previous 3D generative models that rely on human decision-making for inputting spatial constraints, the Building-Agent paves the way for AI to comprehend and complete 3D design tasks autonomously, promising a transformative impact on AI and architectural design.
keywords	Building-Agent, Large Language Model, Graph Generation Model, Language Comprehending, 3D Spatial Reasoning, 3D Cognitive Ability
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_261
id	ecaade2024_261
authors	Zhong, Yuqin; Tan, Zhi Sheng; Mavros, Panagiotis; Hölscher, Christoph; Tunçer, Bige
year	2024
title	Estimating Relative Pedestrian Crowd Distribution: A visibility-graph-based analysis workflow for malls during early design stage
doi	https://doi.org/10.52842/conf.ecaade.2024.2.433
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 2, pp. 433–442
summary	This paper introduces a visibility-graph-based workflow for early stages of architectural design, aimed at estimating relative pedestrian crowd distribution in shopping malls. Traditional methods like Agent-Based Modeling (ABM) and Space Syntax analysis face challenges in early design phases due to extensive data or configuration needs and lack of detail respectively. Our approach uses visibility graph as the foundation and generates visit probabilities and Chains of Activities (COAs) from empirical studies, balancing accuracy, accessibility and efficiency. The workflow's integration within designers’ familiar design interface allows for rapid prototyping and assessment of design iterations, making it a practical tool. Validation through a case study in a shopping mall in Singapore demonstrates the workflow's accuracy, with results showing strong similarity to both ABM and observed data, but with significantly less time and resource demands. This workflow offers a novel solution for early-stage design, providing a swift and accurate means to evaluate pedestrian dynamics and optimize design layouts.
keywords	Pedestrian Crowd Analysis, Mixed-use Building, Shopping Mall Design, Visibility Graph Analysis, Agent-based Modelling, Evidence-based Design
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2018_158
id	ecaade2018_158
authors	Zhou, Jing, Klumpner, Hubert and Brillembourg, Afredo
year	2018
title	The Dynamic Geometric Network Model for Representing Verticalized Urban Environment and its Generation
doi	https://doi.org/10.52842/conf.ecaade.2018.1.525
source	Kepczynska-Walczak, A, Bialkowski, S (eds.), Computing for a better tomorrow - Proceedings of the 36th eCAADe Conference - Volume 1, Lodz University of Technology, Lodz, Poland, 19-21 September 2018, pp. 525-530
summary	Against the background of urbanization and the fast growth of population in big cities, there will be more and more high-rises emerged in the future. In some big cities, the various layers of public transpiration networks such as metro systems also played an essential role in the urban life. In the verticalized urban environment, the complexity of the multi-layers space system connected by various horizontal and vertical connections have been beyond people's cognition. The boundaries between private space and public space, outdoor-space and indoor-space have already blurred. The graph theory based urban spatial analysis approaches are adopted in urban studies to tackle with the urban complexity issues. However, at present, most of the methods proposed are specializing in open urban spaces, and they cannot describe the three-dimensional completely and accurately. Therefore, in this paper, a new graph theory based representation method, the Dynamic Geometric Network Model, which adapted to the verticalized urban environment will be proposed. And the approach of how to automatically generate such a representation model according to the urban layout will also be introduced.
keywords	Graph Model Representation; Graph Model Generation; Verticalized Urban Environment
series	eCAADe
email
last changed	2022/06/07 07:57

_id	caadria2020_173
id	caadria2020_173
authors	Zhou, JueLun and Tong, ZiYu
year	2020
title	Spatial Characteristics Analysis of Urban Form at the Macroscale Based on Landscape Pattern Indices
doi	https://doi.org/10.52842/conf.caadria.2020.1.823
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. 823-832
summary	Spatial characteristics are significant for urban form studies. Because quantifying the urban form at the macroscale is difficult, most of the relevant studies neglect or simplify the diversity of urban built areas. Local climate zone (LCZ) classification systems can transform macro urban form into a theme map composed of different LCZ classes, and such LCZ maps represent an effective urban form mapping technique, especially for built areas. However, this method still fails to provide a quantitative representation of the spatial characteristics. In this paper, the LCZ map is treated as a matrix composed of different patches and landscape pattern indices are applied to quantify the urban form. Taking 8 Chinese cities as case studies, the results show that 4 landscape scale indices and 4 class scale indices can effectively quantify the spatial characteristics of the urban form, including the area, shape, aggregation, and diversity. The quantitative spatial characteristics can provide a reference for urban design and management.
keywords	landscape pattern indices; Local Climate Zones (LCZ); urban form
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	caadria2022_297
id	caadria2022_297
authors	Zhou, Margaret Z., Chen, Shi Yu and Garcia del Castillo y Lopez, Jose Luis
year	2022
title	Elemental Motion in Spatial Interaction (EMSI): A Framework for Understanding Space through Movement and Computer Vision
doi	https://doi.org/10.52842/conf.caadria.2022.1.505
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 505-514
summary	Spatial analysis and evaluation are becoming increasingly common as new technologies enable users, designers, and researchers to study spatial motion patterns without relying on manual notations for observations. While ideas related to motion and space have been studied in other fields such as industrial engineering, choreography, and computer science, the understanding of efficiency and quality in architectural spaces through motion has not been widely explored. This research applies techniques in computer vision to analyse human body motion in architectural spaces as a measure of experience and engagement. A taxonomy framework is proposed to categorize human motion components relevant to spatial interactions, for analysis through computer vision. A technical case study developed upon a machine-learning-aided model is used to test a selection of the proposed framework within domestic kitchen environments. This contribution adds further perspective to wider research explorations in the quality, inclusivity, engagement, and efficiency of architectural spaces through computer-aided tools.
keywords	Pose Estimation, Spatial Evaluation, Architectural Usability, Motion Studies, Computer Vision, SDG 3, SDG 9
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	03b7
authors	Zhou, Ming
year	2000
title	Use of Computers in Reconstruction of Ancient Buildings
doi	https://doi.org/10.52842/conf.acadia.2000.223
source	Eternity, Infinity and Virtuality in Architecture [Proceedings of the 22nd Annual Conference of the Association for Computer-Aided Design in Architecture / 1-880250-09-8] Washington D.C. 19-22 October 2000, pp. 223-225
summary	Many cities in China today are in the midst of a profound architectural transformation. Among these rapidly developing cities, most of them are many centuries old, possessing rich historical architecture of distinct local traditions. However, the ancient buildings and the neighborhood are disappearing quickly, because of the wholesale demolition for urban development or many years of neglect. In this paper, the use of computers in reconstruction of ancient buildings is briefly discussed with some case studies. The advanced computer technology provides a powerful tool for the ancient architecture preservation and reproduction. It makes the reconstruction engineering more efficient, true to the original, and low cost.
series	ACADIA
last changed	2022/06/07 07:57

_id	90b5
authors	Zhou, Qi and Krawczyk, Robert J.
year	2001
title	From CAD to iAD: A survey of Internet application in the AEC industry
doi	https://doi.org/10.52842/conf.acadia.2001.392
source	Reinventing the Discourse - How Digital Tools Help Bridge and Transform Research, Education and Practice in Architecture [Proceedings of the Twenty First Annual Conference of the Association for Computer-Aided Design in Architecture / ISBN 1-880250-10-1] Buffalo (New York) 11-14 October 2001, pp. 392-397
summary	The internet is becoming increasingly more valuable in the field of architectural design that what we conventionally called CAD might soon be changed to iAD (internet Aided Design) (Zhou and Krawczyk 2000). In order to have a clear vision of what iAD will be or could be, we should first examine what is currently available. This research focuses on an investigation of selected web vendors, which are typical and most influential in providing internet related services for the AEC industry. Our purpose for doing this survey is: to understand the progress and development of internet application in the AEC industry, identify the technology used in this area, determine the advantages and deficiencies of current practice and develop a base for future research in proposing a evolutionary model of internet Aided Design for architecture.
keywords	Internet Aided Design, Web-Based Application, On-Line Collaboration
series	ACADIA
email
last changed	2022/06/07 07:57

_id	caadria2023_373
id	caadria2023_373
authors	Zhou, Xinjie, Gong, Lei and Yuan*, Philip F.
year	2023
title	A Large Scale 3D Printing Method for Skeletonized Surfaces Based on Graph Theory
doi	https://doi.org/10.52842/conf.caadria.2023.2.221
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. 221–230
summary	For large-scale Additive manufacturing, while manufacturing thin nonplanar components by printing contours, the printing direction is often perpendicular to the surface, so the components cannot have complex topological features. At the same time, large-scale additive manufacturing is difficult to achieve skeletonized patterns due to the nozzle size and material limitations. Most of the existing printing methods for skeletonized structure use the level set method, which is difficult to adapt to thin shells. This paper introduces a new printing method for 3D printing skeletonized surfaces. The method uses a graph-theoretic approach to plan the printing path, combining the size of the nozzle and the structure of the surface, to enable the printing of surfaces with complex topological features. A 3D printing case is used to verify and prove the practicality of the method. Experimental results show that the method proposed in this paper can effectively solve the problem of printing skeletonized hyperbolic shells and can achieve a continuous printing path. However, there is still room for improvement in many areas of the method to improve print quality.
keywords	graph theory, continuous toolpath, additive manufacturing, shell structure
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	caadria2022_486
id	caadria2022_486
authors	Zhou, Xinyi, Chen, Yao, Chen, Fukai, Li, Kan, Lo, Tian Tian, Xiang, Rufeng and Liu, Liquan
year	2022
title	Remembering Urban Village: Using CloudXR Technology as an Enhanced Alternative to Better Disseminate Heritage
doi	https://doi.org/10.52842/conf.caadria.2022.1.757
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 757-766
summary	Urban villages are strictly related to urban growth. It reflects the era characteristics and memory in urban growth, which has significant value in heritage and sustainable cities (SDG 11). Due to the continuous development of urbanization and the shortage of urban land, many urban villages will be replaced by more valuable functions. Therefore, better preserving the digitalization of urban villages and making more people understand the value of urban villages is particularly important. However, the existing technology still has shortcomings in disseminating digital heritage. For urban villages, usually a large-scale and complex environment, the hardware requirements will be very high for high-precision visualization. Most existing solutions use large hardware devices, such as the virtual sand table. Unlike hand-held devices, such devices are expensive and not portable, limiting better dissemination of such heritage. Due to the hardware limitation of hand-held devices, neither the display resolution nor the interaction effect is satisfying. Therefore, this paper proposes a new workflow by NVIDIA CloudXR streaming technology to achieve high-precision visualization and a rich interactive experience on hand-held devices. Such heritage can be promoted and cities can be more sustainable.
keywords	CloudXR technology, urban village, digital heritage, preservation, dissemination, portable devices, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	caadria2019_664
id	caadria2019_664
authors	Zhou, Yifan, Zhang, Liming, Wang, Xiang, Chen, Zhewen and Yuan, Philip F.
year	2019
title	Exploration of Computational Design and Robotic Fabrication with Wire-Arc Additive Manufacturing Techniques
doi	https://doi.org/10.52842/conf.caadria.2019.1.143
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. 143-152
summary	This paper discussed the exploration of computational design and robotic fabrication with Wire-Arc Additive Manufacturing techniques in a robotic metal printing workshop in Digital Futures 2018. Based on the previous research on structural-performance based design and robotic fabrication, this year's workshop mainly focused on the Wire-Arc Additive Manufacturing techniques and its possible outcomes. A prototype chair was tested for preparation. And the final target of the workshop was to build a bridge about 11m across the river. Through this metal printed bridge project, several computational optimization methods were applied to fulfill the final design. And Wire-Arc Additive Manufacturing techniques with robotic fabrication were carried out during the fabrication process.
keywords	computational design; robotic fabrication; wire-arc additive manufacturing techniques
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	caadria2021_083
id	caadria2021_083
authors	Zhu, Guanqi, Ou, Ya, Bao, Dingwen and Luo, Dan
year	2021
title	Robotic weaving of customizable FRP formworks for large-scale optimized structure
doi	https://doi.org/10.52842/conf.caadria.2021.1.573
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 573-582
summary	This research presents a novel method of robotic fabrication for customizable fiber-reinforced polymer (FRP) tubular formworks, which also function as reinforcements for large-scale structural components. This process is achieved by the spatial weaving of FRP fabric driven by a robotic arm, and calibrated with the fast-cure resin which is applied on the fabric and cures during the weaving process so the fabricated structure is self-supporting and the structure is formed in an additive manner. With this method, structural members with changing sections can be customized and fabricated rapidly with off-the-shelf materials, following a system of structural reinforcement that has been widely adopted in the construction industry and promotes new applications of construction robotics.
keywords	robotic fabrication; fiber reinforced polymer; structural topology optimization
series	CAADRIA
email
last changed	2022/06/07 07:57

_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
doi	https://doi.org/10.52842/conf.caadria.2023.2.109
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
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	caadria2018_082
id	caadria2018_082
authors	Zhu, Li and Yang, Yang
year	2018
title	Optimization Design Study of Lightweight Temporary Building Integrated with PCMS Through CFD Simulation
doi	https://doi.org/10.52842/conf.caadria.2018.2.155
source	T. Fukuda, W. Huang, P. Janssen, K. Crolla, S. Alhadidi (eds.), Learning, Adapting and Prototyping - Proceedings of the 23rd CAADRIA Conference - Volume 2, Tsinghua University, Beijing, China, 17-19 May 2018, pp. 155-164
summary	In fact, the phase change materials (PCMs) integrated in the building envelope structure can decrease the buildings' energy consumption by enhancing thermal energy storage capacity, which has been acknowledged and appreciated by many engineers and architects. To achieve a better practical application effect under the minimum cost principle and provide a different design method based on indoor thermal discomfort evaluation results for stakeholders, this paper numerically test the application effect of composite envelope under Tianjin climate through commercial computational fluid dynamic soft (Fluent). Further, parameter sensitivity to thermal performance of the composite envelope and indoor thermal discomfort are investigated in this paper, and two different evaluation indicators are introduced and used here. The numerical results obtained in this paper support the high potential of using PCM in lightweight temporary buildings and highlight the further optimization design work.
keywords	Optimization design; Lightweight temporary building; PCMs; CFD simulation
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	caadria2021_144
id	caadria2021_144
authors	Zhu, Lufeng, Wibranek, Bastian and Tessmann, Oliver
year	2021
title	Robo-Sheets - Double-Layered Structure Based on Robot-Aided Plastic Sheet Thermoforming
doi	https://doi.org/10.52842/conf.caadria.2021.1.643
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 643-652
summary	Computational design, in combination with robotic fabrication, allows the exploration of complex geometrical differentiation. Notably, thermoplastic sheet materials offer great potential for explorations in robotic fabrication due to their mailable qualities. However, the production of complex shapes from flat-sheet-thermoplastic materials usually depends on molds or on time-consuming procedures. This paper introduces a workflow for the design and fabrication of a double-curved surface made from plastic sheets, which develops a self-supporting structure through using robot-aided one-punch thermoforming. The thickness of a double-curved surface is optimized by applying the Finite Element Method. Notably, forming thermoplastic into a minimal surface strengthens its mechanical properties and this takes a relatively short period of time. According to the relationship between moment and stress in section, two connected minimal-surfaces form a three-dimensional I-profile, making it possible to construct a highly material-efficient structure. Unlike the normal form-finding process, the structure is not limited to compression-only geometry. Compared to thermoforming methods such as Single Point Incremental Forming (SPIF), our one-punch forming process described in this paper shows demonstrates high precision while being less time-consuming. Here, we present a one-to-one scale working prototype as proof of our approach.
keywords	Robotic fabrication; Plastic sheet thermoforming; Lightweight structure; Self-supporting structure; Minimal surface
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	ecaade2022_233
id	ecaade2022_233
authors	Zhu, Zhelun, Coraglia, Ugo-Maria and Fioravanti, Antonio
year	2022
title	PASTA: Parametric Approach for Space Transplanet hAbitations - A generative powered design process for internal configurations in spaceships
doi	https://doi.org/10.52842/conf.ecaade.2022.2.047
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 2, Ghent, 13-16 September 2022, pp. 47–56
summary	This paper focuses on the Space transplanet habitations, or spaceships, that will host astronauts during their transfer to other celestial bodies. In this enterprise, the transfer phase is the most critical in resource shortages (e.g., air, water, room), making it harsh under habitability perspectives. The increasing number of involved scientific disciplines has raised difficulties in managing the design process, and the traditional design strategies have collapsed under the growth of complexities. PASTA proposes an implementation of generative design for the spaceship's internal configurations. This framework focuses on the multi-objective and performance-driven design process, allowing a designer to explore multiple layouts of a complex 'building' such as a spaceship. It encodes habitability needs in an unusual environment and estimates each configuration performance among intertwined needs, including adjacency relationships, by an evaluation system. As a result, PASTA can automate part of the spaceship design tasks and provide decision-making support by evaluating generated solutions, improving the handling of complexities in the design process.
keywords	Space Architecture, Parametric Design, Generative Design, BIM
series	eCAADe
email
last changed	2024/04/22 07:10

_id	caadria2024_58
id	caadria2024_58
authors	Zhuang, Junling, Li, Guanhong, Xu, Hang, Xu, Jintu and Tian, Runjia
year	2024
title	Text-to-City: Controllable 3D Urban Block Generation With Latent Diffusion Model
doi	https://doi.org/10.52842/conf.caadria.2024.2.169
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 2, pp. 169–178
summary	The rise of deep learning has introduced novel computational tools for urban block design. Many researchers have explored generative urban block design using either rule-based or deep learning methods. However, these methods often fall short in adequately capturing morphological features and essential design indicators like building density. Latent diffusion models, particularly in the context of urban design, offer a groundbreaking solution. These models can generate cityscapes directly from text descriptions, incorporating a wide array of design indicators. This paper introduces a novel workflow that utilizes Stable Diffusion, a state-of-the-art latent diffusion model, to generate 3D urban environments. The process involves reconstructing 3D urban block models from generated depth images, employing a systematic depth-to-height mapping technique. Additionally, the paper explores the extrapolation between various urban morphological characteristics, aiming to generate novel urban forms that transcend existing city models. This innovative approach not only facilitates the accurate generation of urban blocks with specific morphological characteristics and design metrics, such as building density, but also demonstrates its versatility through application to three distinct cities. This methodology, tested on select cities, holds potential for broader range of urban environments and more design indicators, setting the stage for future computational urban design research.
keywords	deep learning, generative design, latent diffusion model, urban block morphology, artificial intelligence
series	CAADRIA
email
last changed	2024/11/17 22:05

For more results click below: