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 7082

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

_id	sigradi2020_260
id	sigradi2020_260
authors	Bhattacharya, Maharshi; Jung, Francisco
year	2020
title	Multi-Mission Space Exploration Vehicle (MMSEV) Nosecone Design Optimization
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. 260-266
summary	This paper addresses ergonomic drawbacks in NASA’s modular Multi-Mission Space Exploration Vehicle’s (MMSEV) latest prototype, 2B’s nosecone, to propose new iteration based on considerations such as mass minimization, visibility maximization, and structural integrity. With 2B as a benchmark, and using computational tools typically used in the AEC industry to carry out FEA analysis, comparisons are made with potential design changes. The numerical and visual data such as weight, and stress distribution, provided by the benchmark analysis, served as metrics for comparison and redesign. In turn, this design development exercise attempts to bring together the different design approaches to design, held by human- factors designers and structural engineers.
keywords	Form, Optimization, Finite Element Analysis, Space-Exploration Vehicle, Stress-Analysis
series	SIGraDi
email
last changed	2021/07/16 11:49

_id	ecaade2020_348
id	ecaade2020_348
authors	Chiujdea, Ruxandra Stefania and Nicholas, Paul
year	2020
title	Design and 3D Printing Methodologies for Cellulose-based Composite Materials
doi	https://doi.org/10.52842/conf.ecaade.2020.1.547
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. 547-554
summary	A growing awareness of architecture's environmental responsibility is encouraging a shift from an industrial age to an ecological one. This shift emphasises a new era of materiality, characterised by a special focus on bio-polymers. The potential of these materials is to address unsustainable modes of resource consumption, and to rebalance our relationship with the natural. However, bio-polymers also challenge current design and manufacturing practices, which rely on highly manufactured and standardized materials. In this paper, we present material experiments and digital design and fabrication methodologies for cellulose-based composites, to create porous biodegradable panels. Cellulose, the most abundant bio-polymer on Earth, has potential for differentiated architectural applications. A key limit is the critical role of additive fabrication methods for larger scale elements, which are a subject of ongoing research. In this paper, we describe how controlling the interdependent relationship between the additive manufacturing process and the material grading enables the manipulation of the material's performance, and the related control aspects including printing parameters such as speed, nozzle diameter, air flow, etc., as well as tool path trajectory. Our design exploration responds to the emerging fabrication methods to achieve different levels of porosity and depth which define the geometry of a panel.
keywords	cellulose-based composite material; additive manufacturing; material grading; digital fabrication; spatial print trajectory; porous panels
series	eCAADe
email
last changed	2022/06/07 07:56

_id	ecaade2020_432
id	ecaade2020_432
authors	Fragkia, Vasiliki and Worre Foged, Isak
year	2020
title	Methods for the Prediction and Specification of Functionally Graded Multi-Grain Responsive Timber Composites
doi	https://doi.org/10.52842/conf.ecaade.2020.2.585
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. 585-594
summary	The paper presents design-integrated methods for high-resolution specification and prediction of functionally graded wood-based thermal responsive composites, using machine learning. The objective is the development of new circular design workflow, employing robotic fabrication, in order to predict fabrication files linked to material performance and design requirements, focused on application for intrinsic responsive and adaptive architectural surfaces. Through an experimental case study, the paper explores how machine learning can form a predictive design framework where low-resolution data can solve material systems at high resolution. The experimental computational and prototyping studies show that the presented image-based machine learning method can be adopted and adapted across various stages and scales of architectural design and fabrication. This in turn allows for a design-per-requirement approach that optimizes material distribution and promotes material economy.
keywords	material specification; responsive timber composites; machine learning; robotic fabrication; building envelopes
series	eCAADe
email
last changed	2022/06/07 07:50

_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
doi	https://doi.org/https://doi.org/10.1007/978-981-15-6568-7_13
source	Architectural Intelligence Selected Papers from the 1st International Conference on Computational Design and Robotic Fabrication (CDRF 2025)
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	ecaade2022_161
id	ecaade2022_161
authors	Kharbanda, Kritika, Papadopoulou, Iliana, Pouliou, Panagiota, Daw, Karim, Belwadi, Anirudh and Loganathan, Hariprasath
year	2022
title	LearnCarbon - A tool for machine learning prediction of global warming potential from abstract designs
doi	https://doi.org/10.52842/conf.ecaade.2022.2.601
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. 601–610
summary	The new construction that is projected to take place between 2020 and 2040 plays a critical role in embodied carbon emissions. The change in material selection is inversely proportional to the budget, as the project progresses. Given the fact that early-stage design processes often do not include environmental performance metrics, there is an opportunity to investigate a toolset that enables early-stage design processes to integrate this type of analysis into the preferred workflow of concept designers. The value here is that early-stage environmental feedback can inform the crucial decisions that are made in the beginning, giving a greater chance for a building with better environmental performance in terms of its life cycle. This paper presents the development of a tool called LearnCarbon, as a plugin of Rhino3d, used to educate architects and engineers in the early stages about the environmental impact of their design. It facilitates two neural networks trained with the Embodied Carbon Benchmark Study by Carbon Leadership Forum, which learn the relationship between building geometry, typology, and structure with the Global Warming potential in tCO2e. The first one, a regression model, is able to predict the GWP based on the massing model of a building, along with information about typology and location. The second one, a classification model, predicts the construction type given a massing model and target GWP. LearnCarbon can help improve the building life cycle impact significantly, through early predictions of the structure’s material, and can be used as a tool for facilitating sustainable discussions between the architect and the client.
keywords	Machine Learning, Carbon Emissions, LCA, Rhino Plug-in
series	eCAADe
email
last changed	2024/04/22 07:10

_id	caadria2020_161
id	caadria2020_161
authors	Kido, Daiki, Fukuda, Tomohiro and Yabuki, Nobuyoshi
year	2020
title	Mobile Mixed Reality for Environmental Design Using Real-Time Semantic Segmentation and Video Communication - Dynamic Occlusion Handling and Green View Index Estimation
doi	https://doi.org/10.52842/conf.caadria.2020.1.681
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. 681-690
summary	Mixed reality (MR), that blends the real and virtual worlds, attracted attention for consensus-building among stakeholders in environmental design with the visualization of planned landscape onsite. One of the technical challenges in MR is the occlusion problem which occurs when virtual objects hide physical objects that should be rendered in front of virtual objects. This problem may cause inappropriate simulation. And the visual environmental assessment of present and proposed landscape with MR can be effective for the evidence-based design, such as urban greenery. Thus, this study aims to develop a MR-based environmental assessment system with dynamic occlusion handling and green view index estimation using semantic segmentation based on deep learning. This system was designed for the use on a mobile device with video communication over the Internet to implement a real-time semantic segmentation whose computational cost is high. The applicability of the developed system is shown through case studies.
keywords	Mixed Reality (MR); Environmental Design; Dynamic Occlusion Handling; Semantic Segmentation; Green View Index
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	caadria2020_031
id	caadria2020_031
authors	Kim, Nayeon and Lee, Hyunsoo
year	2020
title	Visual Attention in Retail Environments - Design Analysis using HMD based VR System Integrated Eye-Tracking
doi	https://doi.org/10.52842/conf.caadria.2020.1.631
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. 631-640
summary	The goal of this study is to understand the spatial experience of users in retail environments in an immersive virtual reality setting. This study measures the visual attention and visual merchandising cognition of users via a quantitative method. The study was conducted to assess users' visual perception arising from the visual merchandising in-store environment during virtual reality experiences. The experiment was conducted using eye-tracking methodology in a virtual reality environment. After the experiment, participants responded to questionnaire surveys to assess visual merchandising cognition in retail environments. The experiment stimuli were provided in the virtual simulation of a retail store. During the experiment, each participant wearing a head-mounted display device was asked to experience the virtual retail space. The result shows the quantitative analysis of user behavior in the retail space and which design elements attract their attention. Unlike the precedent eye-tracking studies, this research analyzes visual attention during the spatial experience of retailing in its use of virtual reality technology. The approach and findings of this research provide useful information and practical guidelines to retailers and designers who are interested in improving the retail environment in consideration of customer visual attention and spatial elements.
keywords	Visual Attention; Retail Environment; Eye-tracking ; Virtual Reality; HMD (Head-Mounted Display)
series	CAADRIA
email
last changed	2022/06/07 07:49

_id	acadia20_84
id	acadia20_84
authors	Kirova, Nikol; Markopoulou, Areti
year	2020
title	Pedestrian Flow: Monitoring and Prediction
doi	https://doi.org/10.52842/conf.acadia.2020.1.084
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. 84-93.
summary	The worldwide lockdowns during the first wave of the COVID-19 pandemic had an immense effect on the public space. The events brought up an opportunity to redesign mobility plans, streets, and sidewalks, making cities more resilient and adaptable. This paper builds on previous research of the authors that focused on the development of a graphene-based sensing material system applied to a smart pavement and utilized to obtain pedestrian spatiotemporal data. The necessary steps for gradual integration of the material system within the urban fabric are introduced as milestones toward predictive modeling and dynamic mobility reconfiguration. Based on the capacity of the smart pavement, the current research presents how data acquired through an agent-based pedestrian simulation is used to gain insight into mobility patterns. A range of maps representing pedestrian density, flow, and distancing are generated to visualize the simulated behavioral patterns. The methodology is used to identify areas with high density and, thus, high risk of transmitting airborne diseases. The insights gained are used to identify streets where additional space for pedestrians is needed to allow safe use of the public space. It is proposed that this is done by creating a dynamic mobility plan where temporal pedestrianization takes place at certain times of the day with minimal disruption of road traffic. Although this paper focuses mainly on the agent-based pedestrian simulation, the method can be used with real-time data acquired by the sensing material system for informed decision-making following otherwise-unpredictable pedestrian behavior. Finally, the simulated data is used within a predictive modeling framework to identify further steps for each agent; this is used as a proof-of-concept through which more insights can be gained with additional exploration.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ecaade2020_511
id	ecaade2020_511
authors	Maierhofer, Mathias, Ulber, Marie, Mahall, Mona, Serbest, Asli and Menges, Achim
year	2020
title	Designing (for) Change - Towards adaptivity-specific architectural design for situational open Environments
doi	https://doi.org/10.52842/conf.ecaade.2020.2.575
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. 575-584
summary	The introduction of cybernetic principles to the architectural discourse some 50 years ago stimulated a new notion of buildings as dynamic and under-specified systems. Although their traditional conception as static and deterministic objects has remained predominant to this day, concepts for adaptive architecture capable of interacting with their surroundings and occupants have gained renewed attention in recent decades. However, investigations so far have largely concentrated on small-scale applications or individual adaptation strategies. The notion of situational open Environments, as argued in this paper, provides a framework through which adaptivity can be conceived and explored more holistically as well as on an inhabitable scale. Environments reject deterministic design and adaptation solutions and hence call for integrative and interactive design strategies that not only allow for the exploration of particularly adaptable (i.e. underspecified) architectural morphologies, but also for the communication and negotiation during their further development beyond deployment. In respect thereof, this paper discusses the potentials and implications of computational (design) strategies, meaning the agencies of buildings, designers, residents, and surroundings. The presented research originates from the author's involvement in an interdisciplinary research project centered around the development of an adaptive high-rise building that incorporates various adaptation strategies.
keywords	Adaptive Architecture; Architectural Environment; Computational Design; Agent-based Modeling; Architecture Theory; Cybernetics
series	eCAADe
email
last changed	2022/06/07 07:59

_id	caadria2020_259
id	caadria2020_259
authors	Rhee, Jinmo, Veloso, Pedro and Krishnamurti, Ramesh
year	2020
title	Integrating building footprint prediction and building massing - an experiment in Pittsburgh
doi	https://doi.org/10.52842/conf.caadria.2020.2.669
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. 669-678
summary	We present a novel method for generating building geometry using deep learning techniques based on contextual geometry in urban context and explore its potential to support building massing. For contextual geometry, we opted to investigate the building footprint, a main interface between urban and architectural forms. For training, we collected GIS data of building footprints and geometries of parcels from Pittsburgh and created a large dataset of Diagrammatic Image Dataset (DID). We employed a modified version of a VGG neural network to model the relationship between (c) a diagrammatic image of a building parcel and context without the footprint, and (q) a quadrilateral representing the original footprint. The option for simple geometrical output enables direct integration with custom design workflows because it obviates image processing and increases training speed. After training the neural network with a curated dataset, we explore a generative workflow for building massing that integrates contextual and programmatic data. As trained model can suggest a contextual boundary for a new site, we used Massigner (Rhee and Chung 2019) to recommend massing alternatives based on the subtraction of voids inside the contextual boundary that satisfy design constraints and programmatic requirements. This new method suggests the potential that learning-based method can be an alternative of rule-based design methods to grasp the complex relationships between design elements.
keywords	Deep Learning; Prediction; Building Footprint; Massing; Generative Design
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	cdrf2022_209
id	cdrf2022_209
authors	Yecheng Zhang, Qimin Zhang, Yuxuan Zhao, Yunjie Deng, Feiyang Liu, Hao Zheng
year	2022
title	Artificial Intelligence Prediction of Urban Spatial Risk Factors from an Epidemic Perspective
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_18
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
summary	From the epidemiological perspective, previous research methods of COVID-19 are generally based on classical statistical analysis. As a result, spatial information is often not used effectively. This paper uses image-based neural networks to explore the relationship between urban spatial risk and the distribution of infected populations, and the design of urban facilities. We take the Spatio-temporal data of people infected with new coronary pneumonia before February 28 in Wuhan in 2020 as the research object. We use kriging spatial interpolation technology and core density estimation technology to establish the epidemic heat distribution on fine grid units. We further examine the distribution of nine main spatial risk factors, including agencies, hospitals, park squares, sports fields, banks, hotels, Etc., which are tested for the significant positive correlation with the heat distribution of the epidemic. The weights of the spatial risk factors are used for training Generative Adversarial Network models, which predict the heat distribution of the outbreak in a given area. According to the trained model, optimizing the relevant environment design in urban areas to control risk factors effectively prevents and manages the epidemic from dispersing. The input image of the machine learning model is a city plan converted by public infrastructures, and the output image is a map of urban spatial risk factors in the given area.
series	cdrf
email
last changed	2024/05/29 14:02

_id	caadria2020_045
id	caadria2020_045
authors	Zheng, Hao and Ren, Yue
year	2020
title	Machine Learning Neural Networks Construction and Analysis in Vectorized Design Drawings
doi	https://doi.org/10.52842/conf.caadria.2020.2.707
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. 707-716
summary	Machine Learning, a recently prevalent research domain in data prediction and analysis, has been widely used in a variety of fields. In the design field, especially for architectural design, a machine learning method to learn and generate design data as pixelized images has been developed in previous researches. However, proceeding pixelized image data will cause the problems of precision loss and calculation waste, since the geometric architectural design data is efficiently stored and presented as vectorized CAD files. Thus, in this article, the author developed a specific machine learning neural network to learn and predict design drawings as vectorized data, speeding up the learning and predicting process, while improving the accuracy. First, two necessary geometric tests have been successfully done, which shows the central concept of neural network construct. Then, a design rule prediction model was built to demonstrate the methods to optimize the neural network and data structure. Lastly, a generation model based on human-made design data was constructed, which can be used to predict and generate the bedroom furniture positions by inputting the boundary data of the room, door, and window.
keywords	Machine Learning; Artificial Intelligence; Generative Design; Geometric Design
series	CAADRIA
email
last changed	2022/06/07 07:57

_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	ijac20064306
id	ijac20064306
authors	Klinger, Kevin R.; Vermillion, Joshua
year	2006
title	Visualizing the Operative and Analytic: Representing the Digital Fabrication Feedback Loop and Managing the Digital Exchange
source	International Journal of Architectural Computing vol. 4 - no. 3, 79-97
summary	Digital architecture is process-based and reliant upon a conversation between digital visualization, analysis, and production. With the complexity of information generated in process-based digital practices, we need to effectively manage and exchange the information. Feedback loops are integral to this process/product, and thus require extensive management of complex versions of visual and data related information. Quite a lot of scholarly attention has been focused upon highlighting innovative projects using digital fabrication and serial customization. However, there is a scarcity of scholarly work about innovations in visualizing and representing the design data integral in this feedback loop. This paper will examine innovative representational devices such as the matrix, sectioning, layering, bracketing, nesting, and other new forms of organizing, visualizing, analyzing, and simulating complex data, intent upon communicating multiple levels of operations during the design and fabrication process. With a rigorous taxonomy of operative and analytic devices for process-based digital design development, we can begin to outline a trajectory for future evolutions in practice. This writing is an attempt to make a few steps in this direction, and demonstrate some of these new representational ideas in practice.
series	journal
last changed	2007/03/04 07:08

_id	ecaade2011_068
id	ecaade2011_068
authors	Ma, Jin Yul; Choo, Seung Yeon; Seo, Ji Hyo; Jeong, Seung Woo
year	2011
title	A Study on BIM based Energy Efficient Design Improvement for Rural Standard Drawing and Specification in South Korea: Focusing on Using Buffer-Zone
doi	https://doi.org/10.52842/conf.ecaade.2011.430
source	RESPECTING FRAGILE PLACES [29th eCAADe Conference Proceedings / ISBN 978-9-4912070-1-3], University of Ljubljana, Faculty of Architecture (Slovenia) 21-24 September 2011, pp.430-438
summary	Throughout the world, global warming has been considered a severe problem, which has led to efforts being made for technical development to reduce greenhouse gases in the building sector. As more attention has been paid to energy consumption by residential housing in the building sector, policies and studies on domestic dwellings tend to focus on quality improvement and energy-efficient housing development rather than quantitative housing supply. Yet, policies and guidelines considering residential energy efficiency are inclined to focus on performance and lack in integrated consideration in connection with design. Hence, it seems necessary to compare and analyze design and energy efficiency and to study correlations between housing design and energy. Lately, BIM technology has been used in buildings domestically and proved reliable in respect of its features that enable overall comparison and prediction of housing design, performance and efficiency. The present study is to use the BIM technology to analyze energy consumption and the standard drawing schemes for rural areas to find ways to improve efficient design in singles housing sector and to suggest how to take advantage of buffer zones and how to improve housing design in favor of energy efficiency.
wos	WOS:000335665500049
keywords	BIM; Energy Analysis Tool; Rural Standard Drawing; Buffer-Zone; Sustainable design
series	eCAADe
email
last changed	2022/05/01 23:21

_id	caadria2024_198
id	caadria2024_198
authors	Shi, Zewei, Wang, Xiaoxin, Wang, Jinyu, Wang, Yu, Jian, Yixin, Huang, Chenyu and Yao, Jiawei
year	2024
title	A Method for Real-Time Prediction of Indoor Natural Ventilation in Residential Buildings
doi	https://doi.org/10.52842/conf.caadria.2024.1.009
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 1, pp. 9–18
summary	Against the backdrop of energy crises and climate change, performance-oriented architectural design is increasingly gaining attention. Early-stage assessment of natural ventilation performance is crucial for optimizing designs to enhance indoor environmental comfort and reduce building energy consumption. However, traditional numerical simulations are time-consuming, and existing data-driven surrogate models primarily focus on predicting partial indicators in indoor airflow or single-space airflow. Predicting the spatial distribution of airflow is more advantageous for addressing global issues in building layout design. This paper introduces a surrogate model based on Generative Adversarial Networks. We constructed a dataset of floor plans, with 80% of the data generated using parameterized methods and 20% sourced from real-world examples. We developed a 3D encoding method for the floor plans to facilitate machine understanding of spatial depth and structure. Finally, we conducted airflow simulations on the dataset, with the simulated results used to train the Pix2pix model. The results demonstrate that the Pix2pix model can predict indoor airflow distribution with high accuracy, requiring only 0.8 seconds. In the test set, the average values for MAPE, SSIM, and R2 are 2.6113%, 0.9798, and 0.9114, respectively. Our research can improve architectural design, enhance energy efficiency, and enhance residents' comfort, thereby contributing to the creation of healthier indoor environments.
keywords	generative residential buildings, natural indoor ventilation, early design stage, real-time prediction, generative adversarial networks (GAN)
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	ecaade2024_105
id	ecaade2024_105
authors	Wu, Zhaoji; Li, Mingkai; Liu, Wenli; Wang, Zhe; Cheng, Jack C.P.; Kwok, Helen H.L.
year	2024
title	A Data-Driven Model for Sustainable Performance Prediction of Residential Block Layout Design Using Graph Neural Network
doi	https://doi.org/10.52842/conf.ecaade.2024.1.575
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 1, pp. 575–584
summary	Performance evaluation plays a pivotal role in sustainable architectural design, guiding the design direction towards sustainable objectives. Building simulations based on physical modeling are commonly adopted for performance prediction, but the high computational cost hinders their applications in early design stages that require prompt feedback. Surrogate models have been proposed to emulate the expensive high-fidelity building simulation models using data-driven models. Several studies have been conducted to develop surrogate models for sustainable performance prediction of residential block layout design, but the features proposed by these studies were based on specific cases and cannot represent general residential block layout design. To overcome this gap, this study proposes a novel surrogate model for multi-objective sustainable performance prediction based on graph neural network (GNN), which can be adopted in practical early design stages of residential block layout design. First, a graph schema is proposed to represent the general topological relations among components in residential block layout design. Second, an architecture using graph attention network (GAT) is proposed for multiple sustainable performance predictions. Third, a dataset is established based on parametric design models of residential blocks and simulations of sustainable performance, including energy consumption, daylighting, and thermal comfort. Fourth, the proposed surrogate model using the proposed architecture are trained and fine-tuned to learn the relationship between the residential block design and sustainable performance. Finally, the proposed model is evaluated in terms of accuracy, comparing with benchmark models using graph convolutional network (GCN) and artificial neural network (ANN). The results show that the proposed model (GAT) outperforms the benchmark models (GCN and ANN). The proposed model can achieve a satisfactory accuracy with small CV(RMSE)s of 11.97%, 7.88% and 10.11% in terms of energy use intensity (EUI), annual comfort hour (ACH) and useful daylight illuminance (UDI) in the test dataset.
keywords	Surrogate model, Graph neural network, Building performance prediction, Sustainable building design, Residential block
series	eCAADe
email
last changed	2024/11/17 22:05

_id	caadria2024_80
id	caadria2024_80
authors	Yang, Runyu, Wang, Weili and Gui, Peng
year	2024
title	Predicting Pedestrian Trajectories in Architectural Spaces: A Graph Neural Network Approach
doi	https://doi.org/10.52842/conf.caadria.2024.1.251
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 1, pp. 251–260
summary	This paper introduces a graph neural network-based model for predicting pedestrian trajectories in architectural spaces. Compared to traditional simulations based on physics-based models, this data-driven model has a stronger ability to learn and predict pedestrian behaviour patterns from real-world data. The model is pre-trained based on Hongqiao Railway Station Dataset, then trained and tested based on the ETH Dataset and the Stanford Drone Dataset, enabling comparisons with other AI models. By creating a more intelligent model, we can establish a digital replica of the real world that can predict pedestrian flow with higher accuracy in daily life or extreme situations such as sudden fires. Our results underscore the critical role of such models in comprehending how architectural spaces are utilized, and thus in improving architectural design and urban planning.
keywords	multi-agent simulation, trajectory prediction, graph neural network, conditional variational autoencoder, path-finding
series	CAADRIA
email
last changed	2024/11/17 22:05

_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
doi	https://doi.org/10.52842/conf.caadria.2020.1.485
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
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	acadia20_516
id	acadia20_516
authors	Aghaei Meibodi, Mania; Voltl, Christopher; Craney, Ryan
year	2020
title	Additive Thermoplastic Formwork for Freeform Concrete Columns
doi	https://doi.org/10.52842/conf.acadia.2020.1.516
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. 516-525.
summary	The degree of geometric complexity a concrete element can assume is directly linked to our ability to fabricate its formwork. Additive manufacturing allows fabrication of freeform formwork and expands the design possibilities for concrete elements. In particular, fused deposition modeling (FDM) 3D printing of thermoplastic is a useful method of formwork fabrication due to the lightweight properties of the resulting formwork and the accessibility of FDM 3D printing technology. The research in this area is in early stages of development, including several existing efforts examining the 3D printing of a single material for formwork— including two medium-scale projects using PLA and PVA. However, the performance of 3D printed formwork and its geometric complexity varies, depending on the material used for 3D printing the formwork. To expand the existing research, this paper reviews the opportunities and challenges of using 3D printed thermoplastic formwork for fabricating custom concrete elements using multiple thermoplastic materials. This research cross-references and investigates PLA, PVA, PETG, and the combination of PLA-PVA as formwork material, through the design and fabrication of nonstandard structural concrete columns. The formwork was produced using robotic pellet extrusion and filament-based 3D printing. A series of case studies showcase the increased geometric freedom achievable in formwork when 3D printing with multiple materials. They investigate the potential variations in fabrication methods and their print characteristics when using different 3D printing technologies and printing materials. Additionally, the research compares speed, cost, geometric freedom, and surface resolution.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

For more results click below: