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 344

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

_id	ecaade2024_160
id	ecaade2024_160
authors	Dar, Ofri; Cohen, Omri Y.; Sharon, Eran; Blonder, Arielle
year	2024
title	Visualizing Frustration: Computational simulation tool for ‘Frustrated Ceramics’
doi	https://doi.org/10.52842/conf.ecaade.2024.1.313
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. 313–322
summary	This paper introduces a novel approach to sustainable construction through ‘Frustrated Ceramics’, a self-morphing clay material system, offering an on-site mould-less shaping method. The system consists of two clay bodies with different shrinkage rates, layered to form a flat sheet. The shrinkage difference drives a geometrical incompatibility during firing process that results in the emergence of a complex 3D shape. Through the analysis of physical experiments, based on the theory of incompatible shells, an understanding of key material properties of the system is established. Specifically, the determination of Young’s moduli ratio of the different clay bodies during critical morphing moments at the kiln is defined. This material property proves essential for the adjustment of an initial simulation tool to the case of morphing clay, enhancing our ability to predict Frustrated Ceramics’ morphing results. Further improvements of the simulation also include meshing and gravity considerations . Both material calibration and the simulation code support the newly developed design feature of variable thickness ratio, expanding control and morphological freedom. Combining physical experiments, digital simulation and physics theory, this study aims at providing architects with a predictive understanding of this energy-efficient ‘Frustrated Ceramic’ system, promoting its accessibility and future adoption in the architectural field.
keywords	parametric-simulation, material-system, material programming, self-morphing, frustrated material, morphing clay
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_181
id	ecaade2024_181
authors	Vaknin, Yitzchak; Sharon, Eran; Blonder, Arielle
year	2024
title	Computational Simulation of Anisotropic Self-Morphing Materials in Architectural Design
doi	https://doi.org/10.52842/conf.ecaade.2024.1.303
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. 303–312
summary	This study introduces a computational simulator designed for materials that morph due to internal stresses, applied to architectural contexts. This approach marks a significant evolution in architectural practices, highlighting a shift towards sustainability, adaptability, and responsiveness in design. These materials present new challenges in architectural design, necessitating advanced computational tools for form-finding to predict complex behaviors not easily inferred from initial conditions. Our simulator, integrated with Grasshopper and using the Kangaroo Physics plugin, aims to enhance shape-finding processes for these materials, providing reliable shape predictions and broadening design possibilities. Focusing on anisotropic materials, particularly fiber-based polymer composites, the simulator enables designers to create structures that can adapt to various conditions. This capability extends the potential for sustainable and innovative architectural solutions, moving beyond traditional design constraints to embrace the complexities of material behavior and interaction. Utilizing sophisticated algorithms and models, the tool facilitates early simulation and visualization of materials and structures, bridging theoretical concepts with practical applications.
keywords	frustrated materials, material simulation, self-morphing, moldless fabrication, anisotropic materials, fiber composites
series	eCAADe
email
last changed	2024/11/17 22:05

_id	caadria2024_75
id	caadria2024_75
authors	Kozlovsky, Roy, Grobman, Yasha and Levy, Hanna
year	2024
title	Coastal Infrastructure Design: Researching Sea-Waves and Textured Surfaces Interaction Using Physical and Virtual Wave Flumes
doi	https://doi.org/10.52842/conf.caadria.2024.1.445
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. 445–454
summary	Projected global rise in sea level and intensification of storms place the shoreline at risk, requiring extensive investment in coastal defence infrastructure. These structures are designed to efficiently dissipate wave energy at the expense of ecological and landscape values. The aim of the research is to establish a multifunctional approach to coastal infrastructure. Within this framework, it proposes a method for utilising simulation tools to creatively shape the interaction of sea waves with coastal structures for scenic and ecological benefits. It sets two primary goals: to establish that computational fluid dynamics tools can be used by architects to design the interaction of sea-waves with solid surfaces. This goal is explored by creating a digital simulation of a physical wave flume facility, and running physical experiments to calibrate the virtual simulation tool. Secondly, it uses these tools to systematically explore the range of possibilities latent in wave-structure interaction by initiating basic research into the flow properties of different types of textured surfaces to improve the aesthetic and ecological performance of such structures.
keywords	Computational Fluid Dynamics, Coastal Infrastructure, Ecological Enhancement, Textured Surfaces, Physical and Virtual Simulations, Computational Design
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	ecaade2024_166
id	ecaade2024_166
authors	Kapon, Gal; Blonder, Arielle; Austern, Guy
year	2024
title	A Machine Learning Approach to The Inverse Problem of Self-Morphing Composites
doi	https://doi.org/10.52842/conf.ecaade.2024.1.293
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. 293–302
summary	Composite materials are valued in architecture for their remarkable strength-to-weight ratio and ability to shape intricate structures. However, conventional methods relying on single-use molds raise environmental concerns. Recent advancements in moldless fabrication, particularly self-morphing techniques, leverage geometric frustration—internal stresses generated by material architecture. Uniaxial shrinkage in composites, traditionally seen as distortions, can be harnessed to create a self-shaping mechanism, enabling the achievement of complex geometries by varying fiber orientations. This paper addresses the inverse problem of self-morphing composites, aiming at the generation of production plans from desired designs for morphing. We propose leveraging machine learning, notably Convolutional Neural Networks (CNNs), to predict fiber layouts using 2D data matrices. The paper outlines the use of simulations to construct a dataset for training CNN models to predict the fiber layouts required to achieve design geometry. The contribution of this work is to advance digital design and simulation methods and tools towards the implementation of self-morphing matter in architectural fabrication.
keywords	Self-morphing, geometric frustration, moldless fabrication, digital fabrication, inverse design, machine learning, CNN, composite materials
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_121
id	ecaade2024_121
authors	Aºut, Serdar
year	2024
title	A Non-linear and Divergent Digital Learning Resource for Design Computation
doi	https://doi.org/10.52842/conf.ecaade.2024.2.705
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. 705–712
summary	This paper presents a novel approach to developing Digital Learning Resources (DLR) for Design Computation (DC). Learning DC requires the students to develop cognitive skills in algorithmic thinking and practical skills in using specific software. Few learning resources integrate cognitive and practical skills, often prioritizing the skills related to tool use with a focus on software functionalities. They typically follow linear narratives in audio-visual or text-based tutorials, which do not align well with the essence of computational thinking. The DLR presented in this paper is a self-paced learning resource that integrates a web of interconnected concepts, methods, tools, and instructions on a non-linear interface, and it aligns better with the divergent qualities of computational design thinking. It is developed for an MSc-level course that introduces computational design. This paper presents its design and implementation, evaluation of its pilot use, and directions for future improvements.
keywords	Design Computation, Architecture Education, Digital Learning Resources, Design Pedagogy, Computational Design Education
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_191
id	ecaade2024_191
authors	Chaskopoulou, Margarita; Varoudis, Tasos
year	2024
title	Reversing Urban Food Deserts: Data-driven adaptive food networks for urban resilience
doi	https://doi.org/10.52842/conf.ecaade.2024.2.097
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. 97–106
summary	Dense urbanization highlights the need to explore metabolic processes and mechanisms for developing resilient and adaptive solutions to ecological challenges. The recent pandemic intensified the pressure to re-evaluate the existing urban foodscapes by revealing disparities in food accessibility. Studies indicate that food deserts are present even in the centre of metropoles, bringing forth the question of the relation between food, segregation and urban morphology. This research introduces a Machine Learning-assisted computational tool that evaluates food networks and identifies optimal new spatial configurations based on curated data analytics, unsupervised machine learning models and space syntax. Its primary focus is the creation of a unified model connecting urban morphology, socioeconomic and temporal data. The output provides the planners and local authorities with a set of possible intervention patterns for food-related functions aiming to assist decision-making processes.
keywords	Computational Design, Machine Learning, Urban Analytics, Food Accessibility, Design Tool
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_395
id	ecaade2024_395
authors	Efthimiou, Eftihis; Vaitsos, Alexandros
year	2024
title	Kaleidoscopic Pragmatism: Generative illumination of an historical Athens office building
doi	https://doi.org/10.52842/conf.ecaade.2024.2.271
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. 271–280
summary	This paper explores the dynamic interplay between computational design, digital simulation and physical modeling in the creation of an innovative architectural intervention within a historical office building in Athens. Spanning several decades of construction (1930s-1980s), the building's illumination waned amidst the encroachment of contemporary structures. Our solution involves a meticulously designed 2.60*2.60m light well, carving through the building's core and housing a nine-storey generative sculpture. This colossal kaleidoscopic prism, working in tandem with a heliostat, serves both as a striking aesthetic statement and an efficient lighting apparatus, ensuring stable natural lighting conditions in the surrounding office space. During the form-finding phase, rigorous computational processes guided the placement of reflective and refractive triangles within the sculpture, achieving specific degrees of porosity and performativity. Simultaneously addressing a demanding architectural program while enhancing spatial qualities, the apparatus showcases its multifaceted nature. Physical modeling played a pivotal role, with a precise model constructed from true-to-scale materials. Employing photometry, we validated lighting performance, bridging the gap between computational simulations and real-world applicability. The confluence of computational design and physical computation not only shapes the aesthetic and functional aspects of the generative sculpture but also fortifies the credibility of its lighting performance. As the work undergoes construction in Athens, this paper offers a comprehensive exploration of the innovative synergy between computational and physical methodologies, providing valuable insights into the seamless integration of cutting-edge technologies with traditional architectural practices. Within the paper, we present the intricacies of the computational apparatus, showcasing conceptual and user-friendly implementations for accessibility by non-specialist end users. We delve into digital simulation steps, integrating their findings and cross-referencing them with their physical computation counterparts, offering a holistic understanding of the project, from the standpoint of the computational designer.
keywords	generative design, performance based design, light simulation, physical modeling
series	eCAADe
email
last changed	2024/11/17 22:05

_id	caadria2024_373
id	caadria2024_373
authors	Fan, Zhaoxiang, Tang, Shuoning and Liu, Mengxuan
year	2024
title	Integrating Genetic Algorithms and RBF Neural Networks in the Early Design Stage of Gymnasium for Multi-Objective Optimization Framework
doi	https://doi.org/10.52842/conf.caadria.2024.1.505
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. 505–514
summary	The early design phase of the gymnasium's enclosing interfaces directly affects the indoor daylighting and thermal environmental performance. The optimization framework proposed in this study aims to simultaneously balance and optimize conflicting objectives, including the maximum daylight factor (DF), minimum daylight glare index (DGP), and minimum solar radiation (RS) for gymnasium. This approach aims to maximize daylighting performance in hot summer regions while avoiding glare, reducing energy consumption, and ultimately enhancing both daylight comfort and energy efficiency during the sports facility design process. Using the SPEA-2 genetic algorithm, the study explored the Pareto front solutions for three different skylight patterns and established a predictive model for design results based on a Radial Basis Function (RBF) neural network. Compared to traditional Multi-Objective Optimization (MOO) frameworks, this optimization method improves computational efficiency and provides more intelligent decision support for the early-stage design of gymnasiums.
keywords	Multi-Objective Optimization (MOO), Building Performance Simulation (BPS), Parametric Design (PD), Predictive Model.
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	ecaade2024_291
id	ecaade2024_291
authors	Gomez Z., Paula; Swarts, Matthew; Vegas, Gonzalo
year	2024
title	Spatiotemporal Modeling Vertically Integrated Project: A VIP on human-centered metrics for architecture
doi	https://doi.org/10.52842/conf.ecaade.2024.2.311
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. 311–318
summary	Spatiotemporal Modeling towards human-centered metrics for architecture refers to the integration of a set of parametric models, including: 3D models, building type and functions, schedules, Agent-based simulations (ABS) of human activities, and Computational-Fluid Dynamics (CFD) models of airflows. The meta-goal is to develop human-centric metrics for improving humans’ quality of life. This work specifically focuses on virus spread modeling, thus we added a fifth model: The virus characteristics model, which includes the virus survival time and transmissibility through Direct, Airborne, and Fomite pathways. The objectives are to integrate the models to determine the impact of specific parameters on human-centric metrics, in this case the “risk of exposure” in certain scenarios. We developed ABS and CFD simulations in Anylogic and Eddy3D platforms, respectively. The integration of all models was implemented in Grasshopper. This paper presents three pilot studies, in the context of the Vertically Integrated Project (VIP) program, using a K-12 school project provided by Perkins&Will architecture firm. We explain the structure of the VIP, interdisciplinary research-based class, emphasizing the sub-projects, research designs, and preliminary results. The technical integration of the aforementioned models into one spatiotemporal model aims to communicate the probability of risk under specific scenarios. Examples of pilot studies under this framework include: What is the best high school schedule to reduce the probability of contagion, in a regular weekday, with/out the implementation of policies such as social-distancing?; What is the impact of a door handle on reducing contamination?; What are the safest chairs in which to sit in a classroom in relation to the HVAC system configuration? among others. The analyses for specific scenarios helps propose general solutions for spaces, behaviors, and protocols, to increase human safety inside buildings.
keywords	Spatiotemporal Modeling, Model Integration, Agent-based Simulation, Computational-Fluid Dynamics, Virus spread, Education
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_000
id	ecaade2024_000
authors	Kontovourkis, Odysseas; Phocas, Marios C.; Wurzer, Gabriel
year	2024
title	eCAADe 2024 Data-Driven Intelligence - Volume 1
doi	https://doi.org/10.52842/conf.ecaade.2024.1.001
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, 734 p.
summary	During the 2020s and beyond, the field of computational design and fabrication will face a number of new challenges and opportunities offered by Artificial Intelligence (AI) and Machine Learning (ML). These technologies represent a new era of data-driven intelligence, which is steadily gaining increasing influence in other fields, but as yet has had little impact in architecture. At the core of this new technological shift, data will be collected, processed, shared, and used as a decision-making tool to resolve a multitude of social, economic, and environmental issues. In the near future, the dynamic and adaptable changes occurring in the built environment which are influenced by climatic and environmental phenomena will be leveraged and used. This includes the effects of occupancy behavior, the building’s structural behavior, fabrication and material characteristics, in combination with the effective harvesting, harnessing, processing and use of large amounts of data. This process will in turn offer new opportunities in design decision-making, as well as in the implementation of new ideas for achieving the best performance, but also for considering contradictory objective criteria. In view of this paradigm shift, the conference attempts to provide the ground for presenting and discussing possibilities offered by data-driven intelligence across a range of thematic areas. These diverse themes might in turn influence and provide the ground for reconsidering architectural knowledge and practice in the future. Characteristic examples might include the recording of environmental and behavioral conditions in the built environment. For example, the recording of lighting and temperature through the Internet of Things (IoT), as well as examining their integration with AI, and therefore allowing for greater customization of spaces by the users. Moreover, cases where future advancements in computer capacity, combined with AI and ML, will offer the prospect of more powerful immersive environments coming to the fore. In addition, the conference aims to showcase examples where Virtual and Augmented Reality (VR and AR) experiences can be leveraged by datasets in the form of point clouds. This could, for instance, be through 3D Scanning, allowing for greater interaction between the physical and digital worlds, and simultaneously, through the introduction of concepts such as Digital Twins (DT) in various aspects of architectural design and construction. Furthermore, the conference attempts to discuss cases where a large number of fabrication datasets and workflows might be evolved, in combination with the plethora of digital tools currently available. The aim here would be to present how the collection and processing of constantly added data might extend fabrication intelligence, providing a number of advantages, as well as new challenges. More specifically, the conference aims to demonstrate cases where numerical control mechanisms, including robotic technologies applied in several fabrication tasks, such as Additive Manufacturing (AM) and 3D Printing, might be more adaptive in structural and material behavior conditions. This adaptability allows for superior fabrication intelligence to emerge. In parallel, the conference attempts to critically reflect upon, discuss and question the future of applying data-driven intelligence in architectural knowledge and practice. What are the risks posed by the use of data-driven intelligence in architecture? In this new era, what will the role of architects be? Does this mark the beginning of a reconsideration of the way architects participate in the creation of knowledge and practice, or will it bring about their marginalization? What will the social, economic, and environmental impact of data-driven intelligence be? The conference endeavors to address the theme of data-driven intelligence in architectural knowledge and practice spherically. It also looks to explore the advantages and disadvantages that this can bring to the discipline, but also the possibilities that it might offer, with particular emphasis on computational design and fabrication. In view of this perspective, the conference includes, but is not limited to, the topics of Digital Fabrication, Automated Fabrication, Construction, Materials and Form, Structures, Artificial Intelligence in Design, Data in Design, Building Information Modelling, Smart Cities, Virtual Reality and Augmented Reality in Architecture, Information Technology in Heritage, Design Tools and Development, Collaborative Design, Experimentation and Education. We hope that you will enjoy this book and the conference, and you will gain further insight in the research conducted within the topics handled towards a data-driven intelligence in architecture and the design of a sustainable future of the built environment.
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_001
id	ecaade2024_001
authors	Kontovourkis, Odysseas; Phocas, Marios C.; Wurzer, Gabriel
year	2024
title	eCAADe 2024 Data-Driven Intelligence - Volume 2
doi	https://doi.org/10.52842/conf.ecaade.2024.2.001
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, 722 p.
summary	During the 2020s and beyond, the field of computational design and fabrication will face a number of new challenges and opportunities offered by Artificial Intelligence (AI) and Machine Learning (ML). These technologies represent a new era of data-driven intelligence, which is steadily gaining increasing influence in other fields, but as yet has had little impact in architecture. At the core of this new technological shift, data will be collected, processed, shared, and used as a decision-making tool to resolve a multitude of social, economic, and environmental issues. In the near future, the dynamic and adaptable changes occurring in the built environment which are influenced by climatic and environmental phenomena will be leveraged and used. This includes the effects of occupancy behavior, the building’s structural behavior, fabrication and material characteristics, in combination with the effective harvesting, harnessing, processing and use of large amounts of data. This process will in turn offer new opportunities in design decision-making, as well as in the implementation of new ideas for achieving the best performance, but also for considering contradictory objective criteria. In view of this paradigm shift, the conference attempts to provide the ground for presenting and discussing possibilities offered by data-driven intelligence across a range of thematic areas. These diverse themes might in turn influence and provide the ground for reconsidering architectural knowledge and practice in the future. Characteristic examples might include the recording of environmental and behavioral conditions in the built environment. For example, the recording of lighting and temperature through the Internet of Things (IoT), as well as examining their integration with AI, and therefore allowing for greater customization of spaces by the users. Moreover, cases where future advancements in computer capacity, combined with AI and ML, will offer the prospect of more powerful immersive environments coming to the fore. In addition, the conference aims to showcase examples where Virtual and Augmented Reality (VR and AR) experiences can be leveraged by datasets in the form of point clouds. This could, for instance, be through 3D Scanning, allowing for greater interaction between the physical and digital worlds, and simultaneously, through the introduction of concepts such as Digital Twins (DT) in various aspects of architectural design and construction. Furthermore, the conference attempts to discuss cases where a large number of fabrication datasets and workflows might be evolved, in combination with the plethora of digital tools currently available. The aim here would be to present how the collection and processing of constantly added data might extend fabrication intelligence, providing a number of advantages, as well as new challenges. More specifically, the conference aims to demonstrate cases where numerical control mechanisms, including robotic technologies applied in several fabrication tasks, such as Additive Manufacturing (AM) and 3D Printing, might be more adaptive in structural and material behavior conditions. This adaptability allows for superior fabrication intelligence to emerge. In parallel, the conference attempts to critically reflect upon, discuss and question the future of applying data-driven intelligence in architectural knowledge and practice. What are the risks posed by the use of data-driven intelligence in architecture? In this new era, what will the role of architects be? Does this mark the beginning of a reconsideration of the way architects participate in the creation of knowledge and practice, or will it bring about their marginalization? What will the social, economic, and environmental impact of data-driven intelligence be? The conference endeavors to address the theme of data-driven intelligence in architectural knowledge and practice spherically. It also looks to explore the advantages and disadvantages that this can bring to the discipline, but also the possibilities that it might offer, with particular emphasis on computational design and fabrication. In view of this perspective, the conference includes, but is not limited to, the topics of Digital Fabrication, Automated Fabrication, Construction, Materials and Form, Structures, Artificial Intelligence in Design, Data in Design, Building Information Modelling, Smart Cities, Virtual Reality and Augmented Reality in Architecture, Information Technology in Heritage, Design Tools and Development, Collaborative Design, Experimentation and Education. We hope that you will enjoy this book and the conference, and you will gain further insight in the research conducted within the topics handled towards a data-driven intelligence in architecture and the design of a sustainable future of the built environment.
series	eCAADe
email
last changed	2024/11/17 22:05

_id	caadria2024_489
id	caadria2024_489
authors	Koupaei, Afshin
year	2024
title	Bendscape: Optimized Manufacturing by Incorporating Tool Development and Machining in Design
doi	https://doi.org/10.52842/conf.caadria.2024.3.301
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 3, pp. 301–310
summary	The abundance of computationally designed and manufactured architectural projects and pavilions in recent years has shifted the boundaries of architectural design and fabrication to a great extent. Hence, there exists a gap between the computational design and computationally controlled or informed manufacturing. This imposes additional design and production time, waste of material, and in general project costs, more specifically for non-conventional projects. The expansion of architects' computational design skills did not always require an up-to-speed knowledge of computer-aided manufacturing and expertise with material. This is maybe one of the main causes of the aforementioned gap. Moreover, experiments in architectural firms and schools are not always of the same nature. Students of architecture are not necessarily equipped with the knowledge that could be used in the real field to solve the actual computation design and making problems. This article elaborates on an academic experiment attempting to narrow this gap. The project begins with a series of subtractive wood bending experimentations. These studies then provide the foundations for developing a task-specific design and manufacturing toolkit that allows for an accelerated design and making process. To prove the concept, a group of 12 students finalized the final design in one day and delivered the final manufactured pavilion in a week.
keywords	subtractive manufacturing, cnc machining, robotic manufacturing, computational tool developing, material experiment, wood bending, kerf bending, manufacturing optimization
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	caadria2024_273
id	caadria2024_273
authors	Li, Xiaoqian, Han, Zhen, Liu, Gang and Stouffs, Rudi
year	2024
title	A Rapid Prediction Model for View-Based Glare Performance With Multimodal Generative Adversarial Networks
doi	https://doi.org/10.52842/conf.caadria.2024.1.029
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. 29–38
summary	Machine learning-based glare prediction has greatly improved the efficiency of performance feedback. However, its limited generalizability and the absence of intuitive predictive indicators have constrained its practical application. In response, this study proposes a prediction model for luminance distribution images based on the multimodal learning approach. This model focuses on objects within the field of view, integrating spatial and material features through images. It also employs semantic feature mapping and multimodal data integration to flexibly represent building information, removing limitations on model validity imposed by changes in design scenarios. Additionally, the study proposes a multimodal Generative Adversarial Network tailored for the multimodal inputs. This network is equipped with unique feature fusion and reinforcement blocks, along with advanced up-sampling techniques, to efficiently distill and extract pertinent information from the inputs. The model's efficacy is verified by cases focusing on residential building luminance distribution, with a 97% improvement in computational speed compared to simulation methods. Offering both speed and accuracy, this model provides designers with a rapid, flexible, and intuitive supporting approach for daylight performance optimization design, particularly beneficial in the early design stage.
keywords	Glare Prediction, Prediction Model, Multimodal Model, Generative Adversarial Networks
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	caadria2024_49
id	caadria2024_49
authors	Lu, Owen Zhiyuan, Meng, Leo Lin, Ramos Jaime, Cristina and Haeusler, M. Hank
year	2024
title	Clicking is All You Need: Implementing Wave Function Collapse in Early-Stage Design for Manufacturing and Assembly Projects
doi	https://doi.org/10.52842/conf.caadria.2024.1.303
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. 303–312
summary	Wave Function Collapse (WFC) is a constraint-solving algorithm inspired by the quantum mechanics process. However, few attempts have been made in the Architectural, Engineering, and Construction (AEC) industry. WFC literature indicates that it is constrained by its low-fidelity, stochastic process, making it hard to apply in real-world designs, hence its potential lack of application in the AEC sector. Yet this research sees an opportunity in Design for Manufacturing and Assembly (DfMA). Unlike typical architectural projects, DfMA is often more constrained due to modularity. How the DfMA modularity benefits and constricts the spatial planning process, and if such a priori modular definition better informs the design process, is yet to be explored. Thus, how can the highly constrained spatial rules in DfMA architectural design be used in implementing WFC for higher-fidelity fast design concept prototyping? During the research, a prototype was experimented with and implemented while demonstrating several advantages jointly inherited from both the DfMA and WFC, namely (a) high-resolution rapid prototyping with little user intervention for early-stage DfMA and (b) further building material and topological analytics, were enabled for decision support. Hence, this paper addressed the rarely discussed early-stage design problems in the DfMA lifecycle and contributed to a real-world architectural project-based implementation of WFC integrated into an automated computer-aided architectural design workflow inspired by DfMA’s modularity that aligns with Sustainable Development Goals (SDGs) of 11 Sustainable Cities and Communities and 12 Responsible Consumption and Production.
keywords	Wave Function Collapse (WFC), Decision Support Tool, Computational Design, Design for Manufacturing and Assembly (DfMA), Modular Building and Construction.
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	caadria2024_364
id	caadria2024_364
authors	Miao, Shuhan, Peng, Wenzhe, Tsai, Daniel and Nagakura, Takehiko
year	2024
title	Deep Spatial Memory: Quantifying Architectural Spatial Experiences through Agent-driven Simulations and Deep Learning
doi	https://doi.org/10.52842/conf.caadria.2024.1.109
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. 109–118
summary	In architectural theory, the spatial experience is dynamic, evolving from sequences of interconnected views shaped by past encounters and future expectations. Traditional computational methods such as Isovists provide geometric insights but fall short in representing their sequential nature. To address this gap, the paper introduces a novel methodology that combines agent-driven simulation, 3D Isovist sampling, and deep learning for quantitative analysis and comparison of spatial experiences in architecture. This approach leverages the Grasshopper plugin Pedsim for simulating pedestrian paths and a self-supervised video representation learning model MemDPC for processing depth panorama sequences and extracting numerical features for each sequence. The methodology is first validated through a controlled experiment with various sequence typologies, affirming its efficacy in recognizing typological similarities. A case study is conducted comparing Louis Kahn's designs with Roman architecture, quantitatively analysing their intertwined spatial experiences. This research offers a framework for quantitatively comparing spatial experiences across buildings and interpreting the nuanced impact of historical references on modern spaces.
keywords	Deep Learning, Artificial Intelligence, Spatial Experience, Isovist, Agent-driven Simulation, Self-Supervised Learning
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	architectural_intelligence2024_16
id	architectural_intelligence2024_16
authors	Ming Lu, Hao Wu & Philip F. Yuan
year	2024
title	Optimization for industrial robot joint movement in non-horizontal 3D printing application
doi	https://doi.org/https://doi.org/10.1007/s44223-024-00058-z
source	Architectural Intelligence Journal
summary	When a robot is printing a sequence of non-horizontal goal poses, its joint values often undergo significant variations, resulting in challenges such as singularities or exceeding joint limits. This paper proposes two new methods aimed at optimizing goal poses to solve the problem. The first method, employing an analytical approach, modifies the goal poses to maintain the 4th joint value of a 6-axis industrial robot at zero. This adjustment effectively reduces the motion range of the 5th and 6th axes. The second method utilizes numerical optimization to adjust the goal poses, aiming to minimize the motion range of all joints. Leveraging the analytical method to obtain one good initial value, numerical optimization is subsequently applied to complete the entire path optimization, creating an optimization workflow. It is also possible to use only analytical methods for computational efficiency. The feasibility and effectiveness of these two methods are validated through simulation and real project case.
series	Architectural Intelligence
email
last changed	2025/01/09 15:05

_id	ecaade2024_310
id	ecaade2024_310
authors	Mosca, Caterina; D’Amico, Federico
year	2024
title	Data-driven Reduced-Order Models for Multidisciplinary Design Optimization Process
doi	https://doi.org/10.52842/conf.ecaade.2024.1.499
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. 499–508
summary	Multidisciplinary Design Optimization (MDO) is a model-based simulation and optimization process that integrates multiple disciplines with conflicting objectives and design constraints to allow a more affordable design. In the Architecture, Engineering and Construction (AEC) sector this method still in the research and testing phase compared to the automotive and aerospace industries. However, the ability of MDO to extend the number of solutions examined through automation requires significant computational resources. In this context, the following paper explores the advantages of reducing simulation times using the AI-based reduced-order models (ROM). This data-driven method combines Artificial Intelligence and system modelling techniques to reduce computational complexity as Digital Twin (“As Designed”) and it can be used to speed up system design and optimization analyses. This paper presents a test application that explores how AI-based ROM can support the MDO process, which has already been applied to an AEC retrofit project. The case study is a classroom of an existing building where fluid dynamics, thermal and comfort performances have been optimized to support decisions in the conceptual design phase. Although the simulations were successful, a high computational complexity emerged, making it difficult to extend the simulations to the entire building and to more disciplines. The digital experiment carried out in this paper is about speeding up the process and making simulations easier compared to the legacy approach based on high computational simulations. The digital experiment carried out in this paper is about physics phenomena in buildings, which are only a part of the architecture performance and quality. This is an early example of demonstrating how AI-based ROMs can accelerate MDO simulations to make it scalable up the entire AEC design process in the future.
keywords	Multidisciplinary design Optimization, Reduced-order Model, Data-driven techniques, Machine learning, Energy simulation
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_185
id	ecaade2024_185
authors	Neusser, Wilhelm; Morales-Beltran, Mauricio; Ülkün Neusser, Isik; Berthold, Manfred
year	2024
title	An Investigation into Form Blending in Architecture Through Generative Form-Finding and Optimization Procedures: A form-finding methodology
doi	https://doi.org/10.52842/conf.ecaade.2024.2.383
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. 383–392
summary	‘Form-blending’ is a computational design tool rooted in the animation industry and utilized by 3D programs originally developed for cartoon films. At the turn of the millennium, architects and designers started utilizing ‘form-blending’ to design gradual shapes. However, since these form-blended geometries per se, have their genesis rooted in merging irregular patterns, they do not necessarily embrace structural principles. Thus, the use of ‘form-blending’ tools does not guarantee geometries adhere to any generic structural rationale. To address this problem, a comparison discussing the pros and cons of optimization methods and tools regarding their potential for integration into ‘form-blending’ was initiated. The outcome of this process suggested the development of a methodology incorporating discretization, finite element model, and multi-objective optimization in connection with tools such as ‘form-blending', to generate geometries with structural logic. This methodology aims to enable architects and designers to receive structural feedback during the design process and to generate variants based on structural objectives. In a case study employing form-blended shapes, the methodology was tested to evaluate the methodology’s applicability and performance. The results exhibited form-blended geometry based on structural rationale and form-finding principles. Thus, supporting architects with a methodology to employ computational tools such as ‘form blending’ to design and generate variants of shapes based on a structural logic for further structural development.
keywords	Architectural Geometry, Form-Finding, Form-Blending, Generative Design, Multi-Objective Optimization, Design Method
series	eCAADe
type	normal paper
email
last changed	2024/11/20 22:45

_id	ecaade2024_217
id	ecaade2024_217
authors	Panya, David Stephen; Kim, Taehoon; Heo, Minji; Choo, Seungyeon
year	2024
title	A BIM-based Virtual Reality Evacuation Simulation for Fire Safety Management
doi	https://doi.org/10.52842/conf.ecaade.2024.2.047
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. 47–56
summary	In contemporary design and construction engineering, Building Information Modeling (BIM) technology significantly influences the evolution of fire safety. This research explores the intersection of fire safety and virtual reality (VR) by introducing an innovative emergency evacuation simulation method grounded in BIM technology. The study aims to establish a robust framework for emergency evacuation simulations by synthesizing fire dynamics, evacuation strategies, and BIM-based VR technologies. By bridging the theoretical-practical gap, the research endeavors to provide stakeholders in the construction industry with a toolset that prioritizes safety while enhancing designs for safer building projects. The study incorporates fire simulation utilizing CFAST, a representative zone model from the Korean National Institute of Standards and Technology. CFAST divides the fire room into high-temperature upper and low-temperature lower layers, assuming a uniform thermal and chemical environment. It interprets fire phenomena through principles such as mass conservation, the first law of thermodynamics, and the ideal gas equation. The study employs Cellular Automata (CA) to design an agent's reaction and behavior for evacuation. This involves creating a model based on CA rules, determining state changes, and designing behaviors accordingly. The study also focuses on formulating a calculation for evacuation time, refining it based on key factors. The integration of CFAST and CA, along with models for fire and evacuation simulations, enhances the accuracy and utility of evacuation simulations. The research introduces computational models and BIM models in a visually immersive experience in VR across 3 types of fire emergency scenarios.
keywords	BIM, Virtual Reality, Evacuation Simulation, Fire Safety Management
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ijac202322104
id	ijac202322104
authors	Patino, Ever; Jorge Maya amd Andrés Obregón
year	2024
title	A creative form-finding tool: Deformation of plastic sheets due to the influence of temperature and gravity
source	International Journal of Architectural Computing 2024, Vol. 22 - no. 1, 1-27
summary	A form-finding technique based on the deformation of plastic sheets by the action of gravity and temperature increase is proposed, allowing the exploration of complex geometries to support form-giving processes within architecture projects, both by students and practitioners. Using an analog and computational approach, the ideal material for the technique was selected from a multifactorial experiment. Semi-structured analog experimentation was carried out based on inputs, rules, and outputs previously identified, and the resulting models were morphologically analyzed, to later translate the components of the analog experimentation into a computational algorithm to carry out computational experimentation. The technique can be used as a generator of novel forms possessing adequate transformational qualities. Finally, potential applications of the technique and avenues for future research are presented
keywords	Form-finding, computational design, creative tools, experimentation, plastic sheets, form-giving, representation
series	journal
last changed	2024/07/18 13:03

For more results click below: