Pub Date : 2023-03-31DOI: 10.1177/14780771231168232
Adam Sebestyen, Urs Hirschberg, S. Rasoulzadeh
We present an early prototype of a design system that uses Deep Learning methodology—Conditional Variational Autoencoders (CVAE)—to arrive at custom design spaces that can be interactively explored using semantic labels. Our work is closely tied to principles of parametric design. We use parametric models to create the dataset needed to train the neural network, thus tackling the problem of lacking 3D datasets needed for deep learning. We propose that the CVAE functions as a parametric tool in itself: The solution space is larger and more diverse than the combined solution spaces of all parametric models used for training. We showcase multiple methods on how this solution space can be navigated and explored, supporting explorations such as object morphing, object addition, and rudimentary 3D style transfer. As a test case, we implemented some examples of the geometric taxonomy of “Operative Design” by Di Mari and Yoo.
{"title":"Using deep learning to generate design spaces for architecture","authors":"Adam Sebestyen, Urs Hirschberg, S. Rasoulzadeh","doi":"10.1177/14780771231168232","DOIUrl":"https://doi.org/10.1177/14780771231168232","url":null,"abstract":"We present an early prototype of a design system that uses Deep Learning methodology—Conditional Variational Autoencoders (CVAE)—to arrive at custom design spaces that can be interactively explored using semantic labels. Our work is closely tied to principles of parametric design. We use parametric models to create the dataset needed to train the neural network, thus tackling the problem of lacking 3D datasets needed for deep learning. We propose that the CVAE functions as a parametric tool in itself: The solution space is larger and more diverse than the combined solution spaces of all parametric models used for training. We showcase multiple methods on how this solution space can be navigated and explored, supporting explorations such as object morphing, object addition, and rudimentary 3D style transfer. As a test case, we implemented some examples of the geometric taxonomy of “Operative Design” by Di Mari and Yoo.","PeriodicalId":45139,"journal":{"name":"International Journal of Architectural Computing","volume":"21 1","pages":"337 - 357"},"PeriodicalIF":1.7,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47021139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-30DOI: 10.1177/14780771231168223
Ingrid Mayrhofer-Hufnagl, Benjamin Ennemoser
Understanding the importance of data is crucial for realizing the full potential of AI in architectural design. Satellite images are extremely numerous, continuous, high resolution, and accessible, allowing nuanced experimentation through dataset curation. Combining deep learning with remote-sensing technologies, this study poses the following questions. Do newly available datasets uncover ideas about the city previously hidden because urban theory is predominantly Eurocentric? Do extensive and continuous datasets promise a more refined examination of datasets’ effects on outcomes? Generative adversarial networks can endlessly generate new designs based on a curated dataset, but architectural evaluation has been questionable. We employ quantitative and qualitative assessment metrics to investigate human collaboration with AI, producing results that contribute to understanding AI-based urban design models and the significance of dataset curation. Graphical Abstract
{"title":"Advancing justice in a city’s complex systems using designs enabled by space","authors":"Ingrid Mayrhofer-Hufnagl, Benjamin Ennemoser","doi":"10.1177/14780771231168223","DOIUrl":"https://doi.org/10.1177/14780771231168223","url":null,"abstract":"Understanding the importance of data is crucial for realizing the full potential of AI in architectural design. Satellite images are extremely numerous, continuous, high resolution, and accessible, allowing nuanced experimentation through dataset curation. Combining deep learning with remote-sensing technologies, this study poses the following questions. Do newly available datasets uncover ideas about the city previously hidden because urban theory is predominantly Eurocentric? Do extensive and continuous datasets promise a more refined examination of datasets’ effects on outcomes? Generative adversarial networks can endlessly generate new designs based on a curated dataset, but architectural evaluation has been questionable. We employ quantitative and qualitative assessment metrics to investigate human collaboration with AI, producing results that contribute to understanding AI-based urban design models and the significance of dataset curation. Graphical Abstract","PeriodicalId":45139,"journal":{"name":"International Journal of Architectural Computing","volume":"21 1","pages":"280 - 296"},"PeriodicalIF":1.7,"publicationDate":"2023-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46032667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-29DOI: 10.1177/14780771231168226
Marcela Noronha Pinto de Oliveira e Sousa, F. Corrêa
There has been a recent interest in the field of digital heritage to advance historic building information modeling (HBIM) towards digital twins (DT). This paper investigates the potential and limitations of HBIM use as DTs through a systematic mapping of literature (SML). The conclusions were applied in an incremental and low-code workflow to model historic buildings aiming at achieving a trade-off between a high degree of parametrization and a high degree of geometric accuracy. The proposed workflow is illustrated through a parametric script developed with visual programming in Grasshopper for Rhino 3D to model historic columns from profiles. VisualARQ for Rhino 3D is used to convert the script into a BIM object that uses profiles, automatically extracted from a point cloud acquired with 3D laser scanning, as an initial shape. This results in a simpler workflow to achieve more accurate HBIM models that could be leveraged in DT simulations.
最近，人们对数字遗产领域产生了兴趣，将历史建筑信息模型(HBIM)推进到数字双胞胎(DT)。本文通过系统的文献映射(SML)研究了HBIM作为dt使用的潜力和局限性。这些结论被应用于增量和低代码的工作流程中，以模拟历史建筑，旨在实现高度参数化和高度几何精度之间的权衡。提出的工作流程是通过一个参数化脚本来说明的，该脚本是用可视化编程在Grasshopper中为Rhino 3D开发的，可以从配置文件中对历史列进行建模。VisualARQ for Rhino 3D用于将脚本转换为BIM对象，该对象使用从3D激光扫描获得的点云中自动提取的轮廓作为初始形状。这导致了一个更简单的工作流程，以实现更准确的HBIM模型，可以在DT模拟中利用。
{"title":"Towards digital twins for heritage buildings: A workflow proposal","authors":"Marcela Noronha Pinto de Oliveira e Sousa, F. Corrêa","doi":"10.1177/14780771231168226","DOIUrl":"https://doi.org/10.1177/14780771231168226","url":null,"abstract":"There has been a recent interest in the field of digital heritage to advance historic building information modeling (HBIM) towards digital twins (DT). This paper investigates the potential and limitations of HBIM use as DTs through a systematic mapping of literature (SML). The conclusions were applied in an incremental and low-code workflow to model historic buildings aiming at achieving a trade-off between a high degree of parametrization and a high degree of geometric accuracy. The proposed workflow is illustrated through a parametric script developed with visual programming in Grasshopper for Rhino 3D to model historic columns from profiles. VisualARQ for Rhino 3D is used to convert the script into a BIM object that uses profiles, automatically extracted from a point cloud acquired with 3D laser scanning, as an initial shape. This results in a simpler workflow to achieve more accurate HBIM models that could be leveraged in DT simulations.","PeriodicalId":45139,"journal":{"name":"International Journal of Architectural Computing","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44003552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-24DOI: 10.1177/14780771231162382
Dimitra Tsoumpri
Flexible and adaptable spaces have been a field of interest in western architecture since the 1930s and Modernism’s “Open plan.” Even though it started as a design problem, as cybernetics became a more active part of the design process, adaptable space became dependent on technology and mechanical systems. A lot of methods tend to diminish the role of architectural design and offer deterministic implementations that limit the user’s creative freedom and interaction with the adaptable system. This study explores how adaptable space can be approached through design and how adaptability can be implemented in existing spaces through a computational approach. The paper is structured in two parts, the analysis, and the concept method. The first part includes the literacy review and known architectural examples of adaptability. The second part focuses on proposing a design method for approaching adaptable spaces with a high degree of user creative freedom. The method is tested through a case study regarding the implementation of a spatial adaptable system in a 1970s apartment.
{"title":"Architectural space as an open, adaptable system: A design experiment","authors":"Dimitra Tsoumpri","doi":"10.1177/14780771231162382","DOIUrl":"https://doi.org/10.1177/14780771231162382","url":null,"abstract":"Flexible and adaptable spaces have been a field of interest in western architecture since the 1930s and Modernism’s “Open plan.” Even though it started as a design problem, as cybernetics became a more active part of the design process, adaptable space became dependent on technology and mechanical systems. A lot of methods tend to diminish the role of architectural design and offer deterministic implementations that limit the user’s creative freedom and interaction with the adaptable system. This study explores how adaptable space can be approached through design and how adaptability can be implemented in existing spaces through a computational approach. The paper is structured in two parts, the analysis, and the concept method. The first part includes the literacy review and known architectural examples of adaptability. The second part focuses on proposing a design method for approaching adaptable spaces with a high degree of user creative freedom. The method is tested through a case study regarding the implementation of a spatial adaptable system in a 1970s apartment.","PeriodicalId":45139,"journal":{"name":"International Journal of Architectural Computing","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46692173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1177/14780771221095307
Djordje Stojanovic, M. Vujovic, Yi Ding, Milan Katic
This paper introduces modular and context-aware evaporative cooling for the outdoor urban environment as a physical structure that could be implemented at various scales and physical contexts. We propose a technique for collecting occupancy and climatic data to create a computational context and optimise its operation. We then outline a concept for developing a predictive algorithm that would further enhance its performance. The research focuses on the interaction between the proposed system and the environment and establishes an evidence-based technique to balance the temperature drop and the humidity it generates. The study combines architectural design, mechanical engineering and computer science to enable the upscaled application of evaporative cooling to help reduce local heat accumulation in cities.
{"title":"Context-aware module for evaporative cooling in the outdoor built environment","authors":"Djordje Stojanovic, M. Vujovic, Yi Ding, Milan Katic","doi":"10.1177/14780771221095307","DOIUrl":"https://doi.org/10.1177/14780771221095307","url":null,"abstract":"This paper introduces modular and context-aware evaporative cooling for the outdoor urban environment as a physical structure that could be implemented at various scales and physical contexts. We propose a technique for collecting occupancy and climatic data to create a computational context and optimise its operation. We then outline a concept for developing a predictive algorithm that would further enhance its performance. The research focuses on the interaction between the proposed system and the environment and establishes an evidence-based technique to balance the temperature drop and the humidity it generates. The study combines architectural design, mechanical engineering and computer science to enable the upscaled application of evaporative cooling to help reduce local heat accumulation in cities.","PeriodicalId":45139,"journal":{"name":"International Journal of Architectural Computing","volume":"21 1","pages":"100 - 119"},"PeriodicalIF":1.7,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42142231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1177/14780771221089882
S. M. Haakonsen, A. Rønnquist, N. Labonnote
Shape grammars allow a designer to explore a diverse and broad design space. Especially among architects and engineers, the opportunity to evaluate numerous alternatives in the conceptual phase facilitates creativity. Since the introduction of shape grammars 50 years ago, significant research and development have been performed: new applications, combinations with optimisation and integration in digital environments, among others. Consequently, there is a need to map the existing literature to encourage further progress in the field and a lower threshold for those interested in learning more about shape grammars. This study, therefore, presents a systematic mapping of shape grammars in architecture and engineering. Mapping is performed by identifying a query of relevant keywords used in five databases, with the results forming the basis of the mapping. Each of the included articles is then screened to filter out those that do not fit the content criteria. The remaining publications are then evaluated and organised based on the attributes’ application, research type, implementation, engineering and optimisation. The outcome is organised in explanatory illustrations and tables. The final discussion highlights the extensive work performed with shape grammars in the generation of two-dimensional floor plans, an increase in digital development in recent years and the need for further research. The findings indicate a gap between the state of the art and the necessary level of applicability for shape grammars to be an attractive design tool, especially for non-experts.
{"title":"Fifty years of shape grammars: A systematic mapping of its application in engineering and architecture","authors":"S. M. Haakonsen, A. Rønnquist, N. Labonnote","doi":"10.1177/14780771221089882","DOIUrl":"https://doi.org/10.1177/14780771221089882","url":null,"abstract":"Shape grammars allow a designer to explore a diverse and broad design space. Especially among architects and engineers, the opportunity to evaluate numerous alternatives in the conceptual phase facilitates creativity. Since the introduction of shape grammars 50 years ago, significant research and development have been performed: new applications, combinations with optimisation and integration in digital environments, among others. Consequently, there is a need to map the existing literature to encourage further progress in the field and a lower threshold for those interested in learning more about shape grammars. This study, therefore, presents a systematic mapping of shape grammars in architecture and engineering. Mapping is performed by identifying a query of relevant keywords used in five databases, with the results forming the basis of the mapping. Each of the included articles is then screened to filter out those that do not fit the content criteria. The remaining publications are then evaluated and organised based on the attributes’ application, research type, implementation, engineering and optimisation. The outcome is organised in explanatory illustrations and tables. The final discussion highlights the extensive work performed with shape grammars in the generation of two-dimensional floor plans, an increase in digital development in recent years and the need for further research. The findings indicate a gap between the state of the art and the necessary level of applicability for shape grammars to be an attractive design tool, especially for non-experts.","PeriodicalId":45139,"journal":{"name":"International Journal of Architectural Computing","volume":"21 1","pages":"5 - 22"},"PeriodicalIF":1.7,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44158010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-24DOI: 10.1177/14780771231159239
G. Turhan, Güzden Varinlioğlu, M. Bengisu
Recent studies in digital design and fabrication processes focus on the potentials of using biological systems in nature as mathematical models or more recently as bio-based materials and composites in various applications. The reciprocal integration between mechanical and digital media for designing and manufacturing bio-based products is still open to development. The current digital form-finding scripts involve an extensive material list, although bio-based materials have not been fully integrated yet. This paper explores a customized form-finding process by suggesting a framework through mechanically informed material-based computation. Bacterial cellulose, an unconventional yet potential material for design, was explored across its biological growth, tensile properties, and the integration of datasets into digital form finding. The initial results of the comparison between digital form finding with conventional materials versus mechanically informed digital form finding revealed a huge difference in terms of both the resulting optimum geometry and the maximum axial forces that the geometry could actually handle. Although this integration is relatively novel in the literature, the proposed methodology has proven effective for enhancing the structural optimization process within digital design and fabrication and for bringing us closer to real-life applications. This approach allows conventional and limited material lists in various digital form finding and structural optimization scripts to cover novel materials once the quantitative mechanical properties are obtained. This method has the potential to develop into a commercial algorithm for a large number of bio-based and customized prototypes within the context of digital form finding of complex geometries.
{"title":"Bio-based material integration into computational form-finding tools by introducing tensile properties in the case of bacterial cellulose-based composites","authors":"G. Turhan, Güzden Varinlioğlu, M. Bengisu","doi":"10.1177/14780771231159239","DOIUrl":"https://doi.org/10.1177/14780771231159239","url":null,"abstract":"Recent studies in digital design and fabrication processes focus on the potentials of using biological systems in nature as mathematical models or more recently as bio-based materials and composites in various applications. The reciprocal integration between mechanical and digital media for designing and manufacturing bio-based products is still open to development. The current digital form-finding scripts involve an extensive material list, although bio-based materials have not been fully integrated yet. This paper explores a customized form-finding process by suggesting a framework through mechanically informed material-based computation. Bacterial cellulose, an unconventional yet potential material for design, was explored across its biological growth, tensile properties, and the integration of datasets into digital form finding. The initial results of the comparison between digital form finding with conventional materials versus mechanically informed digital form finding revealed a huge difference in terms of both the resulting optimum geometry and the maximum axial forces that the geometry could actually handle. Although this integration is relatively novel in the literature, the proposed methodology has proven effective for enhancing the structural optimization process within digital design and fabrication and for bringing us closer to real-life applications. This approach allows conventional and limited material lists in various digital form finding and structural optimization scripts to cover novel materials once the quantitative mechanical properties are obtained. This method has the potential to develop into a commercial algorithm for a large number of bio-based and customized prototypes within the context of digital form finding of complex geometries.","PeriodicalId":45139,"journal":{"name":"International Journal of Architectural Computing","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46166373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-04DOI: 10.1177/14780771221147605
Yifan Zhou, Hyoung-June Park
The goal of this paper is to develop an interactive web-based machine learning application to assist architects with multimodal inputs (sketches and textual information) for conceptual design. With different textual inputs, the application generates the architectural stylistic variations of a user’s initial sketch input as a design inspiration. A novel machine learning model for the multimodal input application is introduced and compared to others. The machine learning model is performed through procedural training with the content curation of training data (1) to control the fidelity of generated designs from the input and (2) to manage their diversity. The web-based interface is at its work in progress as a frontend of the proposed application for better user experience and future data collection. In this paper, the framework of the proposed interactive application is explained. Furthermore, the implementation of its prototype is demonstrated with various examples.
{"title":"An AI-augmented multimodal application for sketching out conceptual design","authors":"Yifan Zhou, Hyoung-June Park","doi":"10.1177/14780771221147605","DOIUrl":"https://doi.org/10.1177/14780771221147605","url":null,"abstract":"The goal of this paper is to develop an interactive web-based machine learning application to assist architects with multimodal inputs (sketches and textual information) for conceptual design. With different textual inputs, the application generates the architectural stylistic variations of a user’s initial sketch input as a design inspiration. A novel machine learning model for the multimodal input application is introduced and compared to others. The machine learning model is performed through procedural training with the content curation of training data (1) to control the fidelity of generated designs from the input and (2) to manage their diversity. The web-based interface is at its work in progress as a frontend of the proposed application for better user experience and future data collection. In this paper, the framework of the proposed interactive application is explained. Furthermore, the implementation of its prototype is demonstrated with various examples.","PeriodicalId":45139,"journal":{"name":"International Journal of Architectural Computing","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43887863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-03DOI: 10.1177/14780771221148778
Ruwan Fernando, Ruby Michael
Evolutionary design (ED) is a strategy that makes use of computational power to couple generative techniques with evaluation methods, to put forward designs that are better with each iteration. In this research, we present a representation scheme for solving spatial layout problems that is simple to implement as well as extend. The mechanisms for evaluation and mutation are defined and also shown to be extendable. Ultimately, the topic explored here is the ways in which ED and computation can enhance our design thinking and how computers can provide the background to new design processes and workflows.
{"title":"Solving planning problems with evolutionary computation","authors":"Ruwan Fernando, Ruby Michael","doi":"10.1177/14780771221148778","DOIUrl":"https://doi.org/10.1177/14780771221148778","url":null,"abstract":"Evolutionary design (ED) is a strategy that makes use of computational power to couple generative techniques with evaluation methods, to put forward designs that are better with each iteration. In this research, we present a representation scheme for solving spatial layout problems that is simple to implement as well as extend. The mechanisms for evaluation and mutation are defined and also shown to be extendable. Ultimately, the topic explored here is the ways in which ED and computation can enhance our design thinking and how computers can provide the background to new design processes and workflows.","PeriodicalId":45139,"journal":{"name":"International Journal of Architectural Computing","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45713074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：