Structured Becoming: Evolutionary Processes in Design Engineering

Bollinger, Klaus; Grohmann, Manfred; Tessmann, Oliver

doi:10.1002/ad.1103

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The use of ML in architecture started with the spread of advanced computational design methods such as rule-based systems, generative systems, and knowledge-based systems. The common ground of computational design in architecture is formed by formulating the design process through design rules and parameters (1), automating repetitive tasks (2), and supporting designers' decisions (3) (Bollinger et al, 2010;Duarte, 2005;Herr and Thomas, 2007;Turrin et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

Machine learning for conservation of architectural heritage

Karadağ

2022

OHI

View full text Add to dashboard Cite

PurposeAccurate documentation of damaged or destroyed historical buildings to protect cultural heritage has been on the agenda of architecture for many years. In that sense, this study uses machine learning (ML) to predict missing/damaged parts of historical buildings within the scope of early ottoman tombs.Design/methodology/approachThis study uses conditional generative adversarial networks (cGANs), a subset of ML to predict missing/damaged parts of historical buildings within the scope of early Ottoman tombs. This paper discusses that using GAN as a ML framework is an efficient method for estimating missing/damaged parts of historical buildings. The study uses the plan drawings of nearly 200 historical buildings, which were prepared one by one as a data set for the ML process.FindingsThe study contributes to the field by (1) generating a mixed methodological framework, (2) validating the effectiveness of the proposed framework in the restitution of historical buildings and (3) assessing the contextual dependency of the generated data. The paper provides insights into how ML can be used in the conservation of architectural heritage. It suggests that using a comprehensive data set in the process can be highly effective in getting successful results. The findings of the research will be a reference for new studies on the conservation of cultural heritage with ML and will make a significant contribution to the literature.Research limitations/implicationsA reliable outcome has been obtained concerning the interpretation of documented data and the generation of missing data at the macro level. The framework is remarkably effective when it comes to the identification and re-generation of missing architectural components like walls, domes, windows, doors, etc. on a macro level without details. On the other hand, the proposed methodological framework is not ready for advanced steps of restitution since every case of architectural heritage is very detailed and unique. Therefore, the proposed framework for re-generation of missing components of heritage buildings is limited by the basic geometrical form which means the architectural details of the mentioned components including ornaments, materials, identification of construction layers, etc. are not covered.Originality/valueThe generic literature as to ML models used in architecture mostly constitutes design exploration and floor plan/urban layout generation. More specific studies in the conservation of architectural heritage by using ML mostly focus on architectural component recognition over 3D point cloud data (1) or superficial damage detection of heritage buildings (2). However, we propose a mixed methodological framework for the interpretation of documented architectural data and the regeneration of missing parts of historical buildings. In addition, the methodology and the results of this paper constitute a guide for further research on ML and consequently contribute to architects in the early phases of restitution.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine learning for conservation of architectural heritage

Karadağ

2022

OHI

View full text Add to dashboard Cite

show abstract

“…While the interaction between architects and structural engineers in conceptual exploration has been the subject of much recent research (Bollinger, Grohmann, & Tessmann, 2010;Chok & Donofrio, 2010;Coenders, 2007;, the integration of energy simulation in early architectural modelling is a new area of exploration, which promises original knowledge about the impacts that design decisions have on building energy consumption. The flexible and collaborative integration framework proposed in this thesis offers better decisionsupport in early design by improving the dialogue between architect and engineer to allow the negotiation of different professional worldviews, rather than relying on individual practitioners to interpret information on an as-need basis.…”

Section: Australian Energy Toolsmentioning

confidence: 99%

Energy simulation for decision support in early architectural design

Toth¹

View full text Add to dashboard Cite

Decisions made in the earliest stage of architectural design have the greatest impacts on the environmental and financial performance of buildings. Yet despite being one of the largest contributors to energy consumption and cost, building services are rarely a driving influence in the conceptualisation of architectural form.If building professionals are to engage in sustainable design practices, they must be able to assess the performance impacts of different design options prior to major architectural characteristics becoming fixed. Current modelling and simulation tools, however, largely lack the capacity to resolve design and performance constraints simultaneously. New digital tools and processes for exploring the interdependencies between architecture, building services and energy consumption in early design are needed, so that individual professionals can understand the impacts of their decisions on those of other disciplines and on building performance.In response to this problem, this thesis proposes a framework for performance-oriented design that supports integrated decision-making by enabling architects and engineers to work together to simulate and evaluate the energy performance of design alternatives early on. Arguing the need to work across disciplinary boundaries, it demonstrates how cross-cutting performance objectives can better structure and streamline the integration between design and analysis tasks by establishing a shared basis for communication. Guided by an embedded-practice research methodology, this thesis draws on firsthand experience of multidisciplinary practice to identify the limitations of current tools and processes in supporting performance-oriented investigations, and establishes common goals and principles for an integrated energy-oriented design strategy. It then describes a collaborative tool for energy design and analysis that has been developed as a critical response to observed shortcomings, which provides decision support by permitting practitioners to quickly, flexibly and reliably assess the performance of multiple design options early on.Central to this research is the understanding that there is a need to unify the disparate methods of working that have been adopted by architects and engineers as a result of progressive specialisation within the building industry. This understanding suggests that there is more to the design process than simply data exchanges supported by a common building representation, and points to the importance of communication networks that strengthen the dialogue between architect and engineer. In responding to this finding, the proposed framework facilitates the sharing of knowledge across disciplines, which is of as great a benefit to the design process as the performance evaluation capabilities that it also provides. Principal Supervisor:Professor Journal ArticlesToth, B., Janssen, P., Stouffs, R. Conference PapersJanssen, P., Stouffs, R., Chaszar, A., Boeykens, S., & Toth, B. (2014). Custom digital workflows with user-defined dat...

show abstract

“…Com a recombinação do genótipo (crossover), durante a reprodução e a mutação aleatória, tornou-se possível a existência de variações dentro da população, segundo Wallisser (informação verbal) -Figura 5.26. Depois de mais de 200 gerações, o processo resultou em um sistema que era adaptado a múltiplos critérios arquitetônicos, enquanto, ao mesmo tempo, cumpria as necessidades estruturais (BOLLINGER; GROHMAN;TESSMANN, 2010). No final, havia elementos com e sem paredes, diferentes orientações de paredes, vários tamanhos de vazios, etc.…”

unclassified

Projeto performativo na prática arquitetônica recente

Andrade¹

View full text Add to dashboard Cite

Muitas pessoas participaram ajudando direta ou indiretamente nesta longa jornada de pesquisa e conhecimento que originou esta tese. Mais que um trabalho meu, acredito veementemente que este foi um trabalho coletivo, que surgiu de muitas mentes pensantes e de um esforço coletivo, que foi sintetizado por minha pessoa.Antes de tudo, gostaria de fazer um agradecimento especial a minha orientadora Prof.ª Dr.ª Regina Coeli Ruschel pela amizade, dedicação e paciência. Graças à sua ajuda, foi possível concretizar esta tese.Gostaria também de agradecer aos meus colegas de disciplinas e companheiros do

show abstract

Structured Becoming: Evolutionary Processes in Design Engineering

Cited by 4 publications

References 0 publications

Machine learning for conservation of architectural heritage

Machine learning for conservation of architectural heritage

Energy simulation for decision support in early architectural design

Projeto performativo na prática arquitetônica recente

Contact Info

Product

Resources

About