Mimari Tasarım Optimizasyonunda Evrimsel, Üretken ve Hibrit Yaklaşımların Uygulanması

Abstract

Since the emergence and application of evolutionary optimization approaches in architecture in the early twentieth century, a wide range of studies have attempted to integrate evolutionary strategies with the design process. The extensiveness and dispersion of research in this field and the growing application of the generative evolutionary techniques in solving design problems necessitate analytical classification of pertinent literature review. Based on the descriptive-analytical review of the literature on generative evolutionary strategies in architecture, this paper proposes a research model for an integrated generative design framework to enhance future application of this approach in the conceptual design stage. Therefore, first, selected 140 journal articles, with key-words exploration method, between 2014 and 2020 is analyzed to categorize the applied techniques, identify the gap, and address the issue of selecting the appropriate evolutionary approach in the early stage of design. Literature analysis is classified into seven topics, each demonstrating shortcomings of related studies in four categories of form finding, Spatial Programming, Performance-based optimization, and Multi-objective optimization. The research results indicate a growing interest in applying hybrid methods, multi-objective optimization problems, the need for an integrative generative evolutionary framework in the early design phase, and a conceptual design tools with Co-simulation possibility.

Keywords

• evrimsel optimizasyon algoritması, çok amaçlı optimizasyon, üretken tasarım, hibrit yöntemler

The Application of Evolutionary, Generative, and Hybrid Approaches in Architecture Design Optimization

Abstract

Since the emergence and application of evolutionary optimization approaches in architecture in the early twentieth century, a wide range of studies have attempted to integrate evolutionary strategies with the design process. The extensiveness and dispersion of research in this field and the growing application of the generative evolutionary techniques in solving design problems necessitate analytical classification of pertinent literature review. Based on the descriptive-analytical review of the literature on generative evolutionary strategies in architecture, this paper proposes a research model for an integrated generative design framework to enhance future application of this approach in the conceptual design stage. Therefore, first, selected 140 journal articles, with key-words exploration method, between 2014 and 2020 is analyzed to categorize the applied techniques, identify the gap, and address the issue of selecting the appropriate evolutionary approach in the early stage of design. Literature analysis is classified into seven topics, each demonstrating shortcomings of related studies in four categories of form finding, Spatial Programming, Performance-based optimization, and Multi-objective optimization. The research results indicate a growing interest in applying hybrid methods, multi-objective optimization problems, the need for an integrative generative evolutionary framework in the early design phase, and a conceptual design tools with Co-simulation possibility.

Keywords

• evolutionary optimization algorithm, multi-objective optimization, generative design, hybrid methods

References

1. Abar, S. T. (2017). Agent Based Modelling and Simulation tools: A review of the state-of-art software. Computer Science Review, 24, 13-33. doi:https://doi.org/10.1016/j.cosrev.2017.03.001
2. Abhishek Sanjay Jain, P. S. (2020). Thermal energy performance of an academic building with sustainable probing and optimization with evolutionary algorithm,. Thermal Science and Engineering Progress, 17. doi:https://doi.org/10.1016/j.tsep.2019.100374
3. Araghi, S. K. (2015). Exploring cellular automata for high density residential building form generation. Automation in Construction, 49, 152-162. doi:https://doi.org/10.1016/j.autcon.2014.10.007
4. Bentley, P. (1999). Aspects of evolutionary design by computers. In Advances in Soft Computing (pp. 99-118). Springer, London.
5. Beyer, H. G. (2002). Evolution strategies–A comprehensive introduction. Natural computing, 1 (1), 3-52. doi:https://doi.org/10.1023/A:1015059928466
6. Calixto, V. &. (2015). literature review for space planning optimization using an evolutionary algorithm approach: 1992-2014. SIGRADI 2015 [Proceedings of the 19th Conference of the Iberoamerican Society of Digital Graphics, (pp. 662-671). Florianópolis, SC, Brasil.
7. Ceccato, C. (1999). The architect as toolmaker: computer-based generative design tools and methods. CAADRIA '99 (pp. 295-304). Shanghai (China): Proceedings of The Fourth Conference on Computer Aided Architectural Design Research in Asia / ISBN 7-5439-1233- 3].
8. Chan, K.H., F. J. (2002). An Evolutionary Framework for Enhancing Design. In G. J.S., Artificial Intelligence in Design (pp. 383-403). Dordrecht: Springer. doi:https://doi.org/10.1007/978-94-017-0795-4_19

9. Chatzikonstantinou, I. (2014). A 3-dimensional architectural layout generation procedure for optimization applications: DC-RVD. Thompson, Emine Mine (Ed.), Fusion - Proceedings of the 32nd eCAADe Conference (pp. 287-296). Newcastle upon Tyne, England, UK: olume 1, Department of Architecture and Built Environment, Faculty of Engineering and Environment. Eiben, A. E. (2015). Introduction to evolutionary computing (2nd edition ed.). Berlin, Heidelberg: springer. doi:https://doi.org/10.1007/978-3-662-44874-8
10. Feng Fu. (2018). Design and Analysis of Tall and Complex Structures. ButterworthHeinemann. doi:https://doi.org/10.1016/B978-0-08-101018-1.00006-X
11. Fogel, L. J. (1963). Biotechnology: Concepts and Applications. Englewood Cliffs: NJ: Prentice Hall.
12. Frazer, J. (1995). An Evolutionary Architecture. Architectural Association publications, Themes VII.
13. Frazer, J. H. (2002). Generative and evolutionary techniques for building envelope design. In Soddu, C (Ed.) Generative Art 2002 (pp. 3.1-3.16). Italy, Milan: 5th International Conference GA2002. Generative Design Lab.
14. Gero, J. K. (1997). Learning and re-using information in space layout planning problems using genetic engineering. Artificial Intelligence in Engineering, 11(3), 329-334. doi:https://doi.org/10.1016/S0954-1810(96)00051-9
15. Gong, W. C. (2008). Enhancing the performance of differential evolution using orthogonal design method. Applied Mathematics and Computation 206(1), 56-69. doi:https://doi.org/10.1016/j.amc.2008.08.053
16. Gu, Z. T. (2006). Capturing aesthetic intention during interactive evolution. Computer-Aided Design, 38(3),, 224-237. doi:https://doi.org/10.1016/j.cad.2005.10.008
17. Guo, Z. (2016). Evolutionary approach for spatial architecture layout design enhanced by anagent-based Topolgy finding systems. Frontiers of Architectural Research, 6(1), 53-62. doi:http://dx.doi.org/10.1016/j.foar.2016.11.003
18. Haupt, R. L. (2004). Practical genetic algorithms. Hoboken, New Jersey: John Wiley & Sons, Inc., .
19. Herr, C. M. (2016). Cellular automata in architectural design: From generic systems to specific design tools. Automation in Construction, 72, 39-45. doi:https://doi.org/10.1016/j.autcon.2016.07.005