研究生: |
吴楠 Nan Wu |
---|---|
論文名稱: |
“儀表盤”:蒙地卡羅樹搜索在建築設計初期中的應用 Dashboard: Monte Carlo Tree Search in the Early Stage of Architectural Design |
指導教授: |
施宣光
Shen-Guan Shih |
口試委員: |
謝尚賢
Shang-Hsien Hsieh 彭雲宏 Yeng-Horng Perng 阮怡凱 Yi-Kai Juan 蔡欣君 Lucky Tsaih |
學位類別: |
博士 Doctor |
系所名稱: |
設計學院 - 建築系 Department of Architecture |
論文出版年: | 2020 |
畢業學年度: | 108 |
語文別: | 中文 |
論文頁數: | 176 |
中文關鍵詞: | 衍生式建模 、蒙地卡羅樹搜索 、建築設計初期 、設計決策 、儀表盤 |
外文關鍵詞: | Generative modeling, Monte Carlo Tree Search, Early stage of architectural design, Design decision, Dashboard |
相關次數: | 點閱:371 下載:57 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
建築師在設計流程中對決策節點所建構起來的決策樹進行搜索時,需要在衆多決策選項的搜索空間中找到能夠滿足評估函數的較佳方案。矛盾的是,建築師和專業顧問需要在設計決策確定、有足夠資訊的前提下才能進行有效的評估,但是由於建築設計初期的資訊匱乏導致了建築設計流程中無法進行有效評估。評估資訊無法及時回饋,通常只淪為資料呈現以至於無法實質性地幫助建築師在設計過程中做出決策並造成設計決策無法帶入到下一設計階段的尷尬局面。近年來,在建築資訊建模(Building Information Modeling)深入研究的背景下,資訊技術的提升為解決這種窘境帶來了契機。
本研究提出一個基於衍生式建模(Generative Modeling)與蒙地卡羅樹搜索(Monte Carlo Tree Search)整合而成的架構平臺作爲進行設計決策搜索的“儀表盤”(Dashboard)。在這個架構下,蒙地卡羅樹搜索可以在決策搜索空間較大的決策樹中,在建築設計初期資訊匱乏情況下,通過對未作出決策的決策點進行隨機取樣並評估,並將評估資訊回饋給建築師作爲參考以幫助其瞭解設計趨勢,最終找到滿足評估函數的較佳設計方案。文章通過兩個案例:設計初期對建築量體的配置和建築立面單元幕墻設計來模擬這一過程並進行探討,以證明儀表盤可以幫助建築師做出設計決策,提高溝通與設計效率。
Architects need to find a better solution that can meet the evaluation function in the search space of many design decision options while they are searching the decision tree which constructed by decision nodes in the architectural design process. Paradoxically, architects and professional consultants can only carry out effective evaluations when the design decisions are confirmed and there is sufficient information. However, due to the lack of information in the early stages of architectural design, effective evaluation cannot be carried out in the architectural design process. The evaluation information cannot be feedback in time and is usually used for presentation of data. In this case, the evaluation information cannot substantially help the architect to make design decisions. In recent years, under the background of research on Building Information Modeling, the improvement of information technology has brought an opportunity to solve this problem.
This study proposed a framework platform based on generative modeling and Monte Carlo Tree Search as a dashboard for design decisions searching. Under this framework, Monte Carlo tree search can randomly sample and evaluated on the decision node which have not made decisions in the decision tree with a large searching space, in the case of lack of information in early design stage. It will feedback the information to architects as reference to help them control the design trend, and finally find a better design that meet the evaluation function. This article takes two cases as example, an early design of building massing configuration and building facade unit curtain wall design, to simulate this process and makes discussions to prove that the Dashboard should help architects make design decisions and improve the efficiency of communication and design.
A Working Definition: Integrated Project Delivery. (2007). Retrieved from http://www.ipd-ca.net/images/ IntegratedProjectDeliveryDefinition.pdf 2007.
American Institute of Architects. (2010a). Level of Development. Retrieved from www.aia.org/index.htm.
American Institute of Architects. (2010b). LOD100. Retrieved from www.aia.org/index.htm.
Attia, S., Beltrán, L., Herde1, A., & Hensen, J. (2009). “Architect Friendly”: a comparison of ten different building performance simulation tools. 11th IBPSA Building Simulation Conference, 204–211. Glasgow.
Balcomb, J. D., & Curtner, A. (2002). Multi-criteria decision-making process for buildings. (June), 528–535. https://doi.org/10.1109/iecec.2000.870762
BPMN. (2020). Business Process Modeling Notation. Retrieved from www.bpmn.org
Browne, C., Powley, E. J., Whitehouse, D., Lucas, S., Cowling, P. I., Rohlfshagen, P., … Colton, S. (2012). A survey of Monte Carlo tree search methods. IEEE Transactions on Computational Intelligence and AI in Games, 4(1), 1–43. https://doi.org/10.1109/TCIAIG.2012.2186810
Chang, Y., Wu, N., & ShenGuan, S. (2015). Exploring the integrated project delivery approach for architectural design heuristic. Qingdao: The 11th China Urban Housing Conference.
Cheung, F. K. T., Rihan, J., Tah, J., Duce, D., & Kurul, E. (2012). Early stage multi-level cost estimation for schematic BIM models. Automation in Construction, 27, 67–77. https://doi.org/10.1016/j.autcon.2012.05.008
Chong, Y. T., Chen, C.-H., & Leong, K. F. (2009). A heuristic-based approach to conceptual design. Research in Engineering Design, 20(2), 97–116. https://doi.org/10.1007/s00163-008-0059-9
CURT. (2007). The Construction User`s Roundtable. Retrieved from www.curt.org/
David Silver, Huang, A., Maddison, C. J., Guez, A., Sifre, L., Driessche, G. van den, … Hassabis, D. (2016). Mastering the game of Go with deep neural networks and tree search. Nature, 529, 484–489. https://doi.org/https://doi.org/10.1038/nature16961
David Silver, Julian, S., Simonyan, K., Antonoglou, I., Huang, A., Guez, A., … Hassabis, D. (2017). Mastering the game of Go without human knowledge. Nature, 550, 354–359. https://doi.org/https://doi.org/10.1038/nature24270
de Wit, S., & Augenbroe, G. (2002). Analysis of uncertainty in building design evaluations and its implications. Energy and Buildings, 34(9), 951–958. https://doi.org/10.1016/S0378-7788(02)00070-1
Dieb, T. M., Ju, S., Yoshizoe, K., Hou, Z., Shiomi, J., & Tsuda, K. (2017). MDTS: automatic complex materials design using Monte Carlo tree search. Science and Technology of Advanced Materials, 18(1), 498–503. https://doi.org/10.1080/14686996.2017.1344083
Domínguez-Muñoz, F., Cejudo-López, J. M., Carrillo-Andrés, A., & Ruivo, C. R. (2012). Design of solar thermal systems under uncertainty. Energy and Buildings, 47, 474–484. https://doi.org/10.1016/j.enbuild.2011.12.031
Eastman, C., Teicholz, P., Sacks, R., & Liston, K. (2011). BIM_Handbook_A Guide to Building Information Modeling for Owners, Managers, Designers, Engineers, and Contractors (Second). Hoboken, New Jersey: John Wiley & Sons, Inc.
Flourentzou, F., & Roulet, C.-A. (2002). Elaboration of retrofit scenarios. Energy and Buildings, 34(2), 185–192. https://doi.org/10.1016/S0378-7788(01)00106-2
Generative Modelling Language. (2020). Retrieved from Computer Graphics & Knowledge Visualization, TU Graz website: http://www.generative-modeling.org/GenerativeModeling/Gml.html
Hopfe, C. J., Augenbroe, G. L. M., & Hensen, J. L. M. (2013). Multi-criteria decision making under uncertainty in building performance assessment. Building and Environment, 69, 81–90. https://doi.org/10.1016/j.buildenv.2013.07.019
Huang, Y.-S., Chang, W.-S., & Shih, S.-G. (2014). Building massing optimization in the conceptual design phase. CAD Conference and Exhibition, 78–80. https://doi.org/10.14733/cadconfP.2014.78-80
Hygh, J. S., DeCarolis, J. F., Hill, D. B., & Ranji Ranjithan, S. (2012). Multivariate regression as an energy assessment tool in early building design. Building and Environment, 57, 165–175. https://doi.org/10.1016/j.buildenv.2012.04.021
Isikdag, U. (2012). Design patterns for BIM-based service-oriented architectures. Automation in Construction, 25, 59–71. https://doi.org/10.1016/j.autcon.2012.04.013
Krish, S. (2011). A practical generative design method. Computer-Aided Design, 43(1), 88–100. https://doi.org/10.1016/j.cad.2010.09.009
Kusiak, A., Li, M., & Zhang, Z. (2010). A data-driven approach for steam load prediction in buildings. Applied Energy, 87(3), 925–933. https://doi.org/10.1016/j.apenergy.2009.09.004
Lin, S.-H., & Gerber, D. J. (2014). Evolutionary energy performance feedback for design: Multidisciplinary design optimization and performance boundaries for design decision support. Energy and Buildings, 84, 426–441. https://doi.org/10.1016/j.enbuild.2014.08.034
Mechri, H. E., Capozzoli, A., & Corrado, V. (2010). USE of the ANOVA approach for sensitive building energy design. Applied Energy, 87(10), 3073–3083. https://doi.org/10.1016/j.apenergy.2010.04.001
Meniru, K., Rivard, H., & Bédard, C. (2003). Specifications for computer-aided conceptual building design. Design Studies, 24(1), 51–71. https://doi.org/10.1016/S0142-694X(02)00009-1
Monte Carlo Tree Search. (2020). Retrieved from https://int8.io/monte-carlo-tree-search-beginners-guide/
Negrinho, R., & Gordon, G. (2017). DeepArchitect: Automatically Designing and Training Deep Architectures.
Okudan, G. E., & Tauhid, S. (2008). Concept selection methods- a literature review from 1980 to 2008. International Journal of Design Engineering, 1(3), 243. https://doi.org/10.1504/IJDE.2008.023764
Pietrzyk, K., & Hagentoft, C. (2008). Reliability analysis in building physics design. Building and Environment, 43(4), 558–568. https://doi.org/10.1016/j.buildenv.2007.01.009
Prada, A., Cappelletti, F., Baggio, P., & Gasparella, A. (2014). On the effect of material uncertainties in envelope heat transfer simulations. Energy and Buildings, 71, 53–60. https://doi.org/10.1016/j.enbuild.2013.11.083
Schlueter, A., & Thesseling, F. (2009). Building information model based energy/exergy performance assessment in early design stages. Automation in Construction, 18(2), 153–163. https://doi.org/10.1016/j.autcon.2008.07.003
Shi, X., & Yang, W. (2013). Performance-driven architectural design and optimization technique from a perspective of architects. Automation in Construction, 32, 125–135. https://doi.org/10.1016/j.autcon.2013.01.015
Sun, H., & Ye, X. (2005). Analysis of Risk Factors of Project Cost Base on the MonteCarlo Simulation. Journal of Chongqing Jianzhu University, 121–126.
Turrin, M., von Buelow, P., & Stouffs, R. (2011). Design explorations of performance driven geometry in architectural design using parametric modeling and genetic algorithms. Advanced Engineering Informatics, 25(4), 656–675. https://doi.org/10.1016/j.aei.2011.07.009
Wikipedia. (2015a). Monte Carlo Simulation. Retrieved from https://zh.wikipedia.org/wiki/蒙地卡羅方法
Wikipedia. (2015b). 內容分析法. Retrieved from Wikipedia website: https://zh.wikipedia.org/wiki/內容分析法
Wikipedia. (2020). Monte Carlo tree search. Retrieved from Wikipedia website: https://en.wikipedia.org/wiki/Monte_Carlo_tree_search
Wright, J., & Loosemore, H. (2001). The multi-criterion optimization of building thermal design and control. 7-Th IBPSA Conference, (Dm), 873–880. Retrieved from http://www.inive.org/members_area/medias/pdf/Inive/IBPSA/UFSC505.pdf
Wu, N., & Shih, S.-G. (2015). A BIM Inspired Supporting Platform for Architectural Design. Computer-Aided Design and Applications, 12(3), 327–337. https://doi.org/10.1080/16864360.2014.981463
Zhang, Y. (2017). CityMatrix-An Urban Decision Support System Augmented by Artificial Intelligence. MASSACHUSETTS INSTITUTE OF TECHNOLOGY.
Zook, A., Harrison, B., & Riedl, M. O. (2015). Monte-Carlo Tree Search for Simulation-based Strategy Analysis. Proceedings of the 10th Conference on the Foundations of Digital Games., (Fdg).
謝尚賢. (2012). BIM之應用技術中LOD意謂詳細度或完整度. 營建知識, (352), 60–61.