每當火災發生時，往往會帶給人們生命和財產造成難以估計的損失，因此消防署針對全國住宅火災發生原因提出住宅防火對策2.0，其住宅防火對策包含制定家庭逃生計畫、建構不易起火與易於避難居住環境等措施。隨著科技進步，現今藉由火災模擬軟體可以進行多項災前預防的工作，包含建築防火設計、消防安全評估、火災事故調查和訓練人員疏散自救等災前預防的項目，降低火災發生次數和減少災害擴大。其中，Fire Dynamics Simulator (FDS)軟體相較於其他火災模擬軟體簡單易用並經過火場實驗驗證，因此被廣為使用與研究，但由於使用FDS軟體需要準備的事前工作繁雜，例如手動設計環境模型和收集被驗證過的火災相關參數，以及會使用FDS軟體語法，所以FDS軟體的使用者大部分都是專業人士。
本論文為提高住宅使用火災模擬軟體來進行災前預防的意願，提出自動化建置適用於FDS軟體環境模型之研究，將包括兩個部分：(1)使用數位孿生(Digital Twin)概念建立系統架構，將真實世界環境映射到數位虛擬空間，在數位虛擬空間自動生成FDS6的環境模型，並使用FDS軟體進行火災模擬來得到火場的危害因子；(2)藉由圖像處理和資料融合技術，收集FDS軟體需要的火災相關參數，包含物件材質、物件尺寸和位置。在實驗部分，將真實環境和手動虛擬環境與自動化虛擬環境進行溫度和煙霧比較，用以說明自動化建置環境模型的可行性。

When a fire breaks out, it often causes lots of economic loss and personal injuries. If the fire simulation can be conducted through the Fire Dynamics Simulator (FDS) before the fire occurs, we can analyze the data of fire hazard factors such as temperature, carbon monoxide and carbon dioxide and other harmful factors, thereby reducing the fire hazard. However, because FDS software requires complicated preparations, including designing environmental models and collecting verified fire-related parameters, the users who use fire simulation software are usually professionals. In this paper, to increase the people's willingness to use FDS software, the research on automatically modeling of indoor environments for fire simulation will include two parts. (1) Establish a system architecture based on the concept of the digital twin. Under this framework, we establish a simulation environment suitable for FDS software in the virtual space and simulate fire. (2) Through image processing and data fusion technology, collect the fire related parameters required by FDS software, including object material, object size and location. In the experimental, we compare the difference of fire simulation between real environment, manual virtual environment, and automatic virtual environment to show that our method can accurately simulate fire.

[1] 中華民國內政部消防署，「107年全國火災統計分析」，2019。
[2] 中華民國內政部消防署，「住宅防火對策2.0」，2018。
[3] G. Hadjisophocleous, Q. Jia, “Comparison of FDS Prediction of Smoke Movement in a 10-Storey Building with Experimental Data.” Fire Technol 45.2, pp. 163-177, 2009.
[4] McGrattan K, Hostikka S, McDermott R, Floyd J, Weinschenk C, Overholt K, “Fire dynamics simulator user’s guide, 6th edn.” NIST and VTT Technical Research Centre of Finland, 2014.
[5] Smardz, P., & Novozhilov, V., “Validation of Fire Dynamics Simulator (FDS) for forced and natural convection flows.”University of Ulster, pp. 16-20, 2006.
[6] 陳弘毅、吳喨生，「火災學」，民國102年3月八版，鼎茂圖書出版股份有限公司。
[7] Forney, Glenn P, “Smokeview (Version 5)-A Tool for Visualizing Fire Dynamics Simulation Data, Volume I: User's Guide.” No. Special Publication (NIST SP)-1017-1, 2017.
[8] P. Smardz, V. Novozhilov, “Validation of Fire Dynamics Simulator (FDS) for forced and natural convection flows.” University of Ulster, pp. 16-20, 2006.
[9] Gong, Xu, and Anil K. Agrawal, “Numerical simulation of fire damage to a long-span truss bridge.” Journal of bridge Engineering 20.10, 04014109, 2015.
[10] 盧以霖，「以 FDS 模擬分析火災延燒」，交通大學，碩士論文，2016。
[11] Sellami, I., Manescau, B., Chetehouna, K., de Izarra, C., Nait-Said, R., & Zidani, F., “BLEVE fireball modeling using Fire Dynamics Simulator (FDS) in an Algerian gas industry.” Journal of Loss Prevention in the Process Industries 54, pp. 69-84, 2018.
[12] Li, Z., Zhang, J., Shen, X., & Fan, J., “Prediction based indoor fire escaping routing with wireless sensor network.” Peer-to-peer networking and applications 10(3), pp. 697-707, 2017.
[13] Wang, S. H., Wang, W. C., Wang, K. C., & Shih, S. Y., “Applying building information modeling to support fire safety management. ” Automation in construction 59, pp. 158-167, 2015.
[14] 蔡詠任，「以FDS進行火場感測資訊蒐集分析之研究」，雲林科技大學，碩士論文，2016。
[15] Grieves M, “Digital twin: manufacturing excellence through virtual factory replication.” http://www.apriso.com, 2014.
[16] Edward Glaessgen and David Stargel, “The digital twin paradigm for future NASA and US Air Force vehicles.” 53rd AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference 20th AIAA/ASME/AHS Adaptive Structures Conference 14th AIAA, 2012.
[17] Tao, F., Cheng, J., Qi, Q., Zhang, M., Zhang, H., & Sui, F., “Digital twin-driven product design, manufacturing and service with big data.” The International Journal of Advanced Manufacturing Technology 94(9-12), pp. 3563-3576, 2018.
[18] Gabor, T., Belzner, L., Kiermeier, M., Beck, M. T., & Neitz, A., “A simulation-based architecture for smart cyber-physical systems.” 2016 IEEE International Conference on Autonomic Computing (ICAC), IEEE, pp. 374-379, 2016.
[19] Tuegel, E. J., Ingraffea, A. R., Eason, T. G., & Spottswood, S. M., “Reengineering aircraft structural life prediction using a digital twin.” International Journal of Aerospace Engineering, 2011.
[20] S. Bell, P. Upchurch, N. Snavely, and K. Bala, “Material recognition in the wild with the materials in context database.” arXiv:1412.0623, 2014.
[21] Y. Salih, A.S. Malik, “Depth and geometry from a single 2D image using triangulation.” IEEE International Conference on Multimedia and Expo Workshops, pp. 511–515, 2012.