簡易檢索 / 詳目顯示

研究生: 黃子維
Tzu-Wei Huang
論文名稱: 具使用情境參數的動態BIM之巨量資料分析應用實例
Application Case of Big Data Analysis on Dynamic BIMs with Parameters for Use Scenarios
指導教授: 陳鴻銘
Hung-Ming Chen
口試委員: 呂守陞
Sou-Sen Leu
謝佑明
Yo-Ming Hsieh
學位類別: 碩士
Master
系所名稱: 工程學院 - 營建工程系
Department of Civil and Construction Engineering
論文出版年: 2016
畢業學年度: 104
語文別: 中文
論文頁數: 109
中文關鍵詞: 建築資訊模型雲端運算巨量資料分析資料探勘MapReduce
外文關鍵詞: BIM, Cloud Computing, Big data analysis, Data Mining, MapReduce
相關次數: 點閱:296下載:5
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
  • 本研究基於一雲端化資料儲存與管理系統,採用巨量儲存技術與分散式技術對巨量之BIM資料進行處理,並採用資料探勘之技術,使此雲端系統具備巨量資料分析之功能。傳統BIM中僅包括靜態資料,如幾何參數、物理性質、和空間關係,多屬於物理空間模型。而在本研究中BIM延伸至動態BIM,其中動態BIM中包括了動態資料,其中諸如設施環境與使用狀態之監測歷史記錄,以及持續觀察使用者與建築的互動情況等,透過上述收集而來的資料,進而取得使用者之經驗參數,使BIM變成為一個具經驗參數化的模型。
    對於動態BIM的巨量資料分析應用,本研究基於一具備雲端儲存與管理系統中,提出採用MapReduce分散式運算的巨量資料預處理框架,並整合資料探勘工具R語言於預處理後,對巨量資料進行分析,本研究提出模擬案例,對所提出之系統基於室內環境與能源消耗的狀態下來進行預測人數,使用之模型為各種資料探勘的方法,如關聯規則、分類分群、迴歸分析、以及預測的組合,從預測之結果進行驗證,並依此案例操作流程證實動態BIM之巨量資料分析之可行性,


    In this study, a Cloud-based BIM system which can store and manage massive BIMs online was utilized and integrated with data mining technology for perform-ing big data analysis online. Traditional BIM includes only static information, such as the geometric parameters, physical properties, and spatial relations, for model-ing of the physical space. In this study, BIM was extended to dynamic BIM which also includes dynamic data, such as historical records from the monitoring of the facility environment and usage, as well as the user experience parameters from continuous observation of the interaction between users and the space. Regarding the applications of dynamic BIM big data, this study proposed a big data prepro-cessing framework based on the MapReduce distributed computing for the data of massive BIMs stored in the Cloud-based BIM system. R were integrated into the system as the data mining tools to analyze the data after preprocessing. In a case study, the proposed system was applied to find hidden dependencies in the pro-cessed data sets for estimating the number of people in a facility based on the state of the indoor environment and energy consumption. The model developed is a combination of various data mining methods including association rules, classifi-cation and clustering, regression analysis, and prediction. The estimation results were verified and analyzed in this study. The case study shows the feasibility for performing big data analysis on dynamic BIMs.

    論文摘要 IV ABSTRACT VI 誌謝 VIII 目錄 X 圖表索引 XIV 第一章 緒論 1 1.1 研究動機與背景 1 1.2 研究目的 6 1.3 研究範圍 8 1.4 研究方法 9 1.5 論文架構 10 第二章 文獻回顧 11 2.1 相關研究發展 11 2.1.1 BIM 11 2.1.2 資料探勘 12 2.1.3 巨量資料分析 15 2.2 系統開發技術 17 2.2.1 巨量資料儲存技術 17 2.2.1.1 Apache Hadoop 17 2.2.1.2 Apache HBase 19 2.2.2 巨量資料分析技術 20 2.2.2.1 MapReduce 20 2.2.3 資料探勘工具 21 2.2.3.1 R語言 21 2.2.4 EnergyPlus 22 2.3 系統開發工具 24 2.3.1 Java 24 2.3.2 HTML 25 2.3.3 PHP 26 第三章 系統功能分析與規劃 27 3.1 客戶端介面模組 27 3.1.1 動態資料上傳模組 28 3.1.2 探勘結果存取模組 29 3.2伺服器端運算模組 30 3.2.1 匯出分析檔案模組 30 3.2.2 資料探勘功能模組 31 第四章 系統架構與運作機制 33 4.1系統架構 33 4.1.1 基於Cloud BIM網頁平台擴充之網頁架構 34 4.1.2 HBase資料儲存架構 35 4.2 動態資料上傳運作機制 37 4.3 匯出分析檔案運作機制 38 4.4 巨量資料分析 41 4.4.1 資料探勘前處理 41 4.4.2 資料探勘 42 4.5 分析結果存取運作機制 47 4.6 探勘系統運作機制 48 4.6.1 資料探勘模組運作機制 49 第五章 巨量分析應用實例 51 5.1 BIM專案資訊 51 5.2 分析資料 52 5.2.1 資料收集範圍 52 5.2.2 資料來源 54 5.3 探勘模型 59 5.3.1 分析流程 60 5.3.1.1 關聯模型 61 5.3.1.2 分類分群模組 61 5.3.1.3 迴歸模型 61 5.4 模型建立過程 62 5.4.1 模型輸入輸出 62 5.4.2 資料探勘方法 63 5.4.3.1 方法之參數設定 64 5.4.3.2 方法結果之呈現 68 5.5 分析結果 82 5.5.1 室內人數預測模型(手動分類) 83 5.5.2 室內人數預測模型(K-Means分群) 85 5.5.3 室內人數預測模型(迴歸與其他AI方法比較) 87 第六章 結論與未來展望 91 6.1 結論 91 6.2未來展望 92 參考文獻 93

    [1] 郭榮欽,〈BIM全方位服務優化營建效能〉,《營建知訊》第353期:P.20-27 (2012)。
    [2] National Institute of Standards and Technology (NIST), [Online], Available: http://www.nist.gov/index.html
    [3] 林宗禧,「Cloud BIM: 應用雲端運算與WebGL技術之網路式BIM系統」,碩士論文,國立臺灣科技大學,臺北 (2012)。
    [4] 張凱筌,「雲端化之巨量BIM資料儲存與分析系統架構」,碩士論文,國立臺灣科技大學,臺北 (2014)。
    [5] 洪智國,「具使用情境參數的動態BIM之巨量資料分析架構與應用」,碩士論文,國立臺灣科技大學,臺北 (2014)。
    [6] National Institute of Building Sciences, Charter for the National Building In-formation Model (BIM) Standard Project of the buildingSMARTalliance, The National Building Information Model Standard, WA (2008).
    [7] Popov, V., Juocevicius, V., Migilinskas, D., Ustinovichius, L. and Mikalauskas, S., “The Use of A Virtual Building Design and Construction Model for Devel-oping An Effective Project Concept in 5D Environment”, Automation in Con-struction, Vol. 19, Issue 3, pp. 357-367 (2010).
    [8] Goedert, J.D., and Meadati, P., “Integrating construction process documentation into building information modeling”, Journal of Construction Engineering and Management, ASCE, Vol. 134, No. 7, pp. 509-516 (2008).

    [9] Lin, S.-H., Kensek, K. and Haymond, L., “Analytical Building Information Modeling: What is the Gap Between BIM and Energy Simulation Tools’ Per-formance Feedback Loops?”, Proceedings of Ecobuild 2010Ecobuild 2010, Washiton, DC, USA. (2010).
    [10] Kim, H., and Anderson, K., “Energy modeling system using building infor-mation modeling open standards”, Journal of Computing in Civil Engineering, ASCE, Vol. 27, No. 3, pp. 203-211 (2013).
    [11] Berry, M.J.A. and Linoff, G., “Data Mining Technique for Marketing,” Sale, and
    Customer Support, Wiley Computer (1997).
    [12]Cabena, P., Hadjinian, P., Stadler, R., Verhees, J. and Zanasi, A., “Discovering Data Mining From Concept to Implementation,” Prentice-Hall Inc, (1997).
    [13]Fayyad, U.,Piatetsky-Shapiro, G.,and Smyth, P., “The KDD Process for Extracting Useful Knowledge from Volumes of Data,” Communications of the ACM, 39(11), pp.29 (1996)
    [14] Yakushev, A. and Mityagin, S., “Social Networks Mining for Analysis and Modeling Drugs Usage”, Procedia Computer Science, Vol. 29, pp. 2462-2471 (2014).
    [15] J.-H. Chen and J.-Z. Lin, “Developing an svm based risk hedging prediction model for construction material suppliers,” Automation in Construction, vol. 19, no. 6, pp. 702–708 (2010).
    [16] 黃怡華,「應用類神經網路與關聯法則於銀行消費性貸款」,碩士論文,國立成功大學,台南(2004)
    [17] 黃世承,「資料探勘在颱風降雨量與風速預測上之應用」,碩士論文,國立中央大學,桃園(2002)

    [18] Doug Laney , “3D Data Management: Controlling Data Volume, Velocity, and Variety. ” META group Inc. (2001)
    [19] Laney, Douglas. “The Importance of ‘Big Data’: A Definition”. Gartner. Re-trieved 21 June (2012)
    [20] Isabelle Claverie-Berge, “Solutions Big Data IBM”,(2012)
    [21] Singh, K., Guntuku, S. C., Thakur, A. and Hota, C., “Big Data Analytics framework for Peer-to-Peer Botnet detection using Random Forests”, Infor-mation Sciences, Vol. 278, pp. 488-497 (2014).
    [22] Apache™ Hadoop, [Online], Available: http://hadoop.apache.org/ (2015).
    [23] Apache™ Hive, [Online], Available: http://hive.apache.org/ (2015).
    [24] Apache™ Mahout, [Online], Available: https://mahout.apache.org/ (2015).
    [25] Ackermann, K. and Angus, S. D., “A Resource Efficient Big Data Analysis Method for the Social Sciences: the case of global IP activity”, Procedia Com-puter Science, Vol. 29, pp. 2360-2369 (2014).
    [26] Steed, C. A., Ricciuto, D. M., Shipman, G., Smith, B., Thornton, P.E., Wang, D., Shi, X. and Williams, D. N., “Big data visual analytics for exploratory earth system simulation analysis”, Computer & Geosciences, Vol. 61, pp. 71-82 (2013).
    [27] Cohen, J., Dolan, B., Dunlap, M., Hellerstein, J. M. and Welton, C., “MAD Skills: New Analysis Practices for Big Data”, Proceedings of the VLDB En-dowment, Vol. 2, No. 2, pp. 1481-1492 (2009).
    [28] 李永仁,「應用iBeacon定位技術結合巨量資料分析於購物推薦服務」,碩士論文,國立臺北科技大學,臺北(2015)
    [29] Apache™ HBase, [Online], Available: http://hbase.apache.org/ (2015).
    [30] Apache™ MapReduce, [Online], Available:
    http://hadoop.apache.org/docs/r1.2.1/mapred_tutorial.html (2015).
    [31] EnergyPlus, [Online], Available: http://apps1.eere.energy.gov/buildings/energyplus/ (2015).
    [32] The R Project for Statistical Computing, [Online], Available:
    http://www.r-project.org/ (2015).
    [33] Google Inc., [Online], Available: http://www.google.com/ (2015).
    [34] HDFS Architecture, [Online], Available: http://hadoop.apache.org/common/docs/r0.18.3/images/hdfsarchitecture.gif
    [35] HDFS Datanodes, [Online], Available: http://hadoop.apache.org/common/docs/r0.18.3/images/hdfsdatanodes.gif
    [36] Introduction to Hadoop << Trifork Blog / Trifork: Enterprise Java, Open Source, software solutions, [Online], Avaliable: http://blog.trifork.com/2009/08/04/introduction-to-hadoop (2009).
    [37] 陳景祥,R軟體應用統計方法,東華書局,臺北,第3頁 (2015)。
    [38] Building Technologies Office: EnergyPlus Energy Simulation Software, [Online],Avaliable:http://apps1.eere.energy.gov/buildings/energyplus/?utm_sour-ce=EnergyPlus&;utm_medium=redirect&;utm_campaign=EnergyPlus%2Bredirect%2B1 (2014).
    [39] Java, [Online], Available:
    http://www.oracle.com/technetwork/java/index.html (2015).
    [40] HTML語法教學, [Online], Available: http://www.powmo.com/ (2014).
    [41] PHP, [Online], Available: https://www.php.net/ (2015).
    [42]PHP: 序言 - Manual, [Online], Avaliable:
    http://php.net/manual/zh/preface.php (2010).
    [43] PHP: PHP Usage Stats, [Online], Avaliable: http://php.net/usage.php (2013).
    [44] 維基百科四分位數,[Online], Avaliable:
    https://zh.wikipe dia.org/wiki/%E5%9B%9B%E5%88%86%E4%BD%8D%E6%95%B0 (2016)
    [45]黃文、王正林,利用R語言打通大數據的經脈,佳魁資訊,臺北(2015)
    [46]張云濤、龔玲,資料探勘原理與技術,五南圖書出版股份有限公司,臺北(2007)
    [47]廖述賢、溫志皓,資料採礦與商業智慧,雙葉書廊有限公司,臺北(2009)

    QR CODE