博碩士論文 etd-0610119-072717 詳細資訊


[回到前頁查詢結果 | 重新搜尋]

姓名 陳震宇(Jenn-Yeu Chen) 電子郵件信箱 E-mail 資料不公開
畢業系所 管理學院高階經營碩士學程在職專班(College of Management (Executive Master in Business Administration))
畢業學位 碩士(Master) 畢業時期 107學年第2學期
論文名稱(中) 應用智慧診斷技術於煉油廠關鍵設備操作監控之研究
論文名稱(英) Using Smart Diagnostic Technology to Monitor Operations of Critical Equipments in Refinery
檔案
  • etd-0610119-072717.pdf
  • 本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。
    請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
    論文使用權限

    紙本論文:1 年後公開 (2020-07-10 公開)

    電子論文:使用者自訂權限:校內 3 年後、校外 3 年後公開

    論文語文/頁數 中文/89
    統計 本論文已被瀏覽 18 次,被下載 0 次
    摘要(中) 石油煉製業關鍵設備之關鍵製程變數須被充分監控或控制,一旦發生異常可能會使設備損壞機制的速率受到影響,導致失控損壞,而工廠員工操作往往因為沒有遵守程序、技術能力斷層、溝通和交流不良、疲勞、交接班不清楚、操作人力配備不足、工場操作警報氾濫等原因,未能及時發覺製程異常或處置程序錯誤,從而造成重大製程事故。
    本研究以煉油廠試點工場之動態與靜態關鍵設備為例,藉著收集與分析歷史操作數據,將設備之關鍵變數之操作數據導入指數平滑法,發展一套操作趨勢預測模式,並利用該關鍵設備之製程異常的歷史操作數據資料,使用貝葉斯網路模型的條件依賴性分析、靈敏度分析,進行相關變數與關鍵變數間影響性分析及處置步驟分析,避免人因失效造成工場操作的安全漏洞。
    綜合本研究估算結果、建模複雜度及未來適用性等因素,通過簡約原則,找出二級指數單參數平滑法,做為本研究關鍵變數操作趨勢預測模式; 在影響性分析研究中發現不論是動態設備或靜態設備,以貝葉斯網路法可進行變數特徵篩選,可找出每次發生製程偏移時,與關鍵變數最相關的變數,在研究過程中發現造成每次偏移的原因不同,各變數對關鍵變數影響最大的變數並不相同,各變數對於關鍵變數之影響力亦會隨時間滾動變化,設備發生異常期間,不易以專家領域知識判斷系統所有變數的因果關係,本研究所提出的方法提供了一個更有說服力的因果推理過程,有助於煉油廠領域的管理者,了解設備異常的發生原因,提早提出因應之道。
    摘要(英) The key process variables of critical equipments in the petroleum refining industry shall be fully monitored or controlled. Once an abnormality occurs, the rates of equipment damage mechanisms may be affected, resulting in a loss of control. A major hazard accident occurs often due to the operator/ operators failure to comply with procedures, technical capabilities fault, the communication failure, fatigue, unclear handover, lack of manpower for operation, operation alarms flooding, failure to track the process operation condition, taking the wrong coutermeasures, etc..
    This study takes the rotating and static critical equipments of the pilot unit in refinery as an example. To develop a trend prediction model for the key process variable, the historical operational data of the critical equipment were fed into the exponential smoothing method. The condition-dependent analysis and sensitivity analysis of Bayesian Network methodology is presented to analyze the dependency between the relevant variables and key process variable, and the disposal steps during an abnormal event in order to prevent any safety holes in the workplace caused by human error.
    Based on the estimation, modeling complexity, applicability in future and through the Parsimony Principle, One-parameter double exponential smoothing with forecasting model for key variable is identified to achieve the best accuracy. No matter the dynamic or static equipments in this study, Bayesian network method allows variables feature screening to verify the most related variables to the key variables when every offset occured. The study also find the causes of each offset may be different and the variables that have the greatest influence on the key variables my not be the same. The influence of each variable on the key variables will also change over time. During the abnormal operation period of the equipment, it is not easy to judge the causal relationship of all variables in the system only by the expert domain knowledge. The proposed method in this study provides a more convincing process of causal reasoning. It will help the management in refinery to understand the causes of equipment anomalies and undertake the response in advance.
    關鍵字(中)
  • 人因失效
  • 二級指數平滑
  • 關鍵設備
  • 貝葉斯網路
  • 關鍵變數
  • 關鍵字(英)
  • Key Process Variable
  • Double Exponential Smoothing Method
  • Human Error
  • Bayesian Networks
  • Critical Equipments
  • 論文目次 目錄
    論文審定書……………………………………………………………………………. i
    誌謝…………………………………………………………………………………… ii
    摘要…………………………………………………………………………………… iii
    Abstract………………………………………………………..………………..…….. iv
    目錄…………………………………………………………………………………… v
    圖次…………………………………………………………………………………… vi
    表次…………………………………………………………………………………… ix
    第一章 緒論……………………………………………………….……………........ 1
    第一節 研究背景與動機………………………………………………............. 1
    第二節 研究目的………………………………………………………………. 3
    第三節 研究流程………………………………………………………….……. 4
    第四節 研究範圍與限制……………………………………………………….. 5
    第二章 文獻探討…………………….………………………………………….…… 7
    第一節 建立關鍵變數操作趨勢預測模式………………………………….…. 7
    第二節 變數影響性分析…………………………………………………….… 13
    第三章 研究設計………………………………………………………………….... 16
    第一節 研究結構……………………………………………………………… 16
    第二節 研究範圍……………………………………………………………… 17
    第三節 製程與數據收集……………………………………………………… 18
    第四節 研究模式建構………………………………………………………… 22
    第四章 研究結果與分析…………………………………………………………… 29
    第一節 建立關鍵變數操作趨勢預測模式研究……………………………… 29
    第二節 建立關鍵操作變數與相關操作變數影響性分析研究……………… 39
    第三節 變數處置步驟分析研究……………………………………………… 66
    第五章 結論與建議………………………………………………………………… 72
    第一節 結論與建議…………………………………………………………… 72
    第二節 管理意涵……………………………………………………………… 75
    參考文獻…………………………………………………………………………….… 77
    參考文獻 一、中文
    呂守陞,2015,"失誤數轉化貝氏網路模式之建構及其應用於橋樑風險評估之研究" Journal of the Chinese Institute and Hydraulic 
       Enhineering, Vol.27, No.1, pp.11-22。
    郭至恩、張純明、高振山、許世希、陳振和、蔡瑜潔、梁勝富,2017,"先期開發與評估應用於石化業關鍵設備之智慧預知維護方法" 勞動及職業安全衛生研究季刊 民國107年3月 第26卷第1期,第1-8頁.
    二、英文
    Bobbo A., L. Portinale, M. Minichino, E. Ciancamerla, 2001. "Improving the Analysis of Dependable Ssytems by Mapping Fault Trees into Bayesian Networks" J. Reliability Engineering and SYSTEM Saety, 71, pp. 249-260.
    Ademola Ishola, Liverpool John Moores University, 2017. "Advanced Safety Methodology for Risk Management of Petroleum Refinery 
       Operations", Chapter 6.
    Bhandari, J., Abbassi, R., Garaniya, V. and Khan, F., 2015. "Risk Analysis of Deep water Drilling Operations Using Bayesian network" J.
       Loss Prevent. Proc., 38, pp. 11–23.
    Bruce L.Bowerman/ Richard T. O’connell, Miami University, Ohio "Forecasting and Time Series: An Approach Third Edition" Duxbury
       Press. Califoria, Chater 8.
    Cai, B., Liu, Y., Liu, Z., Tian, X., Zhang, Y., Ji, R., 2013a. "Application of Bayesian Networksin Quantitative Risk Assessment of Subsea
       Blowout Preventer Operations Risk Analysis ", 33 (7), pp. 1293–1311.
    Cai, B., Liu, Y., Zhang, Y., Fan, Q., Liu, Z., Tian, X., 2013b. "A Dynamic Bayesian Networks Modeling of Human Factors on Offshore
       Blowouts", Jounal Loss Prevent. Proc., 26, pp. 639–649.
    Cai, B., Liu, Y., Ma, Y., Liu, Z., Zhou, Y., Sun, J., 2015. "Real-time Reliability Evaluation Methodology Based on Dynamic Bayesian
       Networks: a case study of a subsea pipe ram BOP system" ISA T., 58, pp. 595–604.
    Cai, B., Liu, H., Xie, M., 2016. "A Real-time Fault Diagnosis Methodology of Complex Systems Using Object-oriented Bayesian
       Networks. "Mechical System Signal Process, 80, pp. 31–44.
    Cai, B., Huang, L., Xie, M., 2017a. "Bayesian Networks in Fault Diagnosis" IEEE Trans.Ind. Inf., 13 (5), pp. 2227–2240.
    Cai, B., Xie, M., Liu, Y., Liu, Y., Feng, Q., 2017b. "Availability Based Engineering Resilience Metric and Its Corresponding Evaluation
       Methodology" Reliability Engineering System Safety, 172, pp. 216–224.
    Darwiche, A., 2009. "Modeling and Reasoning with Bayesian Networks" Cambridge University Press, New York.
    Jensen, F.V., Nielsen, T.D., 2007. "Bayesian Networks and Decision Graphs", Second ed. Information Science and Statistics Springer.
    Junyan Zhang, Baoping Cai, Kabwe Mulenga, Yiliu Liu, Min Xie, 2018. "Bayesian Network Based Risk Analysis Methodology: A Case of
       Atmospheric and Vacuum Distillation Unit" Journal Process Safety and Environmental Protection, 117, pp. 660-674.
    HOU Dianguo, 2011. "Analysis on Causes of Scaling in Flue Gas Turbine of FCCU and Countermeasures" China Petroleum and
       Petrochemical Technology, 13, No.1, pp. 66-74.
    K.E. Hild, D. Erdogmus, J. Principe, 2001. "Blind source separation using Renyi's mutual information" IEEE, pp. 174-176.  
    "NIST/SEMATECH e-Handbook of Statistical Methods", NIST., 2010 May.
    Off-shore Installations (Safety Cases) Regulations 2015. No.298, Heath and Safety Environmental Pretection.
    Pearl, J., 1988. "Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference".
    Prajakta S. Kalekar, 2010. "Time series Forecasting using Holt-Winters Exponential Smoothing".
    Sun J, Yan C, Wen J., 2018. "Intelligent Bearing Fault Diagnosis Method Combining Compressed Data Acquisition and Deep Learning" IEEE Transactions on Instrumentation and Measurement, 67.1, pp. 185-195.
    Tukey, John (1977), Exploratory Data Analysis, Addison-Wesley.
    Zhang Q, et al., 2015. "Vibration Sensor Based Intelligent Fault Diagnosis System for Large Machine Unit in Petrochemical Industries",
       International Journal of Distributed Sensor Networks, Vol. 11:239405.
    Xin Zou, Wen Long Yue, 2017. "A Bayesian Network Approach to Causation Analysis of Road Accidents Using Netica" Joural of
       Advanced Transportation, Vol. 2017, Article ID. 2525481.
     
    三、網路
    Engineering Statistics Handbook, 2012, http://www.itl.nist.gov/div898/handbook/eda/section1/eda1.htm.
    HAL, 2010
    http://hal.archives-ouvertes.fr/hal-00546144.
    口試委員
  • 趙平宜 - 召集委員
  • 楊淯程 - 委員
  • 黃三益 - 指導教授
  • 口試日期 2019-06-19 繳交日期 2019-07-10

    [回到前頁查詢結果 | 重新搜尋]


    如有任何問題請與論文審查小組聯繫