臺灣博碩士論文加值系統

台灣兩大石化業者分別成立大數據中心及人工智慧與工業 4.0 研發中心，新製造業與 AI 在石化業龍頭間，相繼擠身人工智慧世界潮流中，對台灣石化業起了帶頭作用。但是石化業邁向工業4.0時，究竟應該在那些方面先期作好規劃與佈署。
國內有學者運用網絡實體系統 (CPS, Cyber-Physical System) 規劃建立石化業關鍵設備健康預測模型，然而，經過透過大數據工具完成建模之後，雖然獲得十分準確的預測成效，但是在探求進一步的詳細故障原因探尋時發現，完全無法繼續失效原因分析的進行，因為空有歷史數據的限制很大，故作者深入該研究的建模發展，並且比對近期研究網絡實體系統(CPS)建置的文獻，經過前期在石化業智慧診斷的研究，再透過整理與國內製造業成功發展或進階工業4.0的企業經驗，歸納本研究的結論。
本研究發現：一、新製造新文化：AI與其說是技術革命，更像是文化革命，AI 比的是學習力，主動學習、主動了解及主動解決問題，首要工作就是建立新文化，培養員工好奇心與鼓勵主動冒險精神，並從容忍錯誤中學習。二、大數據分析：大數據分析的基礎都是專業領域知識 (Domain Knowledge)對領域充分理解，才知道需要那些數據? 三、數據收集及數據品質：製造商與維修廠商必須在硬體與軟體上，對大數據進行收集、前處理與保存，所以多數業者與廠商合約需要進行修正。數據品質亦需要完整非斷斷片片，才有分析利用價值，包括完善正確的維修保養及製程資料，否則沒有完整的數據及履歷，數據沒有分析方向目標，當然不會有結果。四、完整資料庫：雲端只是一個平台，雲端要有其他社群，其他石化廠及自廠資料庫，數據才會夠多，分析才會夠精準，需要建置完整資料庫的 AI，對進一步分析比對，才有意義。
結果期望可以提供國內石化業者認清方向，進而思考改善作法，除了落實製程安全管理提升國際競爭力，更應該先從整體企業文化來改造。本研究亦可提供勞動檢查單位對製程安全管理更深入的認知，引導石化業者提升自動檢查及自主管理能力。

Two major petrochemical companies in Taiwan established Big Data Center, Artificial Intelligent and Industrial 4.0 Research Center respectively and emerged into the big tide of AI as the leaders in Taiwan. They are a leader in the field of artificial intelligence and have played a leading role in the petrochemical industry in Taiwan. However, the petrochemical industry hopes to follow the manufacturing industry's success in moving towards Industry 4.0. What is the most important issue?
Some domestic scholars use the Network Physics System (CPS) program to establish key equipment health prediction models for the petrochemical industry. However, after modeling with big data tools, although very accurate predictions were obtained, further research is being sought. When the detailed cause of the fault was found, it was found that it was impossible to continue analyzing the cause of the fault, because the historical data was too restrictive, so the author deeply studied the modeling development of the fault. Research and comparison of recent research on CPS. The literature summarizes the second phase of the study, and at the same time summarizes the relevant content as the conclusion of this report by collating and interviewing several authoritative individuals who have successfully developed Industry 4.0 in the domestic manufacturing industry.
We conclude the following findings from our preliminary study: First, the new manufacturing of new culture: AI is not so much a technological revolution, more like a cultural revolution, AI is more than learning, active learning, active understanding and proactive problem solving, the priority is to establish a new culture and cultivate employees Curiosity and encourage active adventure and learn from tolerance errors. Second, big data analysis: The basis of big data analysis is the domain knowledge (Domain Knowledge) fully understands the field, only to know which data is needed? Third, data collection and data quality: manufacturers and maintenance vendors must be in hardware and software, Also, the collection, pre-processing and preservation of big data, so most industry and manufacturer contracts need to be revised. Data quality also requires complete non-disruptive film, only to analyze the value of use, including the improvement of correct maintenance and process data, otherwise, there is no complete data and resume, the data does not analyze the direction of the target, of course, there will be no results. Fourth, the complete database: the cloud is just a platform, the cloud must have other communities, other petrochemical plants, and self-factory database, the data will be enough, the analysis will be accurate enough, you need to build a complete database of AI, to further It makes sense to analyze the comparison.

目 錄
圖目錄 V
表目錄 VI
一、緒論 7
1.1 研究背景與動機 7
1.2 研究目的 8
二、文獻探討 10
2.1 工業4.0與石化業製程安全 10
2.2 預知維護保養 14
2.3 工業大數據與資料品質 18
2.4 領域專有知識 (DOMAIN KNOWLEDGE) 24
2.5 網絡實體系統(CPS) 26
2.6 工業4.0企業文化改變 29
三、歸納整理 33
3.1 企業文化 33
3.2 資料意涵掌握 35
3.3 資料完整程度 36
3.4 數據品質維護 37
四、研究與討論 40
4.1 新製造新文化的革命 40
4.2 資料隱匿性 (BELOW SURFACE) 的探求 41
4.3 數據碎片化 (BROKEN) 的避免 42
4.4 資料低質性 (BAD QUALITY) 的回復 42
五、結論與建議 44
參考文獻 46

Bayoumi, A., McCaslin, R. (2017) Internet of Things – A Predictive Maintenance Tool for General Machinery, Petrochemicals and Water Treatment. In: Bahei-El-Din Y., Hassan M. (eds) Advanced Technologies for Sustainable Systems. Lecture Notes in Networks and Systems, vol 4. Springer, Cham.
Beyer, K, et al.1999. When is “nearest neighbor” meaningful? In: International conference on database theory; 217-35.
Bloch, H. P. and F. K. Geitner. (1997) Major Process Equipment Maintenance and Repair. 2nd. Ed., Pratical Machinery Management for Process Plants, Vol. 4, Gulf Publishing Company.
BSI (2016). Petroleum, petrochemical and natural gas industries —Collection and exchange of reliability and maintenance data for equipment (ISO 14224). British Standard.
Burges, Christopher JC. 1998.A tutorial on support vector machines for pattern recognition. Data mining and knowledge discovery ; 2.2: 121-67.
Cao, L., Xia, Y., Wang, J., Zheng, G., Shen, Y., & Shan, T., (2017, July). Aviation bearing fault diagnosis method based on CHSMM. In Prognostics and System Health Management Conference (PHM-Harbin), 2017 (pp. 1-5).
Charles Becht &Larry Lester(2018): Petroleum and Process Industry Best Practices in Maintenance & Reliability. Becht Engineering. http://www.thequakergroup.com
Chebel-Morello, B., J.-M. Nicod and C. Varnier. (2017) From Prognostics and Health Systems Management to Predictive Maintenance, Mechanical Engineering and Solid Mechanics Series- Reliability of Multiphysical Systems Set, Vol. 7, John Wiley.
Chen, Y. (2017). Data Quality Assessment Methodology for Improved Prognostics Modeling. The University of Cincinnati , the degree of Doctor of Philosophy In the School of Dynamic Systems of the College of Engineering and Applied Science, Ohio, United States. Retrieved from:https://etd.ohiolink.edu/pg_10?0::NO:10:P10_ACCESSION_NUM:ucin1330024393
Cheng, H., Zeng, P., Xue, L., Shi, Z., Wang, P., & Yu, H. (2016). Manufacturing Ontology Development Based on Industry 4.0 Demonstration Production Line. 2016 Third International Conference on Trustworthy Systems and Their Applications (TSA), 42–47.
Devezas, T., J. Leitao and A. Sarygulov. (2017) Industry 4.0 Entrepreneurship and Structural Change in the New Digital Landscape. Springer.
Erol, S., Jäger, A., Hold, P., Ott, K., & Sihn, W. (2016). Tangible Industry 4.0: A Scenario-Based Approach to Learning for the Future of Production. Procedia CIRP, 54, 13–18. DOI:10.1016/j.procir.2016.03.162
Frank, A. G., Dalenogare, L. S., & Ayala, N. F. (2019). Industry 4.0 technologies: Implementation patterns in manufacturing companies. International Journal of Production Economics, 210, 15–26. https://doi.org/10.1016/j.ijpe.2019.01.004
Hegde, G.P., M. Seetha, N. Hegde. (2016) Kernel Locality Preserving Symmetrical Weighted Fisher Discriminant Analysis based subspace approach for expression recognition. Engineering Science and Technology, an International Journal, Vol 19, Iss 3, Pp 1321-1333 doi.org/10.1016/j.jestch.2016.03.005
Gilchrist, A. (2016) Industry 4.0, The Industrial Internet of Things..
Gorecky, D., Schmitt, M., Loskyll, M., & Zuhlke, D. (2014). Human-machine-interaction in the industry 4.0 era. 2014 12th IEEE International Conference on Industrial Informatics (INDIN), 289–294. DOI:10.1109/INDIN.2014.6945523
Hermann, M., Pentek, T., & Otto, B. (2015). Design Principles for Industries 4.0 Scenarios: A Literature Review. Working Paper· January 2015. DOI: 10.13140/RG.2.2.29269.22248
Haiyang, Z., Jindong, W., Lee, J., & Ying, L. (2018). A compound interpolation envelope local mean decomposition and its application for fault diagnosis of reciprocating compressors. Mechanical Systems And Signal Processing, 110, 273-295. D.O.I.10.1016/j.ymssp.2018.03.035
Hashemian, H. M. (2008) Predictive Maintenance of Critical Equipment in Industrial Processes, Lamar University Press.
Jia, X., Jin, C., Buzza, M., Di, Y., Siegel, D., & Lee, J. (2018). A deviation based assessment methodology for multiple machine health patterns classification and fault detection. Mechanical Systems And Signal Processing, 99, 244-261. doi.org/10.1016/j.ymssp.2017.06.015
Kiel, D., Müller, J. M., Arnold, C., & Voigt, K.-I. (2017). SUSTAINABLE INDUSTRIAL VALUE CREATION: BENEFITS AND CHALLENGES OF INDUSTRY 4.0. International Journal of Innovation Management, 21(08), 1740015.DOI: 10.1142/S1363919617400151
Lee J, Hossein Davari, Jaskaran Singh, Vibhor Pandhare.2018.Industrial Artificial Intelligence for industry 4.0-based manufacturing systems, Manufacturing Letters, 18, 20-23. DOI: 10.1016/j.mfglet.2018.09.002
Lee, J., Ardakani, H., Yang, S., & Bagheri, B. (2015). Industrial Big Data Analytics and Cyber-physical Systems for Future Maintenance & Service Innovation. Procedia CIRP, 38, 3-7. doi.org/10.1016/j.procir.2015.08.026
Lee, J., Kao, H., & Yang, S. (2014). Service Innovation and Smart Analytics for Industry 4.0 and Big Data Environment. Procedia CIRP, 16, 3-8. DOI: 10.1016/j.procir.2014.02.001
Lee, J., Bagheru, B. & KAO, H.-A. (2015). A Cyber Physical Systems Architecture for Industry 4.0-based Manufacturing Systems. Manufacturing Letters Volume 3, January 2015, Pages 18-23, doi.org/10.1016/j.mfglet.2014.12.001
Lee, J., Wu, F., Zhao, W., Ggaffari, M., Liao, L. & Siegel, D. (2014). Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications. Mechanical Systems and Signal Processing, 42, 314-334. doi.org/10.1016/j.ymssp.2013.06.004
Lian, J., & Zhao, R. (2017). Fault diagnosis model based on NRS and EEMD for rolling-element bearing. In Prognostics and System Health Management Conference (PHM-Harbin), 2017(pp. 1-5).
Luo, S., Chu, V. W., Zhou, J., Chen, F., Wong, R. K., & Huang, W. (2017). A Multivariate Clustering Approach for Infrastructure Failure Predictions. In Big Data (BigData Congress), 2017 IEEE International Congress on (pp. 274-281).
Mika S, et al. (1999). Fisher discriminant analysis with kernels. In: Neural Networks for Signal Processing IX; 41-8. DOI: 10.1109/NNSP.1999.788121
Mounce, S. R. Ellis, K. Edwards, J. M. Speight, V. L. Jakomis, N. Boxall, J. B. (2017). Ensemble Decision Tree Models Using RUSBoost for Estimating Risk of Iron Failure in Drinking Water Distribution Systems. Water Resources Management, v. 31 Issue 5, p1575, 15 p. doi: 10.1007/s11269-017-1595-8
Natalia P, Colthurst T, Gilbert H, Salem H, Soroush R. 2017.Compact multi-class boosted trees. (2017) IEEE International Conference on Big Data (Big Data), 2017 IEEE International Conference on. :47-56, arXiv:1710.11547
Negandhi, V., L. Sreenivasan, R. Giffen, M. Sewak and A. Rajasekharan. (2015) IBM Predictive Maintenance and Quality 2.0 Technical Overview, Redbooks Publisher.
Nolan, F. and H. Heap. (1979) Reliability Centered Maintenance, National Technical Information Service Report, # A066-579.
Northerton, D. (2000) “RCM Standard” Maintenance & Asset Management, 15, 12-20.
Opitz, D., & Maclin, R. (1999). Popular Ensemble Methods: An Empirical Study. Journal of Artificial Intelligence Research, 11, 169–198. doi.org/10.1613/jair.614
Rato, T.J., & Reis, M.S. (2017). Multiresolution Soft Sensors: A New Class of Model Structures for Handling Multiresolution Data, Ind. Eng. Chem. Res., 56(13), pp. 3640-3654. DOI:10.1021/acs.iecr.6b04349
Reis, M.S., & Gins, G. (2017). Industrial Process Monitoring in the Big Data/Industry 4.0 Era: From Detection, to Diagnosis, to Prognosis. Processes, 5(35), pp. 1-16. DOI: 10.3390/pr5030035
Roderic DM. (2001). TreeView. Glasgow University, Glasgow, UK.
Sankavaram, C., Kodali, A., Pattipati, K. R., & Singh, S. (2015). Incremental classifiers for data-driven fault diagnosis applied to automotive systems. IEEE Access, 3, 407-419.
Scheffer, C. and P. Girdhar. (2004) Practical Machinery Vibration Analysis & Predictive Maintenance, Elsevier.
Sherwin, D. (2000) “A Review of Overall Models for Maintenance Management” Journal of Quality in Maintenance Engineering, 6, 138-64.
Sanders, A., Elangeswaran, C., & Wulfsberg, J. (2016). Industry 4.0 implies lean manufacturing: Research activities in industry 4.0 function as enablers for lean manufacturing. Journal of Industrial Engineering and Management, 9(3), 811.DOI: 10.3926/jiem.1940
Sun, J., Yan, C., & Wen, J. (2017). Intelligent Bearing Fault Diagnosis Method Combining Compressed Data Acquisition and Deep Learning, IEEE Transactions on Instrumentation and Measurement, DOI: 10.1109/TIM.2017.2759418.
Thomas H.-J. Uhlemann(2017).The Digital Twin: Realizing the Cyber-Physical Production System for Industry 4.0. Procedia CIRP.Vol 61, 2017, Pages 335-340. doi.org/10.1016/j.procir.2016.11.152
TOMAK, Özgür、KAYIKÇIOǦLU, T. (2018). Bagged tree classification of arrhythmia using wavelets for denoising, compression, and feature extraction. Turkish Journal of Electrical Engineering & Computer Sciences. 2018, Vol. 26 Issue 3, p1555-1571. 17p. doi:10.3906/elk-1706-247
Valdez, A. C., Brauner, P., Schaar, A. K., Holzinger, A., & Ziefle, M. (2015). Reducing Complexity with Simplicity - Usability Methods for Industry 4.0. IEA 2015, At Melbourne, Australia, Volume: 19. DOI: 10.13140/RG.2.1.4253.6809.
Venkatasubramanian, V., Rengaswamy, R., Yin, K., & Ka, S. N. (2003). A review of process fault detection and diagnosis Part I: Quantitative model-based methods. Computers and Chemical Engineering, 19.
Wang, J., Sun, C., Zhao, Z., & Chen, X. (2017). Feature ensemble learning using stacked denoising autoencoders for induction motor fault diagnosis. In Prognostics and System Health Management Conference (PHM-Harbin), 2017 (pp. 1-6).
Wagner, T., Herrmann, C., & Thiede, S. (2017). Industry 4.0 Impacts on Lean Production Systems. Procedia CIRP, 63, 125–131.DOI: 10.1016/j.procir.2017.02.041
Xu, X., Yan, X., Sheng, C., Yuan, C., Xu, D., & Yang, J. (2017). A Belief Rule-Based Expert System for Fault Diagnosis of Marine Diesel Engines. IEEE Transactions on Systems, Man, and Cybernetics: Systems.
Zhang, Boyu, Qin, A. K,Sellis, Timos. (2018) Evolutionary feature subspaces generation for ensemble classification. Genetic & Evolutionary Computation Conference; p577-584, 8p. doi:10.1145/3205455.3205638
李傑，(2016) 工業大數據：工業 4.0 時代的智慧轉型與價值創新，天下雜誌出版社。
李傑，(2017)From BigData to Intelligent Manufacturing and Service Innovation，前程文化。
李傑，(2019) 工業人工智慧，前程文化出版社。
行政院，(2015) 中華民國104年施政年鑑：104年行政院重要施政方針及施政成果，中華民國行政院出版。
美國通用電氣公司 (GE)，(2016)，工業互聯網：打破智慧與機器的邊界，機械工業出版社。
陳兆裕，(2016) “台灣石化產業對經濟的貢獻”，科學發展，9月，525期，48 ~ 54頁。
郭至恩，張純明，高振山，許世希，陳振和，蔡瑜潔，梁勝富，(2018) 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 26: 1, 2018.03，頁1-8。
郭至恩，沈育霖，曹常成，張純明，高振山，許世希，邱俊憲，陳振和，蔡瑜潔，梁勝富，(2018) 應用於石化業關鍵設備之集成式智慧預知維護系統，勞動及職業安全衛生研究季刊，26:3 2018.09，頁141-150。
范振誠、林國權、陳育誠、陳明君、張怡雯、楊思亮、蕭亞漩(2017)，2017石化產業年鑑。
簡禎富(2019) ，工業3.5：台灣企業邁向智慧製造與數位決策的戰略，天下雜誌出版社。
勤業眾信，(2018)，智慧製造大解讀專題。
鐘偉珏(2017),工業4.0與豐田生產系統對三重底線永續發展之影響與分析,國立臺灣大學商學研究所碩士論文，台灣台北。