工業物聯網（Industrial Internet of Things, IIoT）是使用物聯網技術來增強製造和工業流程。IIoT 也稱為工業互聯網或工業4.0，它結合了機器學習和深度學習的大數據技術，以利用在工業環境中存在的傳感器多年的數據，設備通訊機器對機器（M2M）與自動化技術。希望建立開放工業通訊標準，使方便開發支援系統程式設計語言與網路上任何控制器、驅動器、人機介面及其他裝置通訊。

本研究，重點不只是在工業4.0選擇何種IIoT通訊協定，而是使用者須正確了解本身的應用與這些協定的差別，選擇最適合組織應用的OPC UA開放工業通訊標準協定符合IEC62541標準規範，包括端對端(END-TO-END)資料傳輸安全及研製工業物聯網平台(Platform for Industrial Internet of Things, PIIoT)會使用Python跟Java程式語言開發，結合Web應用框架Django、JQuery UI、RWD響應式UX介面，以工業4.0假說模擬環境設備參數資料跟連接NoSQL的MongoDB關聯式資料庫即時和歷史資料運用，進行彙整計量分析數據透過2家公司實際個案，S公司電鍍機台資訊跟E公司焚化爐處理流程，使用Python機器學習Scikit-learn跟深度學習TensorFlow+Keras人工智慧輔助預測設備保養、稼動率、自動化橋接不同設備資料來源移轉，並著手PIIoT系統備援、風險管理網路安全性跟系統負載Crash問題。最後研究透過免費開放資源設計OPC UA工業通訊協定跟Python程式語言套用機器學習與深度學習的工業物聯網平台，在客製化、擴展性、彈性、系統建製花費、資料保密安全性會比現有付費工業物聯網平台具有免費自主開發技術架構優勢，以達到生產製造流程優化跟成本減少的一個工業4.0開放工業物聯網平台(Open Platform for Industrial Internet of Things, OPIIoT)。

To choose an appropriate Industrial Internet of Things (IIoT) communication protocol in the age of Industry 4.0, the users must correctly understand the differences between the application to be developed and the successful and practical examples. In this study, we choose the OPC UA open industrial communication standard protocol that is most suitable for organizational applications in accordance with the IEC62541 standard specification, including (END-TO-END) data transmission security. We use Python and Java to develop the Platform for Industrial Internet of Things (PIIoT), and integrate the platform with the web application framework Django, JQuery UI, and RWD responsive UX Interface. In addition, we adopt the Industry 4.0 hypothesis to simulate the data of environmental equipment parameters, connect the NoSQL MongoDB relational database and historical data in real time, and analyze the data from two companies as case studies. The cases are mainly to deal with the S company's plating machine information and the E company's incinerator processing operations. In the experiments, we use the Python machine learning tool Scikit-learn and the deep learning frameworks TensorFlow and Keras to solve the relevant problems of PIIoT system backup, system load crash, and risk management network security. In summary, this work adopts the free open resources, OPC UA, machine learning tool, and deep learning platform to design and implement an industry 4.0 open industry platform of things (Open Platform for Industrial Internet of Things, OPIIoT) to achieve manufacturing process optimization and cost reduction.

論文審定書 i
誌　謝 ii
摘　要 iii
Abstract iv
目　錄 v
圖目錄 vii
表目錄 xi
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究架構及流程 3
1.3 論文貢獻 4
第二章 文獻探討 5
2.1 工業4.0與工業物聯網運用說明 5
2.2 工業物聯網通訊協定選擇問題 9
2.3 選擇工業物聯網自動化通訊協定OPC UA 12
2.4 物聯網平台選擇問題 21
2.5 工業物聯網平台Python設計製作法 23
第三章 研究方法 26
3.1開放工業物聯網平台(OPIIoT)系統架構圖建置週期說明 26
3.2 工業物聯網通訊協定比較分析表 32
3.3 物聯網平台功能比較分析表 33
3.4 以Python工業物聯網建置OPC UA通訊協定 39
3.5 以Python工業物聯網設計連接設備 43
3.6 以Python連接NoSQL跟SQL資料庫的模擬設備環境參數 48
3.7 以2家公司個案Python機器學習與深度學習工業物聯網平台 50
3.8 以Python設計Web物聯網平台方法 70
3.9 工業物聯網平台負載與網路通訊安全性 72
第四章 研製結果分析 73
4.1工業物聯網平台M2M橋接ERP、MES系統資料庫 74
4.2實作OPIIoT開放工業物聯網平台的工業4.0 78
4.3 工業物聯網平台網路安全性跟系統穩定性負載測試 91
第五章 結論與未來研究 94
參考文獻 96
附錄一 100
附錄二 112
附錄三 115
附錄四 119

[1] Hermann, M., Pentek, T., & Otto, B. (2016, January). Design principles for industrie 4.0 scenarios. In 2016 49th Hawaii International Conference on System Sciences (HICSS) (pp. 3928-3937). IEEE.
[2] Böhler, T. M. (2012). Industrie 4.0–smarte produkte und fabriken revolutionieren die industrie. Produktion Magazin, 10.
[3] 柯燿興, 陳柄佑, 吳年欽, & 吳金能. (2016). 具國際共通標準之工具機產線可視覺化系統. 電腦與通訊, 69-79.
[4] Schweichhart, K. (2016). Reference architectural model industrie 4.0 (rami 4.0). An Introduction. Available online: https://www. plattform-i40. de I, 40.
[5] Serpanos, D., & Wolf, M. (2018). Industrial internet of things. In Internet-of-Things (IoT) Systems (pp. 37-54). Springer, Cham.
[6] Dimitris, M., Ekaterini, V., & Zogopoulos, V. (2018). An iot-based platform for automated customized shopping in distributed environments. Procedia CIRP, 72, 892-897.
[7] Alexopoulos, K., Makris, S., Xanthakis, V., Sipsas, K., & Chryssolouris, G. (2016). A concept for context-aware computing in manufacturing: the white goods case. International Journal of Computer Integrated Manufacturing, 29(8), 839-849.
[8] Radanliev, P., De Roure, D. C., Nicolescu, R., Huth, M., Montalvo, R. M., Cannady, S., & Burnap, P. (2018). Future developments in cyber risk assessment for the internet of things. Computers in Industry, 102, 14-22.
[9] Nicola, Sanna. (2016). What Is a Cyber Value-at-Risk Model?, https://www.fairinstitute.org/blog/what-is-a-cyber-value-at-risk-model.
[10] Lee, J., Bagheri, B., & Kao, H. A. (2015). A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manufacturing letters, 3, 18-23.
[11] OPC Foundation. (2020). https://opcfoundation.org/.
[12] O'Hara, J. (2007). Toward a commodity enterprise middleware. Queue, 5(4), 48-55.
[13] McAteer, I. N., Malik, M. I., Baig, Z., & Hannay, P. (2017). Security vulnerabilities and cyber threat analysis of the AMQP protocol for the internet of things.
[14] Standard, O. A. S. I. S. (2014). MQTT version 3.1. 1. URL http://docs. oasis-open. org/mqtt/mqtt/v3, 1.
[15] Andy, S., Rahardjo, B., & Hanindhito, B. (2017, September). Attack scenarios and security analysis of MQTT communication protocol in IoT system. In 2017 4th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI) (pp. 1-6). IEEE.
[16] Fielding, R. T. (2000). REST: architectural styles and the design of network-based software architectures. Doctoral dissertation, University of California.
[17] Vijayaraghavan, A., Sobel, W., Fox, A., Dornfeld, D., & Warndorf, P. (2008). Improving machine tool interoperability using standardized interface protocols: MT connect.
[18] MTConnect Institute. (2020). https://www.mtconnect.org/ .
[19] Sanner, M. F. (1999). Python: a programming language for software integration and development. J Mol Graph Model, 17(1), 57-61.
[20] Python Language Guide (v1.0). (2012-11-30) Google Documents List Data API v1.0. Google.
[21] Django Software Foundation. (2020). Django (web framework), https://www.djangoproject.com/ .
[22] Mozilla, MDN web docs, Django. (2020). https://developer.mozilla.org/en-US/docs/Learn/Server-side/.
[23] 機器學習：使用Python. (2020). https://machine-learning-python.kspax.io/.
[24] Keras 中文文档. (2020). https://keras.io/zh/.
[25] Industry 4.0_RUs, Point Of View Industry IoT ( IIoT ). (2018) .https://giant18jet.wordpress.com/2018/09/03/2018工業物聯網平台5大廠商/.
[26] MBAlib百科. Forrester Research公司. (2020). https://wiki.mbalib.com/zh-tw/Forrester_Research.
[27] Commons, C. (2009). Creative Commons. Attribution-ShareAlike 3.0 Unported. CC BY-SA, 3.
[28] 邱宗皓. (2014). 下一個 big thing 張忠謀: 物聯網, 中國時報.
[29] 涂志豪. (2018). 賽靈思新發表「Everest」ACAP平台 採台積電7奈米製程, 中國時報.
[30] Kan, C., Yang, H., & Kumara, S. (2018). Parallel computing and network analytics for fast Industrial Internet-of-Things (IIoT) machine information processing and condition monitoring. Journal of manufacturing systems, 46, 282-293.
[31] Ray, P. P. (2018). A survey on Internet of Things architectures. Journal of King Saud University-Computer and Information Sciences, 30(3), 291-319.
[32] MongoDB. (2020). This tutorial is intended as an introduction to working with MongoDB and PyMongo. http://api.mongodb.com/python/current/tutorial.html.
[33] Microsoft . (2018).適用於 Microsoft SQL 資料庫的連線模組，https://docs.microsoft.com/zh-tw/sql/connect/sql-connection-libraries?view=sql-server-2017#anchor-20-drivers-relational-access.
[34] HslCommunication. (2020). PLC Communication Driver, https://github.com/dathlin/HslCommunication.
[35] GDPR, EU GDPR.ORG. (2020). https://eugdpr.org/.
[36] Binary Ninja API, Source code. (2020) .http://api.binary.ninja/_modules/binaryninja/function.html.
[37] Python OPC-UA, Documentation. (2020). https://python-opcua.readthedocs.io/en/latest/.
[38] Kepware. (2020). OPC Server. https://www.kepware.com/en-us/.