銑削加工為機械製造加工上常見方法之一，然隨加工次數之增加，刀具磨耗區域逐漸擴大，是為影響加工業產品精度及良率之重要因素，儘管已有諸多研究提出不同刀具壽命預估模型來預估磨耗量，期望有助於產線上之刀具工序調整，並且利用國際標準組織訂定之磨耗機制與標準來做規範，卻受限於加工條件之不確定性，仍需倚靠直接之監測系統始能有效對不同磨耗類型採取應對措施。因此，為提出有效能量化磨耗程度之檢測方式，本研究將延續先前所架設之光學系統，透過機械視覺之方法進行磨耗量之分析，並主要從軟體端如邊緣計算、三維重建等演算法強化，以期能達到高準確度且快速完成檢測之需求，同時配合QRcode的使用，將刀具與檢測資料連結，欲打造智慧化檢測機台，以利資料之追蹤進而供與使用者採取相對應的配刀程序。

Milling operation plays an important role in industrial manufacturing process. Wear of the cutting tool is an inevitable result of the metal cutting process, and it will directly affect the quality and yield of products in the factory. In the past decades, there were already many researches providing the predictive models to predict wear region by mathematic formula. Even International Organization for Standardization (ISO) has defined types and standards of wear for us to categorize different wear types. However, due to the uncertainty during machining process, wear monitoring system is necessary to detect tool wear effectively. Therefore, in this thesis, I will work on improving the original machine vision system. Modify the contour profile extracted algorithm and precisely quantify wear level of milling cutter tool as the output computing results. Calibrate the hardware parts to make the whole inspection system become more robust, so as to efficiently match the requirement of practical inspection need. Furthermore, complete a proof of concept for combining the output data with QRcode on every milling cutter tool to realize the concept of Industry 4.0 on making a smart inspection machine.

中文摘要 ...........................................................i
英文摘要 ..........................................................ii
目錄 ................................................................iii
表目錄 .............................................................v
圖目錄 ............................................................vi
符號表 .............................................................x

第一章 緒論 .....................................................1
1.1 前言 .........................................................1
1.2 文獻回顧 ..................................................2
1.2.1 端銑刀類型 ......................................2
1.2.2 刀具磨耗機制 ..................................2
1.2.3 刀具磨耗檢測方法 ...........................5
1.2.4 市售刀具檢測產品 ..........................10
1.2.5 檢測數據聯網 .................................13
1.3 研究動機與目的 ......................................16

第二章 理論基礎 ............................................17
2.1 投影輪廓技術 ..........................................17
2.2 輪廓擷取 ................................................18
2.3 輪廓影像偏心校正 ..................................19
2.4 三維輪廓重建 .........................................20
2.5 刀具標籤與資料庫 ..................................22

第三章 系統規劃與實驗設計 ..........................24
3.1 硬體架構 .................................................25
3.2 軟體架構 .................................................27
3.3 刀具QR碼標籤與掃描 ..............................32

第四章 實驗結果與討論 .................................34
4.1 邊緣擷取 .................................................36
4.2 刀具前端輪廓處理 ...................................40
4.3 磨耗相關參數輸出 ...................................41
4.4 銑刀磨耗位置標示補助 ............................43
4.5 QR碼標籤與雲端資料庫連結之概念驗證 ..46
4.6 取像樣本數 ..............................................49
4.7 失效及磨耗刀具重建特徵分析 ..................52

第五章 結論 ....................................................64
第六章 未來展望 .............................................65

參考文獻 ................................................67

1. H. H. Shahabi, M. M. Ratnam, In-cycle monitoring of tool nose wear and surface roughness of turned parts using machine vision, The International Journal of Advanced Manufacturing Technology, February 2009, Volume 40, Issue 11–12, pp 1148–1157
2. S. Engin, Y. Altintas, Mechanics and dynamics of general milling cutters. Part I: helical end mills, International Journal of Machine Tools & Manufacture 41 (2001) 2195–2212
3. 維基百科，Cutter Types, 檢自: http://mindworks.shoutwiki.com/wiki/ Cutter_Types_(Mill) (Aug. 9, 2019)
4. N. Ghosh, et al., Estimation of tool wear during CNC milling using neural network-based sensor fusion, Mechanical Systems and Signal Processing 21 (2007) 466–479
5. 藍天雄，刀具磨耗考量下之數控車削參數最佳化研究，德霖學報「第二十一期」，民國九十六年六月
6. Organization(ISO), I.S., Tool Life Testing in Milling—Part 2: End Milling. 1989: p.8688-2
7. E.P. DeGarmo, et al., Materials and process in manufacturing. 1997: Prentice Hall.
8. P.W. Prickett, C. Johns, An overview of approaches to end milling tool monitoring, International Journal of Machine Tools & Manufacture 39 (1999) 105–122
9. F.W. Taylor, On the art of cutting metals, ASME, 1907. 28.
10. S. Kurada, C. Bradley, A review of machine vision sensors for tool condition monitoring, Computer in Industry, 34 (1997) 55-72
11. A. Weckenmann, K. Nalbantic, Precision measurement of cutting tools with two matched optical 3D-sensors, CIRP Ann.-Manuf. Technology 2003; 52(1):443–6.

12. J. Jurkovic, et al., New approach in tool wear measuring technique using CCD vision system, Int. J. Mach. Tools Manuf. 2005;45(9):1023–30.
13. A. Devillez, S. Lesko, W. Mozer, Cutting tool crater wear measurement with white light interferometry. Wear 2004; 256(1): 56 – 65.
14. M. Szydłowski, et al., Machine vision micro-milling tool wear inspection by image reconstruction and light reflectance, Precision Engineering 44 (2016) 236–244
15. M. Sukeri, et al., Wear Detection of Drill Bit by Image-based Technique, IOP Conf. Series: Materials Science and Engineering, 328(2018) 012011
16. D. M. D’Addona, R. Teti, Image data processing via neural networks for tool wear
prediction, Proced. CIRP 2013; 12:252–7.
17. B. Marek, et al., Tool condition monitoring using artificial intelligence methods, Engineering Applications of Artificial Intelligence 15 (2002) 73–80
18. Y. Dai, and K. Zhu, A machine vision system for micro-milling tool condition monitoring. Precision Engineering, 2018. 52: p. 183-191.
19. T. Goldschmidt, A. Jansen, H. Koziolek, J. Doppelhamer, H. P. Breivold, Scalability and Robustness of Time-Series Databases for Cloud-Native Monitoring of Industrial Processes, 2014 IEEE 7th International Conference on Cloud Computing
20. 林瑋琦(2011年), 德國「工業4.0」產業趨勢與衍生商機大揭密, 中華民國對外貿易發展協會
21. ZVEI (April, 2017), Guideline: What Criteria do Industrie 4.0 Products Need to Fulfil?, German Electrical and Electronic Manufactures’ Association
22. ZVEI (November, 2018), Details of the Asset Administration Shell, Part 1- The exchange of information between partners in the value chain of Industrie 4.0, Federal Ministry for Economic Affairs and Energy(BMWi)
23. X. Zhang, W. Tsang, X. Tian, K. Yamazaki, and M. Mori, Automatic Segmentation of the Apparent Contour for 3D Modeling of Cutting Tools from Single View, In: Bebis G. et al. (eds) Advances in Visual Computing. ISVC 2008. Lecture Notes in Computer Science, vol 5359. Springer, Berlin, Heidelberg
24. N. Otsu, A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics, 1979. 9(1): p. 62-66.
25. Jae S. Lim, Two-Dimensional Signal and Image Processing, Englewood Cliffs, NJ, Prentice Hall, 1990, p. 548, equations 9.26, 9.27, and 9.29.
26. 維基百科，QR碼，檢自https://zh.wikipedia.org/wiki/QR碼, 修訂於2019年6月24日(Jul. 2, 2019)
27. 科技網，360°應用—二維條碼4種規格 QR Code容量最大, 檢自https://www.digitimes.com.tw/tw/dt/n/shwnws.asp?id=61060 (Jul. 2, 2019)
28. AWS, 什麼是NoSQL?，檢自https://aws.amazon.com/tw/nosql/ (Jul.2, 2019)
29. taazaa, NoSQL or SQL – How to Choose the Best Fit for a Project, 檢自https://taazaa.com/nosql-or-sql-how-to-choose-the-best-fit-for-a-project/ (Jul. 2, 2019)
30. 王鴻鈞，應用三維機械視覺於端銑刀磨耗檢測系統，國立清華大學動力機械工程研究所，碩士論文，民國107年7月
31. 維基百科，MongoDB, 檢自https://zh.wikipedia.org/wiki/MongoDB (Jul.7, 2019)
32. W. H. Wang, G. S. Hong and Y. S. Wong, Flank wear measurement by a threshold independent method with sub-pixel accuracy, International Journal of Machine Tools & Manufacture 46 (2006) 199–207
33. M. K. Balasundaram, M. M. Ratnam, In-Process Measurement of Surface Roughness using Machine Vision with Sub-Pixel Edge Detection in Finish Turning, International Journal of Precision engineering and manufacturing, 2014. Vol. 15, No. 11, pp. 2239-2249
34. B. M. Kumar and M. M. Ratnam, Machine vision method for non-contact measurement of surface roughness of a rotating workpiece, Sensor Review, (2015) Vol. 35 No. 1, pp. 10-19