鑽孔為加工過程中生產線最常見的加工形態，在過程中一旦刀具磨損嚴重或產生斷刀情況時，會使得不良品產出率增加，甚而迫使機台停機干擾生產線整體運作，造成工廠嚴重損失。為避免上述情況發生，有效監控刀具磨耗狀況對於加工生產而言極為重要。
因此本研究開發出一套運用數位影像處理方法的鑽削刀自動化檢測系統，該系統除了可求得磨耗率外，更利用數位影像處理之特性，使得檢測流程可以非接觸的方式運行，大幅提升檢測的安全性。本研究之檢測系統使用C#語言開發，並以數位單眼拍攝刀具實際影像進行實驗測試。
研究過程首先檢測上刀過程是否有夾持異常發生，確認鑽削刀無夾持異常問題之後再進行加工。加工結束後便立即對刀具執行磨耗率檢測，確認磨耗率是否超過換刀的停用值以決定刀具的更換與否。除了開發磨耗率檢測系統之外，本研究亦建置鑽削刀磨耗率管制圖系統，以統計品管的七大手法之一的管制圖計算鑽削刀磨耗率提醒值。
研究結果顯示，本研究的檢測系統可以有效的判斷鑽削刀是否有夾持異常情況發生，也能夠計算出鑽削刀的磨耗率，並計算出合理的鑽削刀磨耗率提醒值，給予正確的處理建議。
本研究發展出電腦與工具機之連線自動化功能，讓檢測系統能夠在加工過程結束後會自動啟動並檢測鑽削刀磨耗率，達成自動檢測鑽削刀之目的。此實驗以webcam做為實驗設備。

In this study, an automatic inspection system inspecting wear rate of drilling tool is developed to maintain the production process in good situation and to reduce defective products by making the right decision in different wear conditions. The inspection system of digital image process is developed with C# programming language. Digital single-lens reflex camera is used in the system to take picture. Before machining, the position of drilling tool would be inspected to make sure there is no holding abnormal. After machining, the inspection system is executed to measure wear rate of drilling tool instantly. If its wear rate does not exceed wear rate disable value (WRD), the drilling tool could be kept using in machining; otherwise, the drilling tool should be changed immediately. A wear rate control chart is also developed in this study to calculate wear rate reminded value (WRR). Along with the inspection system, an automatic connection system between computer and machining machine is designed. With such connection system, the inspection will start automatically from taking pictures to obtaining wear rate.

[1] 黃耀賢，主軸震動與聲射訊號於微銑刀具磨浩監測之應用研究，國立中興大學機械工程研究所碩士論文，2010。
[2] 謝秉澂，“端銑刀具端面刀腹磨耗自動檢測技術”，Retrieved from: http://aoiea.itri.org.tw/files/columnist/20160108135529918152/file/1/08.pdf。
[3] Byrne, G., et al. "Tool condition monitoring (TCM)—the status of research and industrial application." CIRP Annals-Manufacturing Technology 44.2 (1995): 541-567.
[4] Dan, Li, and Joseph Mathew. "Tool wear and failure monitoring techniques for turning—a review." International Journal of Machine Tools and Manufacture 30.4 (1990): 579-598.
[5] Dutta, S., et al. "Application of digital image processing in tool condition monitoring: A review." CIRP Journal of Manufacturing Science and Technology 6.3 (2013): 212-232.
[6] Byrne, G., et al. "Tool condition monitoring (TCM)—the status of research and industrial application." CIRP Annals-Manufacturing Technology 44.2 (1995): 541-567.
[7] Dimla, Dimla E. "Sensor signals for tool-wear monitoring in metal cutting operations—a review of methods." International Journal of Machine Tools and Manufacture 40.8 (2000): 1073-1098.
[8] Prickett, P. W., and C. Johns. "An overview of approaches to end milling tool monitoring." International Journal of Machine Tools and Manufacture 39.1 (1999): 105-122.
[9] Akbari, Ali Akbar, Amin Milani Fard, and Amir Goodarzvand Chegini. "An effective image based surface roughness estimation approach using neural network." Automation Congress, 2006. WAC'06. World. IEEE, 2006.
[10] Inoue, Shinichiro, Masami Konishi, and Jun Imai. "Surface defect inspection of a cutting tool by image processing with neural networks." Mem Fac Eng—Okayama Univ 43 (2009): 55-60.
[11] Palani, S., and U. Natarajan. "Prediction of surface roughness in CNC end milling by machine vision system using artificial neural network based on 2D Fourier transform." The International Journal of Advanced Manufacturing Technology 54.9-12 (2011): 1033-1042.
[12] Prasad, K. Niranjan, and B. Ramamoorthy. "Tool wear evaluation by stereo vision and prediction by artificial neural network." Journal of Materials Processing Technology 112.1 (2001): 43-52.
[13] Zhang, Chen, and Jilin Zhang. "On-line tool wear measurement for ball-end milling cutter based on machine vision." Computers in industry 64.6 (2013): 708-719.
[14] Otsu, Nobuyuki. "A threshold selection method from gray-level histograms." Automatica 11.285-296 (1975): 23-27.
[15] Gonzalez, Rafael C., and Richard E. Woods. "Digital image processing." Nueva Jersey (2008).
[16] 潘嘉偉，變焦測深技術的應用，國立中山大學機械工程學系研究所碩士論文，2000。
[17] 劉育至、吳培輔、喻子賢，自動對焦與測探之設計，逢甲大學自動控制工程學系專題論文。
[18] Heckbert, Paul S. "A seed fill algorithm." Graphics gems. Academic Press Professional, Inc., 1990..
[19] J. R. Shaw, “QuickFill: An efficient flood fill algorithm,” http://www.codeprojectcom/gdi/QuickFill.asp.
[20] L. Vandevenne, “Lode’s computer graphics tutorial, flood fill,” http://student.kuleuven.be/~m0216922/CG/floodfill.html.
[21] Chauhan, Ajay Pal Singh, and Sharat Chandra Bhardwaj. "Inspection of bare PCB defects by image subtraction method using machine vision." Proceedings of the World Congress on Engineering. Vol. 2. 2011.
[22] Sun, Yung-Nien, and Ching-Tsorng Tsai. "A new model-based approach for industrial visual inspection." Pattern Recognition 25.11 (1992): 1327-1336.
[23] Wu, Wen-Yen, Mao-Jiun J. Wang, and Chih-Ming Liu. "Automated inspection of printed circuit boards through machine vision." Computers in industry 28.2 (1996): 103-111.
[24] Mandel, B. J. "The regression control chart." Journal of Quality Technology 1.1 (1969): 1-9.
[25] 葉書華，以機器視覺無追刀具磨耗偵測系統開發，義守大學工業工程與管理學系研究所碩士論文，2008。
[26] Tu, Jack V. "Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes." Journal of clinical epidemiology 49.11 (1996): 1225-1231.
[27] Snee, Ronald D. "Impact of Six Sigma on quality engineering." Quality Engineering 12.3 (2000): 9-14.
[28] Cha, Sung-Hyuk. "Comprehensive survey on distance/similarity measures between probability density functions." City 1.2 (2007): 1.
[29] Montgomery, Douglas C. Introduction to statistical quality control. John Wiley & Sons, 2007.