銑削加工是機械製造領域中常見的加工方法之一，其中銑削刀具的磨耗情況會對金屬機械加工成品精度與良率造成重大影響，而汰換磨耗刀具成為業者維持加工成品品質的重要方針，然刀具的汰換策略需評估磨損狀況與刀具壽命分類而訂定。故本研究期能從國際標準組織所訂定之磨耗機制做以規範，發展出客觀且標準化的壽命分類準則，進而能夠提供加工業者包含磨耗樣態與磨耗數值等輔助決策指標的壽命分級模型。
有鑒於四刃端銑刀為機加工廠最常用的銑削刀具，因此本研究將著重在四刃端銑刀做為主要研究物件。本研究將延續先前所架設的光學檢測設備，優化其演算法及硬體系統，以期能達到更高系統解析度和自動化之需求，並加以分析刀具上所存在的磨耗樣態與系統重建之拓樸圖關聯，將量化出的磨耗特徵交由監督式機器學習模型進行多類別分類訓練，模型最終分類結果得以用於輔助判斷刀具壽命分級，利於機加工業決策者能應用此技術取代原先以人工檢測判讀、依循師傅經驗法則等，此類缺乏客觀的量化標準的壽命分級方式。

Milling process is one of the common processing methods in mechanical manufacturing industry. The tool wear of milling tools causes a significant impact on the accuracy and yield of metal machining products. In the case replacing worn tools has become one of the companies’ decisions to maintain the quality in finished products. However, the strategy of tool replacement needs to be determined with reference to the evaluation of the wear level. It will directly affect milling tool life. Therefore, in this research, the wear mechanism and standards should follow the rules of International Standards Organization. Develop scientifically defined quantitative classification standards, and provide processing industry classification models including wear patterns and wear values and other decision-making indicators.
In view of the fact that the four-flute end mill is the most commonly used for milling in machining factories, so this research will focus on the four-flute end mill as the main research object. This research will take over the automated optical inspection system which set up previously. To optimize the algorithm and hardware system, in order to achieve higher system resolution and rapid inspection requirements. Analyze the different wear patterns and condition value on the tools. The analysis feature will feed the supervised machine learning model for doing multicategory tool life classification. So that the decision makers in the machine processing industry can apply this quantitative classification model replacing the original manual detection and judgment which is depend on the master’s personal judgement. Develop an objective quantified standard life grading method to milling cutter.

[1] H. Shahabi and 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, vol. 40, no. 11, pp. 1148-1157, 2009.
[2] F. W. Taylor, On the art of cutting metals. American society of mechanical engineers, 1906.
[3] L. ENDMILL-WOTEK Precision Tools Co., "Introduction, features and types of solid end mills," 2020.
[4] Wikipidia,"Cutter_Types_(Mill), resource from http://mindworks.shoutwiki.com/w iki/Cutter_Types_(Mill)," ed. JNKVV Jabalpur, Aug. 9, 2019.
[5] E. P. DeGarmo, J. T. Black, R. A. Kohser, and B. E. Klamecki, Materials and process in manufacturing. Prentice Hall Upper Saddle River, 1997.
[6] I. S. Organization(ISO), "Tool Life Testing in Milling—Part2: End Milling," pp. 8688-2, 1989.
[7] M. A. Kuttolamadom, M. Laine Mears, and T. R. Kurfess, "On the volumetric assessment of tool wear in machining inserts with complex geometries—part 1: need, methodology, and standardization," Journal of manufacturing science and engineering, vol. 134, no. 5, 2012.
[8] G. Byrne, D. Dornfeld, I. Inasaki, G. Ketteler, W. König, and R. Teti, "Tool condition monitoring (TCM)—the status of research and industrial application," CIRP annals, vol. 44, no. 2, pp. 541-567, 1995.
[9] A. Siddhpura and R. Paurobally, "A review of flank wear prediction methods for tool condition monitoring in a turning process," The International Journal of Advanced Manufacturing Technology, vol. 65, no. 1-4, pp. 371-393, 2013.
[10] William. EBERT, "Heavy equipment proximity sensor," U.S. Patent Application, no 12/925,506, 2012.
[11] S. Kurada and C. Bradley, "A review of machine vision sensors for tool condition monitoring," Computers in industry, vol. 34, no. 1, pp. 55-72, 1997.
[12] S. Jetley, "Applications of surface activation in metal cutting," in Proceedings of the Twenty-Fifth International Machine Tool Design and Research Conference, 1985.
[13] Y. Yeşin and Z. Özel, "A study of cutting tool wear by neutron activation technique," Journal of radioanalytical and nuclear chemistry, vol. 99, no. 2, pp. 441-445, 1986.
[14] M. Szydłowski, B. Powałka, M. Matuszak, and P. Kochmański, "Machine vision micro-milling tool wear inspection by image reconstruction and light reflectance," Precision Engineering, vol. 44, pp. 236-244, 2016.
[15] M. Sukeri, M. Zulhilmi Paiz Ismadi, A. Rahim Othman, and S. Kamaruddin, "Wear Detection of Drill Bit by Image-based Technique," in IOP Conference Series: Materials Science and Engineering, 2018.
[16] D. Kong, Y. Chen, and N. Li, "Force-based tool wear estimation for milling process using Gaussian mixture hidden Markov models," The International Journal of Advanced Manufacturing Technology, vol. 92, no. 5-8, pp. 2853-2865, 2017.
[17] B. Sick, "On-line and indirect tool wear monitoring in turning with artificial neural networks: a review of more than a decade of research," Mechanical systems and signal processing, vol. 16, no. 4, pp. 487-546, 2002.
[18] M. Ahmad, M. Z. Nuawi, S. Abdullah, Z. Wahid, Z. Karim, and M. Dirhamsyah, "Development of tool wear machining monitoring using novel statistical analysis method, I-kaz™," Procedia Engineering, vol. 101, pp. 355-362, 2015.
[19] E. Haddadi, M. R Shabgha, and M. M Ettefag, "Effect of different tool edge conditions on wear detection by vibration spectrum analysis in turning operation," Journal of Applied Sciences, vol. 8, no. 21, pp. 3879-3886, 2008.
[20] C. Ai, Y. Sun, G. He, X. Ze, W. Li, and K. Mao, "The milling tool wear monitoring using the acoustic spectrum," The International Journal of Advanced Manufacturing Technology, vol. 61, no. 5-8, pp. 457-463, 2012.
[21] F. Klocke, B. Döbbeler, T. Pullen, and T. Bergs, "Acoustic emission signal source separation for a flank wear estimation of drilling tools," Procedia CIRP, vol. 79, pp. 57-62, 2019.
[22] M. Malekian, S. S. Park, and M. B. Jun, "Tool wear monitoring of micro-milling operations," Journal of Materials Processing Technology, vol. 209, no. 10, pp. 4903-4914, 2009.
[23] P. Prickett and C. Johns, "An overview of approaches to end milling tool monitoring," International Journal of Machine Tools and Manufacture, vol. 39, no. 1, pp. 105-122, 1999.
[24] C. Zhang and J. Zhang, "On-line tool wear measurement for ball-end milling cutter based on machine vision," Computers in industry, vol. 64, no. 6, pp. 708-719, 2013.
[25] S. Ravikumar, K. Ramachandran, and V. Sugumaran, "Machine learning approach for automated visual inspection of machine components," Expert systems with applications, vol. 38, no. 4, pp. 3260-3266, 2011.
[26] W. Wang, Y. Wong, and G. S. Hong, "Flank wear measurement by successive image analysis," Computers in Industry, vol. 56, no. 8-9, pp. 816-830, 2005.
[27] J. Su, C. Huang, and Y. Tarng, "An automated flank wear measurement of microdrills using machine vision," Journal of Materials Processing Technology, vol. 180, no. 1-3, pp. 328-335, 2006.
[28] K. N. Prasad and B. Ramamoorthy, "Tool wear evaluation by stereo vision and prediction by artificial neural network," Journal of Materials Processing Technology, vol. 112, no. 1, pp. 43-52, 2001.
[29] S. Zhang, High-resolution, real-time 3-D shape measurement. State University of New York at Stony Brook, 2005.
[30] S. Wei, S. Wang, C. Zhou, K. Liu, and X. Fan, "Binocular vision measurement using Dammann grating," Applied Optics, vol. 54, no. 11, pp. 3246-3251, 2015.
[31] W. Wang, Y. Wong, and G. Hong, "3D measurement of crater wear by phase shifting method," Wear, vol. 261, no. 2, pp. 164-171, 2006.
[32] M. T. García-Ordás, E. Alegre, V. González-Castro, and R. Alaiz-Rodríguez, "A computer vision approach to analyze and classify tool wear level in milling processes using shape descriptors and machine learning techniques," The International Journal of Advanced Manufacturing Technology, vol. 90, no. 5-8, pp. 1947-1961, 2017.
[33] X. Wu, Y. Liu, X. Zhou, and A. Mou, "Automatic Identification of Tool Wear Based on Convolutional Neural Network in Face Milling Process," Sensors, vol. 19, no. 18, p. 3817, 2019.
[34] D. M. D’Addona, A. S. Ullah, and D. Matarazzo, "Tool-wear prediction and pattern-recognition using artificial neural network and DNA-based computing," Journal of Intelligent Manufacturing, vol. 28, no. 6, pp. 1285-1301, 2017.
[35] WRIGHT, Raymond E, "Logistic regression," 1995.
[36] X. Yin, J. Goudriaan, E. A. Lantinga, J. Vos, and H. J. Spiertz, "A flexible sigmoid function of determinate growth," Annals of botany, vol. 91, no. 3, pp. 361-371, 2003.
[37] S. R. Safavian and D. Landgrebe, "A survey of decision tree classifier methodology," IEEE transactions on systems, man, and cybernetics, vol. 21, no. 3, pp. 660-674, 1991.
[38] W. S. Noble, "What is a support vector machine?," Nature biotechnology, vol. 24, no. 12, pp. 1565-1567, 2006.
[39] T. G. Dietterich, "Ensemble methods in machine learning," in International workshop on multiple classifier systems, 2000.
[40] L. Breiman, "Bagging predictors," Machine learning, vol. 24, no. 2, pp. 123-140, 1996.
[41] M. Pal, "Random forest classifier for remote sensing classification," International journal of remote sensing, vol. 26, no. 1, pp. 217-222, 2005.
[42] R. E. Schapire, "The boosting approach to machine learning: An overview," Nonlinear estimation and classification, pp. 149-171, 2003.
[43] D. D. Margineantu and T. G. Dietterich, "Pruning adaptive boosting," in ICML, vol. 97: Citeseer, pp. 211-218, 1997.
[44] S. Džeroski and B. Ženko, "Is combining classifiers with stacking better than selecting the best one?," Machine learning, vol. 54, no. 3, pp. 255-273, 2004.
[45] 王鴻鈞, "應用三維機械視覺於端銑刀磨耗檢測系統," 碩士論文, 動力機械工程學系, 國立清華大學, 新竹市, 2018.
[46] 莊于萱, "端銑刀磨耗定量檢測系統," 碩士論文, 動力機械工程學系, 國立清華大學, 新竹市, 2019.
[47] 林于翔, "端銑刀磨耗樣態分類系統." 碩士論文, 動力機械工程學系, 國立清華大學, 新竹市, 2020.
[48] Y. Jung, "Multiple predicting K-fold cross-validation for model selection," Journal of Nonparametric Statistics, vol. 30, no. 1, pp. 197-215, 2018.