近年來製造業對於預測機械系統故障或刀具壽命之模型開發愈趨重視。過往刀具壽命預測模型以物理為基礎之方式建立，然而若欲推演出該系統解析解之數學模型，需要對目標系統進行深入的探討。但對複雜的製造系統而言，以物理為基礎建立適合的數學模型相當困難，因此有越來越多基於數據分析的預測模型被開發。
過往基於數據分析之刀具磨耗監測系統的研究中，是根據其所制定的切削條件建立刀具磨耗監控模型並進行辨識，對於此切削條件下之數據具有良好的辨識能力，但對於切削條件外的數據辨識能力卻鮮少著墨，如此一來監測模型的泛化性(generalization)便無法被驗證。本研究嘗試將特定切削條件下的所有數據排除於訓練數據集中，並做為測試樣本，測試模型之辨識率，藉此檢驗刀具磨耗監測模型之泛化性。
本研究利用主軸電流以及置於虎鉗上的加速規擷取之振動訊號，做為刀具磨耗狀態的對應特徵。主軸電流為機台本身的訊號來源，不需要額外的感測器，該訊號與刀具磨耗有高度正相關。而加速規安裝空間需求小、成本低，且有較高的信噪比(Signal-to-Noise ratio)，比切削力能更即時的監測刀具狀態的變化。本研究利用上述特徵建立機器學習模型以辨識刀具磨耗之狀態。當特定轉速數據排除於訓練數據集，對於該轉速數據的辨識準確率在類神經網路上很差。而經由前處理的改善並搭配隨機森林模型後，模型辨識準確率得以提升10%-20%。

In recent years, the manufacturing industry has paid more attention to the development of models for predicting mechanical system failure or tool life. In past tool life prediction model in milling was established in a physics-based manner. However, for complex manufacturing systems, it is quite difficult to build a suitable mathematical model so predictive models based on data analysis are being developed.
In this study, the spindle current and the vibration signal captured by the controller and the accelerometers placed on the vise are used as the corresponding features of the tool wear state. The spindle current is the signal source of the machine itself, so no additional sensors are needed. This signal is highly positively correlated with tool wear. Accelerometers are small, low cost, and a high signal-to-noise ratio, which can monitor the change of tool status more instantaneously than the cutting force. This study utilizes the above features to establish a machine learning model to identify the state of tool wear, then compare the identification results of the artificial neural network with the random forest model, and discuss the physical meaning behind the important features. The recognition rate of the random forest model is 10%-20% higher than that of the neural network.

目錄
口試委員會審定書 i
誌謝 ii
摘要 iii
Abstract iv
目錄 v
圖目錄 vii
表目錄 ix
第1章 緒論 1
1.1 研究背景 1
1.2 研究動機與目的 2
1.3 研究架構 4
第2章 文獻回顧 5
2.1 切削過程監控訊號源 5
2.2 刀具磨耗監控 8
2.3 小結 9
第3章 研究方法 10
3.1 研究架構 10
3.2 感測器裝設位置 11
3.3 訊號擷取理論-奈奎斯特定理(Nyquist Theorem) 14
3.4 訊號頻域轉換 15
3.5 訊號前處理 18
3.6 切削力與電流訊號之對應性 21
3.7 類神經網路 22
3.7.1 類神經網路概念(Artificial neural network) 22
3.7.2 類神經網路架構 23
3.8 隨機森林(Random forest) 26
3.8.1 隨機森林概念 26
3.8.2 CART決策樹 26
3.8.3 隨機森林架構 28
3.9 特徵選取 29
3.9.1 相關係數 29
3.9.2 隨機森林特徵選取 30
3.10 刀具磨耗量計算 31
第4章 實驗設備與規劃 33
4.1 實驗架構 33
4.2 實驗設備 34
4.3 實驗規劃 44
4.3.1 銑削實驗流程 44
4.3.2 訊號分析流程 46
第5章 實驗結果與討論 48
5.1 刀具磨耗分析 48
5.2 演算法辨識結果比較 50
5.2.1 Artificial Neural Network 50
5.2.2 Random Forest 57
5.2.3 特徵工程改善 64
5.2.4 驗證結果 76
5.3 特徵比較 77
5.3.1 特徵集合相關係數 77
5.3.2 重要特徵比較 79
第6章 結論與未來展望 83
6.1 總結 83
6.2 未來展望 84
參考文獻 85

[1] J. Corbett, R. A. McKeown, G. N. Peggs, and R. Whatmore, “Nanotechnology: International developments and emerging products,” CIRP Annals - Manufacturing Technology, pp. 523-545, 2000.
[2] L. Monostori, and H. Van Brussel, “Machine Learning Approaches to Manufacturing,” CIRP Annals, pp. 675-712, 1996.
[3] M.C.Shaw, “Metal cutting principles,” Oxford University Press, New York, 2005.
[4] J. S. Lemaster, “The use of process monitoring techniques on a CNC wood router. Part 1. Sensor selection,” Forest Products Journal, pp. pp.31-38, 2000.
[5] J. K. Tae-Yong Kim, “Adaptive cutting force control for a machining center by using indirect cutting force measurements,” International Journal of Machine Tools and Manufacture, pp. pp.925-937, 1996.
[6] K. Jemielniaka, and P.J. Arrazola, “Application of AE and cutting force signals in tool condition monitoring in micro-milling,” CIRP Journal of Manufacturing Science and Technology, pp. 97-102, 2008.
[7] Donertas, I. Korkut , “The influence of feed rate and cutting speed on the cutting forces, surface roughness and tool–chip contact length during face milling,” Materials & design, pp. 308-312, 2007.
[8] I. Tansel, M. Trujillo, A. Nedbouyan, C. Velez, W.-Y. Bao, T. Arkan, “Micro-end-milling—III. Wear estimation and tool breakage detection using acoustic emission signals,” International Journal of Machine Tools and Manufacture, pp. 1449-1466, 1998.
[9] M. Malekian, S. S. Park, and M. B. G. Jun, “Tool wear monitoring of micro-milling operations,” Journal of Materials Processing Technology, pp. 4903-4914, 2009.
[10] J. T. Roth, and S. M. Pandit, “Monitoring End-Mill Wear and Predicting Tool Failure Using Accelerometers,” Journal of Manufacturing Science and Engineering, pp. 559-567, 1999.
[11] J. Z. Zhang, and J. C. Chen, “Tool condition monitoring in an end-milling operation based on the vibration signal collected through a microcontroller-based data acquisition system,” International Journal of Advanced Manufacturing Technology, pp. 118-128, 2008.
[12] P. Lister, and D. Dimla, “On-line metal cutting tool condition monitoring.: I: force and vibration analyses,” International Journal of Machine Tools and Manufacture, pp. 739-768, 2000.
[13] J. C. Chen and W. L. Chen, “A tool breakage detection system using an accelerometer sensor,” Journal of Intelligent Manufacturing, pp. 187-197, 1999.
[14] M. Savage, J. Chen, “A fuzzy-net-based multilevel in-process surface roughness recognition system in milling operations,” The International Journal of Advanced Manufacturing Technology, pp. 670-676, 2001.
[15] B. Kilundu, and P. Dehombreux, “Tool wear monitoring by machine learning techniques and singular spectrum analysis,” Mechanical Systems and Signal Processing, pp. 400-415, 2011.
[16] F. Aghazadeh, A. Tahan,and M. Thomas, “Tool condition monitoring using spectral subtraction and convolutional neural networks in milling process,” The International Journal of Advanced Manufacturing Technology, 2018.
[17] P. Krishnakumar, K. Rameshkumar,and K. I. Ramachandran, “Tool Wear Condition Prediction Using Vibration Signals in High Speed Machining (HSM) of Titanium (Ti-6Al-4V) Alloy,” International Symposium on Big Data and Cloud Computing, pp. 270-275, 2015.
[18] 洪沛志, and 李貫銘, “銑削加工振動訊號與表面粗糙度之關聯性,” 碩士論文, 國立臺灣大學, 台北, 2018.
[19] 黃門, and 李貫銘, “以電流及振動訊號監測微銑削刀具磨耗之研究,” 碩士論文, 國立臺灣大學, 台北, 2017.
[20] J. W, Tukey, "An algorithm for the machine calculation of complex Fourier series," Mathematics of computation, pp. 297-301, 1965.
[21] 邱雅琳, and 李貫銘, “等切削力控制系統動態特性建立之研究,” 碩士論文, 國立臺灣大學, 台北, 2017.
[22] D. E. Hinkle, W. Wiersma, and S. G. Jurs, “Applied Statistics for the Behavioral Sciences,” 5th ed., Houghton Mifflin, 2003.
[23] 周士嚴, “微量潤滑應用於微銑削之研究,” pp. 24-26, 2009.
[24] D. Dornfeld, M. F. DeVries, “Neural Network Sensor Fusion for Tool Condition Monitoring,” CIRP Annals, pp. 101-105, 1990.
[25] Dazhong Wu, “A Comparative Study on Machine Learning Algorithms for Smart Manufacturing: Tool Wear Prediction Using Random Forests,” Journal of Manufacturing Science and Engineering, pp. 1-8, 2017.
[26] N. Author, “awesome-machine-learning,” 05 11 2018. [線上]. Available: https://github.com/jacksu/machine-learning/blob/master/awesome.md. [存取日期: 25 12 2018].