微加工為製造尺寸從數十微米到數毫米的微型裝置或零件的製造方法。然而，基於感測、通訊、與計算能力的智慧製造應用於微加工製程仍存有下列議題須研究: (1) 多感測訊號的記錄與同步；(2) 微小訊號的特徵萃取；和(3) 不同目標的狀態估測等。本研究提出一適於微加工產業的精度與磨耗預測機制，包含基於事件導向製程監視與回溯模組、錯誤樹診斷方法、全自動虛擬量測系統、與混合動態神經網路模組等。
在應用結果上，本機制所提出的多感測訊號同步控制能力，可於7 ms內識別出刀具與工件異常碰撞，並於25 ms內停止機台進給，從而避免機台受損。而在微小訊號的特徵處理結合加工精度的預測上，藉由小波濾波器加上振動感測特徵，透過全自動虛擬量測系統，可提供毫米等級的微加工精度估測。最後，在刀具的磨耗估測上，本機制可藉由主軸與伺服馬達的電流感測特徵，透過動態類神經網路模組，提供等同使用其他感測器 (如測力計)的磨耗估測能力。總之，本研究結合感測特徵與預測模型的方案實具有實施的可行性與經濟性。

Micro-machining is a method to manufacture miniature devices or components with sizes ranging from dozens μm to a few mm. However, when it comes to applying sensor-communication-calculation based intelligent manufacturing to micro-machining, some issues still need to be addressed: (1) recording and synchronization of multiple sensors; (2) feature extraction of tiny signals; and (3) status estimation of different targets. To tackle these problems, this paper proposes an accuracy and tool wear prediction scheme for the micro-machining industry which includes an event-oriented process monitoring and back-tracking module, a failure tree diagnosis method, an Automatic Virtual Metrology (AVM) system, and a hybrid dynamic neural network module.
As the application results of the experiment in this paper suggest, the synchronizing multi-sensor signal control capacity in the proposed scheme is able to identify abnormal tool and workpiece collision within 7 ms and stop the machine from proceeding within 25 ms so as to avoid machine damage. As for the processing precision prediction, tiny signal feature extraction uses wavelet filter and vibration sensor along with the AVM system to help provide micro-machining precision prediction in the unit of millimeters. And lastly, concerning the tool wear estimation, the proposed scheme has the tool wear prediction capacity that equals to that of adopting other sensors (e.g., dynamometer) with its current sensor features of the spindle and servo motor going through the hybrid dynamic neural network module. In summary, this scheme integrated with sensor features and prediction model in this paper is proven to be feasible and economical for implementation.

[1] J. Chae, S.S. Park, T. Freiheit, "Investigation of micro-cutting operations," International Journal of Machine Tools & Manufacture, vol. 46, pp. 313-332, 2006.
[2] A. Aramcharoen; P.T. Mativenga, "Size effect and tool geometry in micromilling of tool steel," Precision Engineering, vol. 33, pp. 402-407, 2009.
[3] Dimitris Mourtzis, Ekaterini Vlachou, Nikolaos Milas, Nikitas Xanthopoulos, "A cloud-based approach for maintenance of machine tools and equipment based on shop-floor monitoring," Procedia CIRP, vol. 41, pp. 655-660, 2016.
[4] S. Kurada, C. Bradley, "A review of machine vision sensors for tool condition monitoring," Computers in Industry, vol. 34, no. 1, pp. 55-72, 1997.
[5] N.A. Abukhshim, P.T. Mativenga, M.A. Sheikh, "Heat generation and temperature prediction in metal cutting: A review and implications for high speed machining," International Journal of Machine Tools & Manufacture, vol. 46, pp. 782-800, 2006.
[6] Somkiat Tangjitsitcharoen, Toshimichi Moriwaki, "Intelligent monitoring and identification of cutting states of chips and chatter on CNC turning machine," Journal of Manufacturing Processes, vol. 10, pp. 40-46, 2008.
[7] R. Gao, L. Wang, R. Teti, D. Dornfeld, S. Kumara, M. Mori,M. Helu, "Cloud-enabled prognosis for manufacturing," CIRP Annals - Manufacturing Technology, vol. 64, pp. 749-772, 2015.
[8] R. Teti, K. Jemielniak, G. O’Donnell, D. Dornfeld, "Advanced monitoring of machining operations," CIRP Annals - Manufacturing Technology, vol. 59, pp. 717-739, 2010.
[9] J. Paulo Davim, V.N. Gaitonde, S.R. Karnik, "Investigations into the effect of cutting conditions on surface roughness in turning of free machining steel by ANN models," Journal of materials processing technology, vol. 205, pp. 16-23, 2008.
[10] Tuncay, Erzurumlu, Hasan Oktem, "Comparison of response surface model with neural network in determining the surface quality of moulded parts," Materials and Design, vol. 28, pp. 459-465, 2007.
[11] Ilhan Asiltürk, Mehmet Çunkas, "Modeling and prediction of surface roughness in turning operations using artificial neural network and multiple regression method," Expert Systems with Applications, vol. 38, pp. 5826-5832, 2011.
[12] C. Ahilan, Somasundaram Kumanan, N. Sivakumaran, J. Edwin Raja Dhas, "Modeling and prediction of machining quality in CNC turning process using intelligent hybrid decision making tools," Applied Soft Computing, vol. 13, pp. 1543-1551, 2013.
[13] Hao Tieng, Haw-Ching Yang, Min-Hsiung Hung, Fan-Tien Cheng, "A Novel Virtual Metrology Scheme for Predicting Machining Precision of Machine Tools," The 2013 IEEE International Conference on Robotics and Automation (ICRA 2013), pp. 264-269, 2013.
[14] Haw-Ching Yang, Hao Tieng, Fan-Tien Cheng, "Total Precision Inspection of Machine Tools with Virtual Metrology," Journal of the Chinese Institute of Engineers, vol. 39, 2016.
[15] Fan-Tien Cheng, Hao Tieng, Haw-Ching Yang, Min-Hsiung Hung, Yu-Chuan Lin, Chun-Fan Wei, Zih-Yan Shieh, "Industry 4.1 for Wheel Machining Automation," IEEE ROBOTICS AND AUTOMATION LETTERS, vol. 1, no. 1, 1 2016.
[16] Huseyin Metin Ertunc, Cuneyt Oysu, "Drill wear monitoring using cutting force signals," Mechatronics, vol. 14, pp. 533-548, 2004.
[17] D.A. Tobon-Mejia, K.Medjaher, N.Zerhouni, "CNC machine tool's wear diagnostic and prognostic by using dynamic Bayesian networks," Mechanical Systems and Signal Processing, vol. 28, pp. 167-182, 2012.
[18] N. Ghosh, Y.B. Ravi, A. Patra, S. Mukhopadhyay, S. Paul, A.R. Mohanty, A.B. Chattopadhyay, "Estimation of tool wear during CNC milling using neural network-based sensor fusion," Mechanical Systems and Signal Processing, vol. 21, pp. 466-479, 2007.
[19] Karali Patra, Surjya K. Pal, Kingshook Bhattacharyya, "Artificial neural network based prediction of drill flank wear from motor current signals," Applied Soft Computing, vol. 7, pp. 929-935, 2007.
[20] Luis Alfonso Franco-Gasca, Gilberto Herrera-Ruiz, Rocı´o Peniche-Vera, Rene´ de, Jesu´s Romero-Troncoso, Wbaldo Leal-Tafolla, "Sensorless tool failure monitoring system for drilling machines," International Journal of Machine Tools & Manufacture, vol. 46, pp. 381-386, 2006.
[21] Bulent Kaya, Cuneyt Oysu, Huseyin M. Ertunc, "Force-torque based on-line tool wear estimation system for CNC milling of Inconel 718 using neural networks," Advances in Engineering Software, vol. 42, pp. 76-84, 2011.
[22] K. Patra, A.K. Jha, T. Szalay, J. Ranjan, L. Monostori, "Artificial neural network based tool condition monitoring in micro mechanical peck drilling using thrust force signals," Precision Engineering, vol. 48, pp. 279-291, 2017.
[23] Dazhong Wu, Shaopeng Liu, Li Zhang, Janis Terpenny, Robert X. Gao, Thomas Kurfess, Judith A. Guzzo, "A fog computing-based framework for process monitoring and prognosis in cyber-manufacturing," Journal of Manufacturing Systems, vol. 43, pp. 25-34, 2017.
[24] E.E. Hurdle, L.M.Bartlett, J.D.Andrews, "Fault diagnostics of dynamic system operation using a fault tree based method," Reliability Engineering and System Safety, vol. 94, pp. 1371-1380, 2009.
[25] H.-C. Yang and Y.-Y. Li, "Event-Oriented Process Monitoring and Backtracking Method and Computer Product Thereof". R.O.C. Patent I551967, 2016.
[26] Yu-Yung Li, Haw-Ching Yang, Hao Tieng, Fan-Tien Cheng, "Extracting Relevant Features for Diagnosing Machine Tool Faults in Cloud Architecture," in 2015 IEEE International Conference on Automation Science and Engineering, Gothenberg, Sweden, 2015.
[27] Ryo Koike, Yasuhiro Kakinuma, Tojiro Aoyama, Kouhei Ohnishi, "Tool collision detection in high-speed feeding based on disturbance observer," Procedia CIRP, vol. 14, pp. 478-483, 2014.