在強調工業4.0的時代，為了提高生產速率，降低機台停機可能造成的虧損，機台狀態監控已是不可或缺的環節，同時隨著電腦運算能力的提升，人工智慧因此蓬勃發展，使得缺乏物理模型之次系統有機會透過演算法建立診斷模型，故許多研究爭相以人工智慧建立機台狀態診斷模型，然而多數研究皆有過於仰賴人工智慧的情況，主要聚焦於模型選擇與模型訓練參數探討，使得預測準確率難有明顯突破，故本文嘗試以領域知識為核心協助人工智慧的方式進行改善。本研究以刀具狀態診斷作為應用情境，然而目前仍缺乏刀具狀態相關領域知識，因此首先進行監控軟硬體環境建立，包含安裝狀態監測的五種感測器、配置訊號傳輸與擷取設備、撰寫訊號處理程式以及最後透過時域及頻域指標執行特徵擷取，接著為了獲得切削與刀具狀態相關領域知識，設計四組實驗，並由實驗結果探討特徵指標與切削條件及刀具狀態之間的關係，針對刀具狀態診斷，本研究以其中的磨耗刀具變切削參數的實驗結果進行特徵指標評估，整理出六個對於刀具狀態偵測較為靈敏的指標，最後以特徵指標評估結果配合多層感知器建立刀具狀態診斷模型，並與不同輸入特徵之模型做比較，使用特徵指標評估結果的模型在四個不同切削參數下對三種刀具磨耗程度進行診斷，準確率可達98%，由比較結果可發現以領域知識協助人工智慧模型能提升模型建立效率，同時維持高診斷準確率。綜合以上研究結果，期望本文提出之研究方法未來可廣泛應用於狀態診斷模型之建立。

Machine tools play key roles in modern manufacturing industry. The quality of machined products are largely depended on the status of machines in various aspects. As a result, appropriate condition monitoring would be essential for both quality control and life assessment. With recent advancement of computer science, artificial intelligence (AI) becomes an alternative choice for establishing diagnostic model. AI provides a decision-making system by using multiple sensor features to predict the states of machines, especially for the machines without physical model. While many research works focus on the adjustment of model parameters or trying different algorithm to improve accuracy, the domain knowledge of machine failures is rarely studied. As a result, an artificial neural network based status monitoring system which is combined with comprehensive investigation of sensor features should be developed. Moreover, for modern machine tools, high ratio of down time is attributed to tool failure. In addition, the complexity of machining operation makes development of a model which can universally applied to different operations by curve fitting difficult. Hence, tool condition assessment is taken as a scenario in this work. For achieving above addressed goal, the experimental system must be setup first. For establishing a low cost wireless communication system, a four channels data transmission module based on Arduino board and Bluetooth is developed. Meanwhile, to access cutting tool condition from physical signal, the multi-sensor environment and data acquisition system are configured. In addition, the signal processing and feature extraction schemes are also addressed. Meanwhile, to obtain the corresponding domain knowledge of tool failure, a number of machining experiments are designed and executed. Through the effort of investigating the relation between tool conditions and sensor indexes by sensor index evaluation, six indexes which are more sensitive to tool condition can be listed to initially establish a diagnostic process. Finally, a multilayer perceptron (MLP) model is adopted to carry out condition assessment, and three models trained by different input features are compared to examine the feasibility of integrating domain knowledge and AI. In the near future, with more data collected, it is expected that more sophisticated models would be developed for better predicting the tool condition. Meanwhile, this concept can be further applied to other sub-systems which are also lack of physical models for establishing status diagnostic model to enhance the manufacturing reliability.

[1]. Personnel work 4.0 - megatrends of digitization, http://www.management-circle.de/blog/personalarbeit-4-0-megatrends-der-digitalisierung
[2]. Smart manufacturing vs. lights out manufacturing,, https://enterpriseiotinsights.com/
[3]. B. Li, M.-Y. Chow, Y. Tipsuwan, and J.C. Hung, "Neural-network-based motor rolling bearing fault diagnosis," IEEE transactions on industrial electronics, vol. 47, no. 5, pp. 1060-1069, 2000.
[4]. N.K. Hsieh, W.Y. Lin, and H.T. Young, "High-speed spindle fault diagnosis with the empirical mode decomposition and multiscale entropy method," Entropy, vol. 17, no. 4, pp. 2170-2183, 2015.
[5]. T.I. El-Wardany, D. Gao, and M.A. Elbestawi, "Tool condition monitoring in drilling using vibration signature analysis," International Journal of Machine Tools Manufacture, vol. 36, no. 6, pp. 687-711, 1996.
[6]. D.M.O. González and J.C.E. Ferreira, "MEMS accelerometer-based system for inexpensive online CNC milling process chatter detection," Automation Science and Engineering (CASE), 2016 IEEE International Conference IEEE, 2016.
[7]. A.A. Jaber and R. Bicker, "Design of a Wireless Sensor Node for Vibration Monitoring of Industrial Machinery," International Journal of Electrical and Computer Engineering, vol. 6, no. 2, pp. 639-653, 2016.
[8]. R.T.R. de Jesus, H.R. Gilberto, T.V. Ivan, and J.C.J. Carlos, "Driver current analysis for sensorless tool breakage monitoring of CNC milling machines," International Journal of Machine Tools Manufacture, vol. 43, no. 15, pp. 1529-1534, 2003.
[9]. K. Jemielniak and O. Otman, "Tool failure detection based on analysis of acoustic emission signals," Journal of Materials Processing Technology, vol. 76, no. 1-3, pp. 192-197, 1998.
[10]. C.H. Martins, P.R. de Aguiar, A. Frech, and E.C. Bianchi, "Tool Condition Monitoring of Single-Point Dresser Using Acoustic Emission and Neural Networks Models," IEEE Transactions on Instrumentation and Measurement, vol. 63, no. 3, pp. 667-679, 2014.
[11]. 吳宗軒, 以調變主軸轉速抑制銑削顫震之探討, 國立成功大學機械工程學系碩士論文, 2017.
[12]. 物聯網示意圖, https://www.zdnet.com/article/the-future-of-enterprise-iot-2-factors-to-watch/
[13]. S. Binsaeid, S. Asfour, S. Cho, and A. Onar, "Machine ensemble approach for simultaneous detection of transient and gradual abnormalities in end milling using multisensor fusion," Journal of Materials Processing Technology, vol. 209, no. 10, pp. 4728-4738, 2009.
[14]. N. Ghosh, Y. Ravi, A. Patra, S. Mukhopadhyay, S. Paul, A. Mohanty, and A. Chattopadhyay, "Estimation of tool wear during CNC milling using neural network-based sensor fusion," Mechanical Systems Signal Processing, vol. 21, no. 1, pp. 466-479, 2007.
[15]. D. Johansson, S. Hägglund, V. Bushlya, and J.-E. Ståhl, "Assessment of commonly used tool life models in metal cutting," Procedia manufacturing, vol. 11, no., pp. 602-609, 2017.
[16]. 蔡瑞敏, 多波段微機電加速規整合設計於工具機主軸振動監控應用, 國立成功大學機械工程學系碩士論文, 2018.
[17]. Yamamoto Metal trchnos Co., Ltd., Manufacturing Process Monitoring Device - Multi Intelligence, https://www.yama-kin.co.jp/english/products/m-intel.html
[18]. R. Teti, K. Jemielniak, G. O’Donnell, and D. Dornfeld, "Advanced monitoring of machining operations," CIRP Annals-Manufacturing Technology, vol. 59, no. 2, pp. 717-739, 2010.
[19]. K.F. Martin, "A review by discussion of condition monitoring and fault diagnosis in machine tools," International Journal of Machine Tools Manufacture, vol. 34, no. 4, pp. 527-551, 1994.
[20]. M.S.H. Bhuiyan, I.A. Choudhury, and Y. Nukman, "Tool condition monitoring using acoustic emission and vibration signature in turning," Proceedings of the world congress on engineering, vol. 3, no., pp. 1-5, 2012.
[21]. H. Su and K.T. Chong, "Induction machine condition monitoring using neural network modeling," IEEE Transactions on Industrial Electronics, vol. 54, no. 1, pp. 241-249, 2007.
[22]. B. Luo, H. Wang, H. Liu, B. Li, and F. Peng, "Early fault detection of machine tools based on deep learning and dynamic identification," IEEE Transactions on Industrial Electronics, vol. 66, no. 1, pp. 509-518, 2019.
[23]. 三興機器工業股份有限公司, 車床, https://www.sanshinglathe.com.tw/zh-tw/
[24]. 邁鑫科技工業股份有限公司, 砲塔式銑床, http://www.manford.com.tw/index_CT.php?Langx=CT
[25]. 東台精機, CNC工具機, http://www.tongtai.com.tw/tw/index.php
[26]. 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.
[27]. 林瑞容, 銑削製程特徵值及暫態響應之探討, 國立成功大學機械工程學系碩士論文, 2018.
[28]. S.A. Tobias and W. Fishwick, " A Theory of Regenerative Chatter," The Engineer-London, vol., no., 1958.
[29]. S. Smith and J. Tlusty, "Stabilizing chatter by automatic spindle speed regulation," CIRP Annals-Manufacturing Technology, vol. 41, no. 1, pp. 433-436, 1992.
[30]. Vertical milling center, https://grabcad.com/library/vmc-vertical-milling-center-bt40-1
[31]. Svenska Kullagerfabriken Inc., Electro-spindle in a horizontal machine centre, https://www.skf.com/us/products/bearings-units-housings/super-precision-bearings/angular-contact-ball-bearings/designs-and-variants/high-speed-E-design-bearings/index.html
[32]. Planlauf GmbH, 顫振現象之工件表面, https://www.planlauf.com/en/measurement/diagnosis-of-chatter-marks/
[33]. A. Priyadarshini, S.K. Pal, and A.K. Samantaray, Finite element modeling of chip formation in orthogonal machining, in Statistical and computational techniques in manufacturing. 2012, Springer. p. 101-144.
[34]. Y. Huang, X. Zhang, and Y. Xiong, Finite element analysis of machining thin-wall parts: error prediction and stability analysis, in Finite Element Analysis-Applications in Mechanical Engineering. 2012, IntechOpen.
[35]. 朱效賢, 包絡譜分析於軸承故障診斷之探討暨工程應用, 國立中央大學機械工程學系碩士論文, 2005.
[36]. Y. Koren, "Flank wear model of cutting tools using control theory," Journal of Engineering for Industry, vol. 100, no. 1, pp. 103-109, 1978.
[37]. E. Usui, T. Shirakashi, and T. Kitagawa, "Analytical prediction of cutting tool wear," Wear, vol. 100, no. 1-3, pp. 129-151, 1984.
[38]. H. Shao, H. Wang, and X. Zhao, "A cutting power model for tool wear monitoring in milling," International Journal of Machine Tools Manufacture, vol. 44, no. 14, pp. 1503-1509, 2004.
[39]. J. Jurkovic, M. Korosec, and J. Kopac, "New approach in tool wear measuring technique using CCD vision system," International Journal of Machine Tools Manufacture
vol. 45, no. 9, pp. 1023-1030, 2005.
[40]. J.-H. Kim, D.-K. Moon, D.-W. Lee, J.-s. Kim, M.-C. Kang, and K.H. Kim, "Tool wear measuring technique on the machine using CCD and exclusive jig," Journal of materials processing technology, vol. 130, no., pp. 668-674, 2002.
[41]. 卓家弘, 開發具加工感測與磨耗量測之刀具分析系統, 國立高雄第一科技大學電機工程研究所碩士論文, 2015.
[42]. 李明哲, 影像處理輔助微銑刀以及鑽石刀具之刀具磨耗檢測, 國立臺灣科技大學機械工程學系碩士論文, 2011.
[43]. 林育佐, 一種基於機器視覺系統的鏟花刀具磨耗檢測, 國立成功大學工程科學系碩士論文, 2012.
[44]. H. Takeyama, Y. Doi, T. Mitsuoka, and H. Sekiguchi, "Sensors of Tool Life for Optimization of Machining," Bulletin of JSME, vol. 12, no. 49, pp. 132-140, 1969.
[45]. Y. Altintas, M. Eynian, and H. Onozuka, "Identification of dynamic cutting force coefficients and chatter stability with process damping," CIRP annals, vol. 57, no. 1, pp. 371-374, 2008.
[46]. W. Bao and I. Tansel, "Modeling micro-end-milling operations. Part I: analytical cutting force model," International Journal of Machine Tools Manufacture, vol. 40, no. 15, pp. 2155-2173, 2000.
[47]. W. Lin, B. Lee, and C. Wu, "Modeling the surface roughness and cutting force for turning," Journal of Materials Processing Technology, vol. 108, no. 3, pp. 286-293, 2001.
[48]. R.S. Figliola and D. Beasley, Theory and design for mechanical measurements. 2015: John Wiley & Sons.
[49]. ISO 8688-2:1989(E), Tool-life Testing in Milling, Part 2, End Milling,
[50]. M. Bhuiyan, I. Choudhury, and M. Dahari, "Monitoring the tool wear, surface roughness and chip formation occurrences using multiple sensors in turning," Journal of Manufacturing Systems, vol. 33, no. 4, pp. 476-487, 2014.
[51]. 詠業科技股份有限公司, 壓電效應示意圖, https://www.unictron.com/
[52]. PCB Piezotronics Inc., Accelerometers/Vibration Sensors, http://www.pcb.com/TestMeasurement/Accelerometers
[53]. Analog Devices Inc., ADXL001 Breakout Board, http://www.analog.com/en/design-center/evaluation-hardware-and-software/evaluation-boards-kits/eval-adxl001.html#eb-overview
[54]. A. Rastegari, A. Archenti, and M. Mobin, "Condition based maintenance of machine tools: Vibration monitoring of spindle units," Reliability and Maintainability Symposium (RAMS), 2017 Annual, IEEE, 2017.
[55]. J. Kopač and S. Šali, "Tool wear monitoring during the turning process," Journal of Materials Processing Technology, vol. 113, no. 1-3, pp. 312-316, 2001.
[56]. D. Salgado and F. Alonso, "An approach based on current and sound signals for in-process tool wear monitoring," International Journal of Machine Tools Manufacture, vol. 47, no. 14, pp. 2140-2152, 2007.
[57]. Cross-section of dynamic microphone, https://www.mediacollege.com/audio/microphones/dynamic.html
[58]. Cross-section of condenser microphone, https://www.mediacollege.com/audio/microphones/condenser.html
[59]. H. Ravindra, Y. Srinivasa, and R. Krishnamurthy, "Acoustic emission for tool condition monitoring in metal cutting," Wear, vol. 212, no. 1, pp. 78-84, 1997.
[60]. National Instruments Inc., 訊號混疊示意圖, https://zone.ni.com/reference/en-XX/help/371361P-01/lvanlsconcepts/aliasing/
[61]. Parallel and Distributed Deep Learning: A Survey, https://towardsdatascience.com/parallel-and-distributed-deep-learning-a-survey-97137ff94e4c
[62]. 利偉木工機械有限公司, PMC五軸加工機, https://www.lihwoei.com.tw/mini5-axis-cnc-tw
[63]. National Instruments, cDAQ-9191 Wi-Fi CompactDAQ機箱, http://www.ni.com/zh-tw/support/model.cdaq-9191.html
[64]. National Instruments, NI-9215 C系列電壓輸入模組, http://www.ni.com/zh-tw/support/model.ni-9215.html
[65]. 黃耀賢, 主軸振動與聲射訊號於微銑刀具磨耗監測之應用研究, 國立中興大學機械工程學系碩士論文, 2010.
[66]. 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 signal processing, vol. 16, no. 4, pp. 487-546, 2002.
[67]. S.S. Rao and F.F. Yap, Mechanical vibrations. Vol. 4. 2011: Prentice hall Upper Saddle River.
[68]. SKF Co., Ltd., Influence of external load on preload bearing sets, https://www.skf.com/group/products/bearings-units-housings/super-precision-bearings/principles/design-considerations/bearing_preload/actbb/index.html
[69]. H. Heisler, Advanced vehicle technology. 2002.
[70]. F.T. Liu, K.M. Ting, and Z.-H. Zhou, "Isolation forest," 2008 Eighth IEEE International Conference on Data Mining, IEEE, 2008.
[71]. R. De Maesschalck, D. Jouan-Rimbaud, and D.L. Massart, "The mahalanobis distance," Chemometrics intelligent laboratory systems, vol. 50, no. 1, pp. 1-18, 2000.
[72]. W.-R. Chen, Y.-H. Yun, M. Wen, H.-M. Lu, Z.-M. Zhang, and Y.-Z. Liang, "Representative subset selection and outlier detection via isolation forest," Analytical Methods, vol. 8, no. 39, pp. 7225-7231, 2016.