沖床於製造業的用途十分廣泛，可用於沖剪、成形、彎曲、引伸和壓縮等加工用途，可知其在工業上的重要性。傳統沖床以馬達為動力源，並藉由皮帶來帶動飛輪運作，故若皮帶發生異常，不僅降低了機台運作效率，也會使機台軸承發生損傷。因此，本研究提出利用機器學習中的支持向量機以及其核函數的應用與比較，建立沖床皮帶之狀態分類模型，也透過結合主成分分析方法使資料降維達成空間可視化，以及在數據的蒐集係透過沖床機台現有的設備來擷取，節省額外加裝感測器來蒐集資料以節省實驗成本。實驗結果顯示，分類模型的準確率可達近99%，並且可透過空間可視化的方法，觀察數據之間的分佈及關聯性，可進一步分析皮帶的異常問題，達到機台預測保養的效果。

Stamping presses are widely used in the manufacturing industry and can be used for processing purposes such as punching, forming, bending, stretching and shrinking, marking their importance in the industry. The traditional punching machine uses motor as power source, and belt is used to transfer the motor power to the flywheel. Therefore, if the belt is abnormal, it will not only reduce the operation efficiency of the machine, but also can damage the bearings of the machine. Therefore, this study proposes to use the support vector machine in machine learning and the application and comparison of its kernel function to establish the state classification model of the punch machine belt. Also, this study is able to reduce the collected data dimension by employing the principal component analysis method to achieve spatial visualization. This is achieved using the existing equipment of the punching machine, thus saving additional sensors, and experimental cost. The experimental results show that the accuracy of the classification model can reach nearly 99%, and the distribution and correlation between the data can be observed through spatial visualization. The abnormal problem of the belt can then be further analyzed to achieve the effect of predictive maintenance of the machine.

[1] Tsai, Y. T., “Applying a Case-Based Reasoning Method for Fault Diagnosis During Maintenance,” Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, Vol. 223, No. 10, pp.2431-2441 (2009).
[2] Lee, J., “Machine Performance Monitoring and Proactive Maintenance in Computer-Integrated Manufacturing:Review and Perspective,” International Journal of Computer Integrated Manufacturing, Vol. 8, No. 5, pp. 370-380 (1995).
[3] Lee, J., “Recent Advances on Advanced Prognostics and Trends of Intelligent Maintenance Systems,”Proceedings of ICME2006: International Conference on Maintenance Engineering, Chengdu, China, pp.292-307 (2006).
[4] 蔡有藤, 陳宗傑, and 廖哲賢. "機械系統性能衰退預測與故障診斷之研究." Journal of Technology, vol. 27, no. 3, pp. 121-129, 2012.
[5] M. Canizo, A. Conde, S. Charramendieta, R. Miñón, R. G. Cid-Fuentes and E. Onieva, "Implementation of a Large-Scale Platform for Cyber-Physical System Real-Time Monitoring," in IEEE Access, vol. 7, pp. 52455-52466,2019.
[6] 吳宗倫，「基於沖壓聲音的沖床生命週期偵測與嵌入式系統實現」，國立中正大學電機工程研究所，碩士論文，2017。
[7] 方姿晴，「沖床之智慧異常偵測與即時監控系統」，國立臺灣師範大學機電工程研究所，碩士論文，2019。
[8] CHINFONG,https://www.chinfong.com/products.php?mode=proDetail&cid=1485397868&pid=1486715584, Reference Data:2022/03/09
[9] 東延有限公司, http://edpt.com.tw/big5/index.php, Reference Data:2022/03/09.
[10] Bose, Bimal K. Adjustable Speed AC Drive Systems. New York: IEEE Press. 1980. ISBN 0-87942-146-0.
[11]伍得福企業有限公司, https://sites.google.com/site/wdfbelt/others/gates_tension_pen
[12] Turing, Alan M. "Computing machinery and intelligence, " Parsing the Turing Test. Springer, Dordrecht, pp.23-65, 2009.
[13] Cortes, C. and Vapnik, V., 1995. Support-vector networks. Machine learning, Vol.20, no. 3, pp. 273-297.
[14] Boser, B. E.; Guyon, I. M.; Vapnik, V. N. A training algorithm for optimal margin classifiers. Proceedings of the fifth annual workshop on Computational learning theory – COLT '92. 1992: 144.
[15] Meyer, D.; Leisch, F.; Hornik, K. The support vector machine under test. Neurocomputing. 2003, 55: 169.
[16] Hsu, Chih-Wei; Chang, Chih-Chung & Lin, Chih-Jen.2003. A Practical Guide to Support Vector Classification.Department of Computer Science and Information Engineering, National Taiwan University.
[17] I Steinwart,D Hush,C Scovel ,2006. An explicit description of the reproducing kernel Hilbert spaces of Gaussian RBF kernels. IEEE Transactions on Information Theory, 52, 4635-4643
[18] S. Wold, K. Esbensen, and P. Geladi, “Principal component analysis,”Chemometr. Intell. Lab. Syst., vol. 2, no. 1–3, pp. 37–52, Aug. 1987.
[19] F. Provost, T. Fawcett, Data Science and its Relationship to Big Data and Data-Driven Decision Making Big Data, 1 (1) (2013), pp. 51-59.
[20] CHIN FONG, https://www.chinfong.com/index.php, Reference:2022/03/09
[21] 東元TECO, "東元510系列變頻器",http://globalsa.teco.com.tw/tw/products_series.aspx?KindID=1&ID=30
[22] Two-Way雙向貿易股份有限公司, "MITSUBISHI三菱電機-FX3G, http://www.two-way.com.tw/product/fx/fx3g/
[23] NotFalse 技術客, TCP 三向交握 (Three-way Handshake), Available:https://notfalse.net/7/three-way-handshake
[24] MODBUS Application Protocol 1 1 b, https://modbus.org/docs/Modbus_Application_Protocol_V1_1b.pdf
[25] Wikipedia contributors. "Linux." 维基百科, 自由的百科全书. 维基百科, 自由的百科全书, 21 Feb. 2022. Web. 21 Feb. 2022.‹https://zh.wikipedia.org/w/index.php?title=Linux&oldid=70280562›.
[26] Linux C參考手冊, https://people.cs.nctu.edu.tw/~yslin/library/linuxc/main.htm
[27] Wikipedia contributors. "MySQL." 维基百科, 自由的百科全书. 维基百科, 自由的百科全书, 22 Jan. 2022. Web. 22 Jan. 2022.‹https://zh.wikipedia.org/w/index.php?title=MySQL&oldid=69799072›.