科技發展日新月異，現今許多自動化產品及高精密儀器設備其動力來源為馬達，其生產結構與磁石息息相關。磁石製造過程多樣且繁雜，特別是近期熱門的3D磁石列印技術，不管用何種方式所製作的磁石，生產完成後皆需經過嚴謹的磁場量測，檢驗磁石的品質與特性。
現今磁場量測方式多為手動或半自動式量測，其量測數據僅能呈現磁石各個角度所對應的磁場大小，無從得知全面性的磁力線分佈。本研究將透過待測物之CAE磁場特性，與實際量測之磁特徵進行分析，並配合其CAD三維幾何資訊，規劃實際待測物周遭量測路徑CAD/CAM，發展一套可自動定位之三維量測系統，有別以往AI智動化技術，是以待測物本身既有資訊，以快速且精準定位為訴求，達到智能定位量測功能。
本文分為四個部分，第一部分為介紹本研究之實驗機台與設備功能：第二部分將介紹本文所使用NCC、K-means演算法與最小平方擬合圓演算法；第三部分為介紹完整智能化量測流程；最後第四部分以實驗結果驗證上述所有流程與智能定位之可行性，並展示最終量測結果。

At the present state of the development, magnetic field measurements mostly are operated manually or semi-automatically, and the measured data can only indicate the relationship between the angle of the magnetic field and its range. The comprehensive distribution of magnetic field lines would however still stay unknown with current methods.
This thesis is aimed to establish an automated detected and intelligent magnetic field measurement platform. The CAE magnetic field characteristics of the object to be measured and the magnetic characteristics of the actual measurement are analyzed, the CAD three-dimensional geometric information is utilized to plan the CAD/CAM measurement routing of the object to be measured, and then finally an automatic positioning three-dimensional (3D) measurement system using Normalized Cross Correlation (NCC) algorithm, K-means clustering and the least squares circle fitting is developed. The proposed system is different from the previous AI intelligent technology, which is based on the existing information of the object to be measured with the feature of fast and accurate positioning to achieve the intelligent positioning function.
Finally, the feasibility of the proposed intelligent positioning system was verified with experimental results.

[1] 賴建志，「利用磁場迴授訊號於三維軌跡量測系統之研究」，碩士論文，國立成功大學機械工程學系，2007年。
[2] 楊君賢，「三維磁場量測與磁場追蹤控制之研究」，博士論文，國立成功大學機械工程學系，2007年。
[3] A. Heyder, M. Tenner, A. Meyer, S. Abersfelder and J. Franke, "Magnetic stray field measurement of magnetic specimen," 2016 6th International Electric Drives Production Conference (EDPC), Nuremberg, 2016, pp. 312-316.
[4] 林敬智, 「三維磁通量測之原理與平台建置」, 成大馬達科技研究中心, 第836期, 2019年3月。
[5] C. Huber, C. Abert, F. Bruckner, M. Groenefeld, S. Schuschnigg, I. Teliban, C. Vogler, G. Wautischer, R. Windl and D. Suess, " 3D printing of polymer-bonded rare-earth magnets with a variable magnetic compound fraction for a predefined stray field, " Sci. Rep., p. 9419., 2017
[6] M. Ortner, C. Huber, N. Vollert, J. Pilz and D. Süss, "Application of 3D-printed magnets for magnetic position detection systems," 2017 IEEE SENSORS, Glasgow, pp. 1-3., 2017
[7] H. Edwin, "On a New Action of the Magnet on Electric Currents". American Journal of Mathematics vol 2, 1879.
[8] L. Chow, "Electromagnetic theory, " Sudbury MA: Jones and Bartlett. 2006: pp. 172-175. ISBN 0-7637-3827-1.
[9] 陳韋竹，「霍爾效應量測裝置開發與應用」，碩士論文,樹德科技大學電腦與通訊系，2010年。
[10] 「F.W. Bell 8030 manual」，8000-series-gaussmeter-user-manual-rev.B-UN1270.pdf
[11] 東佑達自動化科技股份有限公司，軌道內嵌式滑台模組GTH系列，
[Available]:http://www.acepillar.com.tw/data/goods/201606/1467251309YIJGA.pdf
[12] 台達電子股份有限公司，台達交流伺服驅動器ASDA-A2系列，
[Available]:http://www.deltaww.com/products/CategoryListT1.aspx?CID=060201&PID=14&hl=zhtw&Name=ASDAA2%E7%B3%BB%E5%88%97
[13] 啟興科技股份有限公司，電動滑台系列，
[Available]: https://www.cimax.com.tw/product/1523430398
[14] 究準科技股份有限公司，2D&3D磁場分佈測試系統，
[Available]:http://joinprecision.com/zh/2dor3d%E7%A3%81%E5%A0%B4%E5%88%86%E4%BD%88%E6%B8%AC%E8%A9%A6%E7%B3%BB%E7%B5%B1/
[15] J. Mac, "Some Methods for Classification and Analysis of Multivariate Observations", Proc. of the Fifth Berkeley Symposium on Math. Stat and Prob., vol. 1, pp. 281-296, 1967.
[16] E. Jeffrey, A. Martin,M. Anirban, "Traffic Classification Using Clustering Algorithms", SIGCOMM'06 Workshops, September 11-15, 2006.
[17] 周智華，「機器學習」，清華大學出版社，2015年。
[18] Driver and Kroeber, "Quantitative Expression of Cultural Relationships," University of California Publications in American Archaeology and Ethnology,Quantitative Expression of Cultural Relationships: 211-256.
[19] H. Geoffrey, J. Sejnowski, "Unsupervised Learning and Map Formation: Foundations of Neural Computation, " MIT Press, ISBN 0-262-58168-X
[20] S. Kotsiantis, P. Pintelas, " Recent Advances in Clustering: A Brief Survey, " WSEAS Transactions on Information Science and Applications, Vol 1, No 1 (73-81), 2004.
[21] J.A.Hartigan,M.A.Wong, "Algorithm AS 136: A k-Means Clustering Algorithm, " Journal of the Royal Statistical Society, Series C. 1979, 28 (1): 100–108. JSTOR 2346830.
[22] G.Hamerly,C.Elkan, "Alternatives to the k-means algorithm that find better clusterings (PDF), " Proceedings of the eleventh international conference on Information and knowledge management (CIKM). 2002.
[23] D.Arthur, B.Manthey,H.Roeglin, "k-means has polynomial smoothed complexity, " Proceedings of the 50th Symposium on Foundations of Computer Science (FOCS). 2009.
[24] https://blog.csdn.net/liyuanbhu/article/details/50889951
[25] W. Guorong,W. Yimin,Q. SanZheng,Equation, "Solving Generalized Inverses," Beijing: Science Press. 2004: pp. 6. ISBN 7-03-012437-5
[26] J. P. Lewis, " Fast normalized cross-correlation," Vision Interface, Canadian Image Processing and Pattern Recognition Society , pp. 120-123,1995
[27] K. Briechle and U. D. Hanebeck, "Template matching using fast normalized cross correlation", Proc. SPIE, vol. 4387, pp. 95-102, 2001.
[28] https://www.itread01.com/content/1544863514.html