全球煉鋼廠都會面臨一個極嚴重問題，就是『洩鋼』。鋼液吊運或生產過程中，如發生盛鋼桶異狀，就可能會導致洩鋼意外，輕則桶內鋼液全毀、主設備損壞、耽誤生產排程、降低產能，嚴重時則會對人員造成致命意外。為了避免洩鋼意外的發生，目前煉鋼廠內對盛鋼桶的管控方式主要是以『回數控制』為主，搭配檢修人員以目視判修或進入盛鋼桶進行手動鑿孔的方式量測內襯殘厚，作為是否下線進行維修的依據。
然而，人工判定常因經驗與風險容許程度的不同，會有相當大的差異；同時，回數控制為主的管控方式並沒辦法即時反應各個盛鋼桶的使用狀況，是目前的檢修策略所存在的隱憂。
據此，本研究擬開發盛鋼桶內襯殘厚的非破壞檢測(nondestructive testing)技術，利用深度掃描儀取得三維點雲資訊，並開發疊合、特徵區萃取與比對等相關技術，來實現對可疑的洩鋼區、或是增厚區的預測與監控。首先，利用基於飛時測距(time of flight)原理的深度掃描儀對盛鋼桶內襯進行非接觸式的量測，並產生點雲(point cloud)記錄下盛鋼桶的內襯殘厚；接著利用主成分分析(Principal Component Analysis, PCA)搭配最近點疊代法(Iterative Closest Point, ICP)，將初始狀態的盛鋼桶點雲與出現缺陷的盛鋼桶點雲進行對齊；再來藉由比較兩組點雲中各個點的特徵變化，找出可能屬於缺陷區域的變異點；最後，再將變異點進行分群，產生數個變異區域，並搭配 -shape以及德勞內三角剖分(Delaunay Triangulation)計算各個變異區域的範圍與大小。
本研究成果以自動化方式完成檢測，不須人工介入，故無操作危險性，且可建立實際數據資料，協助檢修人員進行可視化判讀，進而做出檢修決策。

This research intended to develop an automatic and nondestructive defect detection strategy for ladle furnaces. By using range scanners to acquire 3D point cloud for the refractory lining, combining with point cloud registration and feature extraction techniques, potential defects such as corrosion areas and deposition areas inside the ladle can be detected, monitored, and predicted.
Firstly, by using range scanners based on time-of-flight technologies, a non-contact measurement on the ladle can be performed, and the lining surface can be reconstructed as a 3D point cloud model. Secondly, to complete point cloud registration, Principal Component Analysis (PCA) and Iterative Closest Points (ICP) are applied to align a defected ladle to a reference undamaged ladle. Thirdly, compare the aligned two ladle models and find the points that satisfied the defect's characteristics. At last, cluster defect points into different regions, and the size for each defect region can be computed by alpha-shape and Delaunay Triangulation. Once the defect regions are being located and categorized, valuable information could be provided for maintenance decision-making.

[1] R. Usamentiaga, P. Venegas, J. Guerediaga, L. Vega, J. Molleda, and F. G. Bulnes, "Infrared thermography for temperature measurement and non-destructive testing," Sensors, vol. 14, no. 7, pp. 12305-12348, 2014.
[2] B. Chakraborty and B. K. Sinha, "Process-integrated steel ladle monitoring, based on infrared imaging–a robust approach to avoid ladle breakout," Quantitative InfraRed Thermography Journal, vol. 17, no. 3, pp. 169-191, 2020.
[3] M. Viale, O. Martin, F. Muratori, U. Bertezzolo, J. Perez, and J. Usart, "Application of on-line infrared thermography in steel making industry," in Thermosense XXIX, 2007, vol. 6541, p. 65410H: International Society for Optics and Photonics.
[4] R. Horaud, M. Hansard, G. Evangelidis, and C. Ménier, "An overview of depth cameras and range scanners based on time-of-flight technologies," Machine vision and applications, vol. 27, no. 7, pp. 1005-1020, 2016.
[5] H. Zhu et al., "A review of point set registration: From pairwise registration to groupwise registration," Sensors, vol. 19, no. 5, p. 1191, 2019.
[6] B. Maiseli, Y. Gu, and H. Gao, "Recent developments and trends in point set registration methods," Journal of Visual Communication and Image Representation, vol. 46, pp. 95-106, 2017.
[7] K. S. Arun, T. S. Huang, and S. D. Blostein, "Least-squares fitting of two 3-D point sets," IEEE Transactions on pattern analysis and machine intelligence, no. 5, pp. 698-700, 1987.
[8] P. J. Besl and N. D. McKay, "A method for registration of 3-D shapes," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 239-256, 1992.
[9] S. Rusinkiewicz and M. Levoy, "Efficient variants of the ICP algorithm," in Proceedings third international conference on 3-D digital imaging and modeling, 2001, pp. 145-152: IEEE.
[10] K.-L. Low, Linear Least-Squares Optimization for Point-to-Plane ICP Surface Registration. 2004.
[11] Y. Wang, R. Xiong, and Q. Li, "Em-Based Point to Plane ICP for 3D Simultaneous Localization and Mapping," I. J. Robotics and Automation, vol. 28, 2013.
[12] A. Myronenko and X. Song, "Point set registration: Coherent point drift," IEEE transactions on pattern analysis and machine intelligence, vol. 32, no. 12, pp. 2262-2275, 2010.
[13] P. Biber, "The Normal Distributions Transform : A New Approach to Laser Scan Matching," Proc. of IROS2003, 2003 2003.
[14] M. Magnusson, The three-dimensional normal-distributions transform an efficient representation for registration, surface analysis, and loop detection. Örebro: Örebro universitet, 2009.
[15] A. Abellán, M. Jaboyedoff, T. Oppikofer, and J. Vilaplana, "Detection of millimetric deformation using a terrestrial laser scanner: experiment and application to a rockfall event," Natural hazards and earth system sciences, vol. 9, no. 2, pp. 365-372, 2009.
[16] A. Abellán, J. Calvet, J. M. Vilaplana, and J. Blanchard, "Detection and spatial prediction of rockfalls by means of terrestrial laser scanner monitoring," Geomorphology, vol. 119, no. 3-4, pp. 162-171, 2010.
[17] W. Liu, S. Chen, and E. Hauser, "LiDAR-based bridge structure defect detection," Experimental Techniques, vol. 35, no. 6, pp. 27-34, 2011.
[18] Y. Turkan, J. Hong, S. Laflamme, and N. Puri, "Adaptive wavelet neural network for terrestrial laser scanner-based crack detection," Automation in construction, vol. 94, pp. 191-202, 2018.
[19] A. Janowski, K. Nagrodzka-Godycka, J. Szulwic, and P. Ziolkowski, "Remote sensing and photogrammetry techniques in diagnostics of concrete structures," Computers and Concrete, vol. 18, no. 3, pp. 405-420, 2016.
[20] J.-S. Yoon, M. Sagong, J. Lee, and K.-s. Lee, "Feature extraction of a concrete tunnel liner from 3D laser scanning data," Ndt & E international, vol. 42, no. 2, pp. 97-105, 2009.
[21] M. Makuch and P. Gawronek, "3D point cloud analysis for damage detection on hyperboloid cooling tower shells," Remote Sensing, vol. 12, no. 10, p. 1542, 2020.
[22] M.-K. Kim, H. Sohn, and C.-C. Chang, "Localization and quantification of concrete spalling defects using terrestrial laser scanning," Journal of Computing in Civil Engineering, vol. 29, no. 6, p. 04014086, 2015.
[23] I. Jovančević et al., "3D point cloud analysis for detection and characterization of defects on airplane exterior surface," Journal of Nondestructive Evaluation, vol. 36, no. 4, pp. 1-17, 2017.
[24] T. Reyno, C. Marsden, and D. Wowk, "Surface damage evaluation of honeycomb sandwich aircraft panels using 3D scanning technology," NDT & E International, vol. 97, pp. 11-19, 2018.
[25] A. A. Siddiqui, "A New Inspection Method Based on RGB-D Profiling," Virginia Tech, 2015.
[26] K. Klasing, D. Althoff, D. Wollherr, and M. Buss, "Comparison of surface normal estimation methods for range sensing applications," in 2009 IEEE International Conference on Robotics and Automation, 2009, pp. 3206-3211: IEEE.
[27] M. Pauly, M. Gross, and L. P. Kobbelt, "Efficient simplification of point-sampled surfaces," in IEEE Visualization, 2002. VIS 2002., 2002, pp. 163-170.
[28] J. J. Koenderink and A. J. Van Doorn, "Surface shape and curvature scales," Image and vision computing, vol. 10, no. 8, pp. 557-564, 1992.
[29] J. Sell and P. O'Connor, "The xbox one system on a chip and kinect sensor," IEEE Micro, vol. 34, no. 2, pp. 44-53, 2014.
[30] D. Pagliari and L. Pinto, "Calibration of kinect for xbox one and comparison between the two generations of microsoft sensors," Sensors, vol. 15, no. 11, pp. 27569-27589, 2015.
[31] P. Fankhauser, M. Bloesch, D. Rodriguez, R. Kaestner, M. Hutter, and R. Siegwart, "Kinect v2 for mobile robot navigation: Evaluation and modeling," in 2015 International Conference on Advanced Robotics (ICAR), 2015, pp. 388-394: IEEE.
[32] 林牧衡, "太空載具三維姿態自我感知與登陸決策," 2019.
[33] H. Edelsbrunner, D. Kirkpatrick, and R. Seidel, "On the shape of a set of points in the plane," IEEE Transactions on information theory, vol. 29, no. 4, pp. 551-559, 1983.