金屬積層製造是近年製造領域發產趨勢之一，其提供強大的客製化能力。然而，因其複雜的製程特性，包含雷射變異、粉末的顆粒尺寸、加工位置及風場變化等，即使在相同的製程條件下，生產品質也會有所差異。而生產過程中，瑕疵的發生會損耗時間及材料成本，如能於加工過程中即時評估品質即可減少浪費，品質評估結果並可作為每層回饋控制的參考，進而提升良率。
為捕捉生產中的變化，積層製造機台通常會安裝高速攝影機來拍攝熔池，而大量的影像於短時間中處理完畢是一大挑戰。本論文應用全自動虛擬量測(Automatic Virtual Metrology, AVM）於智慧積層製造量測來達成此目標。透過影像特徵萃取，處理機上量測中同軸高速攝影機之大量影像，並整合熱溫機收集之溫度值，做為虛擬量測的製程特徵。藉由平行運算機制，在加工過程中，同步處理資料達到於次層列印間估測出品質結果。
案例分析中，分別驗證不同層數以及不同製程條件下之估測精度。在不同層數的驗證中，縱使真實製作過程中，無法實際量測到中間層的粗糙度變化，估測結果仍在精度內。而不同製程條件下的粗糙度及密度品質估測，皆有隨實際值趨勢變化。因此本研究能達到生產過程中，評估積層製造品質之能力，後續可做為每層回饋控制之參考。

Metal additive manufacturing, which provides strong customization capability, is a focus area of manufacturing recently. However, the production quality varies even under identical process condition. The problem arises from laser variance, powder size distribution, printing position and airflow change. The defects in production result in time waste and material loss. To reduce the cost, the production quality should be estimated in real time. The estimated results can be a reference of layer-to-layer control for yield enhancement.
To collect the production variances, an AM machine is usually equipped with the high-speed camera to capture the melt-pool images. However, it is a challenge to process huge data timely. This research applies automatic virtual metrology (AVM) in the intelligent additive manufacturing metrology (IAMM) scheme to solve the problem. Through extracting image features to handle huge-volume images of the in-situ coaxial camera and integrating temperature data of the pyrometer, the process data will be converted into virtual metrology (VM) features. With parallel computing, the estimated results are conjectured in the next layer of real-time production.
The case studies verify the accuracy of various layers and different process conditions. Even when the roughness of the internal layers cannot be measured during production, the accuracy results still fall in the specification in the case of various layers. The estimated final roughness and overall density results of different conditions do follow the changes of physical measurement. This research helps to estimate the AM quality in real-time production with the results serving as a reference of layer-to-layer control.

[1] S.-H. Huang, P. Liu, A. Mokasdar and L. Hou, “Additive manufacturing and its societal impact: a literature review,” The International Journal of Advanced Manufacturing Technology, vol. 67, issue. 5-8, pp. 1191-1203, July 2013.
[2] Y. Kok, X. P. Tan, P. Wang, M. L. S. Nai, N. H. Loh, E. Liu, and S. B. Tor, “Anisotropy and heterogeneity of microstructure and mechanical properties in metal additive manufacturing: A critical review,” Materials & Design, col. 139, pp. 565-586, Feb. 2018.
[3] Y. Mostafa, E. Mohamed and S.C. Veldhuis, “A Review of Metal Additive Manufacturing Technologies,” Solid State Phenomena, vol. 278. pp. 1-14, July 2018.
[4] K-A Mumtaz, P. Erasenthiran and N. Hopkinson, “High density selective laser melting of Waspaloy,” Journal of Materials Processing Technology, vol. 195, issues 1–3, pp. 77-87, Jan. 2008
[5] W. E. Frazier, “Metal Additive Manufacturing: A Review,” Journal of Materials Engineering and Performance, vol. 23, pp.1917–1928, 2014.
[6] S.K. Everton, M. Hirsch, P. Stravroulakis, R.K. Leach, and A.T. Clare, “Review of in-situ process monitoring and in-situ metrology for metal additive manufacturing,” Materials and Design, vol. 95, pp. 431–445, 2016.
[7] W. Gao, Y. Zhang, D. Ramanujan, K. Ramani, Y. Chen, C. B. Williams, C. C. Wang, Y. C. Shin, S. Zhang, and P. D. Zavattieri, “The status, challenges, and future of additive manufacturing in engineering,” Computer-Aided Design, vol. 69, pp. 65–89, Dec. 2015.
[8] A. Khorasani, I. Gibson, U. S. Awan, and A. Ghaderi, “The effect of SLM process parameters on density, hardness, tensile strength and surface quality of Ti-6Al-4V,” Additive Manufacturing, vol. 25, pp. 176–186, Jan. 2019.
[9] D. Greitemeier, C. D. Donne, F. Syassen, J. Eufigner and T. Melz, “Effect of surface roughness on fatigue performance of additive manufactured Ti–6Al–4V,” Materials Science and Technology, vol. 32, issue 7, pp. 629-634, Jun. 2016.
[10] T. Craeghs, S. Clijsters, E. Yasa, F. Bechmann, S. Berumen, and J.-P. Kruth, “Determination of geometrical factors in Layerwise Laser Melting using optical process monitoring,” Optics and Lasers in Engineering, vol. 49, no. 12, pp. 1440–1446, Dec. 2011.
[11] F. Imani, A. Gaikwad, M. Montazeri, P. Rao, H. Yang and E. Reutzel, “Layerwise In-Process Quality Monitoring in Laser Powder Bed Fusion,” Proceedings of the ASME 2018 13th International Manufacturing Science and Engineering Conference, Texas, USA, vol. 1, June, 2018.
[12] B. Cheng and K. Chou, “Melt pool geometry simulations for powder-based electron beam additive manufacturing,” Proceedings of the 24th Annual International Solid Freeform Fabrication Symposium, Austin, USA, Aug, 2013.
[13] B. Cheng, J. Lydon, K. Cooper, J.V. Cole, P. Northrop and K. Chou, “Melt pool sensing and size analysis in laser powder-bed metal additive manufacturing,” Journal of Manufacturing Processes, vol. 32, pp. 744-753, April 2018.
[14] T. Kolb, P. Gebhardt, O. Schmidt, J. Tremel, and M. Schmidt, “Melt pool monitoring for laser beam melting of metals: assistance for material qualification for the stainless steel 1.4057,” Procedia CIRP, vol. 74, pp. 116–121, Jan., 2018.
[15] S. Berumen, F. Bechmann, S. Lindner, J.-P. Kruth and T. Craeghs, “Quality control of laser- and powder bed-based Additive Manufacturing (AM) technologies,” Physics Procedia, vol. 5, pp. 617-622, Dec., 2010
[16] L. Zheng, Q. Zhang, H. Cao, W. Wu, H. Ma, X. Ding, J. Yang, X. Duan, and S. Fan, “Melt pool boundary extraction and its width prediction from infrared images in selective laser melting,” Materials & Design, vol. 183, pp. 108-110, Aug., 2019.
[17] F.-T. Cheng, H.-C. Huang, and C.-A. Kao, “Developing an Automatic Virtual Metrology System,” IEEE Transactions on Automation Science and Engineering, vol. 9, no. 1, pp. 181-188, January 2012.
[18] H.-C. Yang, H. Tieng and F.-T. Cheng, “Automatic virtual metrology for wheel machining automation,” International Journal of Production Research, vol. 54, issue 21, pp. 6367-6376, Nov. 2015.
[19] F.-T Cheng, H.-C Huang and C.-A Kao, “Developing an Automatic Virtual Metrology System,” IEEE Transactions on Automation Science and Engineering, vol. 9, no. 1, pp. 181-188, Jan. 2012.
[20] H. Tieng, T. Tsai, C. Chen, H. Yang, J. Huang and F. Cheng, “Automatic Virtual Metrology and Deformation Fusion Scheme for Engine-Case Manufacturing,” IEEE Robotics and Automation Letters, vol. 3, no. 2, pp. 934-941, April 2018.
[21] Y. Hsieh, C. Lin, Y. Yang, M. Hung and F. Cheng, “Automatic Virtual Metrology for Carbon Fiber Manufacturing,” IEEE Robotics and Automation Letters, vol. 4, no. 3, pp. 2730-2737, July 2019.
[22] H. Yang, M. Adnan, C-H. Huang, F. Cheng, Y. Lo and C. Hsu, “An Intelligent Metrology Architecture With AVM for Metal Additive Manufacturing,” IEEE Robotics and Automation Letters, vol. 4, no. 3, pp. 2886-2893, July 2019.
[23] F.-T. Cheng, G-W. Huang, C.-H. Chen and M.-H. Hung, “Generic embedded device and mechanism thereof for various intelligent-maintenance applications,” US7162394B2, 2003.
[24] L. Ding and A. Goshtasby, “On the Canny Edge Detector,” Pattern Recognition, vol. 34, issue 3, pp. 721-725, Mar. 2001.