Abstract
Additive manufacturing (AM) is gaining attention because of its ability to design complex geometries. Direct energy deposition (DED), one of the AM processes, is widely used nowadays for its high deposition rate. When using DED process in manufacturing or repairing, it is important to know the melt pool dimensions as a function of processing parameters to obtain high deposition rate and avoid defects such as lack of fusion. In this study, we used the random forest (RF) algorithm to predict melt pool dimensions and compared the results against existing physics based lumped model by Doumanidis et al. [1]. The results show that RF model works well to predict the DED melt pool dimensions, where energy density and material volume deposited govern the dimensions. Further, we tested the ubiquitous semi-ellipsoidal shape assumption for DED cross section against the circular shape and found semi-ellipsoidal shape to be fair when deposition process is stable and free of defects. Overall, this study highlights the applicability of machine learning algorithms for small AM datasets.
Similar content being viewed by others
References
Doumanidis C, Kwak YM (2001) Geometry modeling and control by infrared and laser sensing in thermal manufacturing with material deposition. J Manuf Sci Eng. 123(1):45–52. https://doi.org/10.1115/1.1344898
Saboori A, Aversa A, Marchese G, Biamino S, Lombardi M, Fino P (2019) Application of directed energy deposition-based additive manufacturing in repair. Appl Sci. https://doi.org/10.3390/app9163316
Oh WJ, Lee WJ, Kim MS, Jeon JB, Shim DS (2019) Repairing additive-manufactured 316L stainless steel using direct energy deposition. Optics Laser Technol 117(April):6–17. https://doi.org/10.1016/j.optlastec.2019.04.012
Gibson I, Rosen D, Stucker B (2015) Additive manufacturing technologies. Springer, New York. https://doi.org/10.1007/978-1-4939-2113-3
Liu S, Shin YC (2019) Additive manufacturing of Ti6Al4V alloy: a review. Mater Des 164:107552. https://doi.org/10.1016/j.matdes.2018.107552
Wolff S, Lee T, Faierson E, Ehmann K, Cao J (2016) Anisotropic properties of directed energy deposition (DED)-processed Ti-6Al-4V. J Manuf Process 24:397–405. https://doi.org/10.1016/j.jmapro.2016.06.020
Choi J, Chang Y (2005) Characteristics of laser aided direct metal/material deposition process for tool steel. Int J Mach Tools Manuf 45(4–5):597–607. https://doi.org/10.1016/j.ijmachtools.2004.08.014
Shim DS, Baek GY, Seo JS, Shin GY, Kim KP, Lee KY (2016) Effect of layer thickness setting on deposition characteristics in direct energy deposition (DED) process. Optics Laser Technol 86:69–78. https://doi.org/10.1016/j.optlastec.2016.07.001
DebRoy T, Wei HL, Zuback JS, Mukherjee T, Elmer JW, Milewski JO et al (2018) Additive manufacturing of metallic components - Process, structure and properties. Prog Mater Sci 92:112–224. https://doi.org/10.1016/j.pmatsci.2017.10.001
Bayat M, Dong W, Thorborg J, To AC, Hattel JH (2021) A review of multi-scale and multi-physics simulations of metal additive manufacturing processes with focus on modeling strategies. Addit Manuf 47:102278. https://doi.org/10.1016/j.addma.2021.102278
Fox J, Beuth J (2013) Process mapping of transient melt pool response in wire feed e-beam additive manufacturing of Ti-6Al-4V. In: 24th international SFF symposium - an additive manufacturing conference, SFF 2013. pp 675–683
Gockel J, Beuth J (2013) Understanding Ti-6Al-4V microstructure control in additive manufacturing via process maps. In: Solid freeform fabrication proceedings. Univ. Tex. Austin. pp 666–674
Mukherjee T, Zhang W, DebRoy T (2017) An improved prediction of residual stresses and distortion in additive manufacturing. Comput Mater Sci 126:360–372. https://doi.org/10.1016/j.commatsci.2016.10.003
Gan Z, Yu G, He X, Li S (2017) Numerical simulation of thermal behavior and multicomponent mass transfer in direct laser deposition of co-base alloy on steel. Int J Heat Mass Transf 104:28–38. https://doi.org/10.1016/j.ijheatmasstransfer.2016.08.049
Bayat M, Nadimpalli VK, Biondani FG, Jafarzadeh S, Thorborg J, Tiedje NS et al (2021) On the role of the powder stream on the heat and fluid flow conditions during directed energy deposition of maraging steel-Multiphysics modeling and experimental validation. Addit Manuf. https://doi.org/10.1016/j.addma.2021.102021
Foteinopoulos P, Papacharalampopoulos A, Stavropoulos P (2018) On thermal modeling of additive manufacturing processes. CIRP J Manuf Sci Technol 20:66–83. https://doi.org/10.1016/j.cirpj.2017.09.007
Yan W, Lu Y, Jones K, Yang Z, Fox J, Witherell P et al (2020) Data-driven characterization of thermal models for powder-bed-fusion additive manufacturing. Addit Manuf 36:101503. https://doi.org/10.1016/j.addma.2020.101503
Gan Z, Jones KK, Lu Y, Liu WK (2021) Benchmark study of melted track geometries in laser powder bed fusion of inconel 625. Integr Mater Manuf Innov 10(2):177–195. https://doi.org/10.1007/s40192-021-00209-4
Stavropoulos P, Foteinopoulos P (2018) Modelling of additive manufacturing processes: a review and classification. Manuf Rev. https://doi.org/10.1051/mfreview/2017014
Lalas C, Tsirbas K, Salonitis K, Chryssolouris G (2007) An analytical model of the laser clad geometry. Int J Adv Manuf Technol 32:34–41. https://doi.org/10.1007/s00170-005-0318-0
Bamberger M, Kaplan WD, Medres B, Shepeleva L (1998) Calculation of process parameters for laser alloying and cladding. J Laser Appl 10:29–33. https://doi.org/10.2351/1.521829
Liu J, Li L (2005) Study on cross-section clad profile in coaxial single-pass cladding with a low-power laser. Optics Laser Technol 37:478–482. https://doi.org/10.1016/j.optlastec.2004.07.010
Wang Q, Li J, Gouge M, Nassar AR, Reutzel EW (2017) Physics-based multivariable modeling and feedback linearization control of melt-pool geometry and temperature in directed energy deposition. J Manuf Sci Eng 139(2):021013. https://doi.org/10.1115/1.4034304
Lee S, Peng J, Shin D, Choi YS (2019) Data analytics approach for melt-pool geometries in metal additive manufacturing. Sci Technol Adv Mater 20:972–978. https://doi.org/10.1080/14686996.2019.1671140
Xiong J, Zhang G, Hu J, Wu L (2014) Bead geometry prediction for robotic GMAW-based rapid manufacturing through a neural network and a second-order regression analysis. J Intell Manuf 25(1):157–163. https://doi.org/10.1007/s10845-012-0682-1
Caiazzo F, Caggiano A (2018) Laser direct metal deposition of 2024 al alloy: trace geometry prediction via machine learning. Materials. https://doi.org/10.3390/ma11030444
Guo S, Agarwal M, Cooper C, Tian Q, Gao RX, Guo W et al (2022) Machine learning for metal additive manufacturing: towards a physics-informed data-driven paradigm. J Manuf Syst 62:145–163. https://doi.org/10.1016/j.jmsy.2021.11.003
Bonnín Roca J, Vaishnav P, Fuchs ERH, Morgan MG (2016) Policy needed for additive manufacturing. Nat Mater 15(8):815–818. https://doi.org/10.1038/nmat4658
Teng C, Gong H, Szabo A, Dilip JJS, Ashby K, Zhang S et al (2016) Simulating melt pool shape and lack of fusion porosity for selective laser melting of cobalt chromium components. J Manuf Sci Eng. https://doi.org/10.1115/1.4034137
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction, Second Edition. 2nd ed. Springer series in statistics. Springer-Verlag, New York. Available from: https://www.springer.com/us/book/9780387848570
Grinsztajn L, Oyallon E, Varoquaux G (2022) Why do tree-based models still outperform deep learning on tabular data? NeurIPS 2022 Datasets and Benchmarks Track. Available from: https://arxiv.org/abs/2207.08815
James G, Witten D, Hastie T, Tibshirani R (2013) An introduction to statistical learning. vol. 103 of Springer Texts in Statistics. Springer, New York. https://doi.org/10.1007/978-1-4614-7138-7
Breiman L (2001) Random forests. Mach Learn 45(1):5–32. https://doi.org/10.1023/A:1010933404324
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830
Kottman M, Zhang S, McGuffin-Cawley J, Denney P, Narayanan BK (2015) Laser hot wire process: a novel process for near-net shape fabrication for high-throughput applications. JOM 67(3):622–628. https://doi.org/10.1007/s11837-014-1288-1
Voort GV Metallographic preparation of titanium and its alloys. Available from: https://vacaero.com/information-resources/metallography-with-george-vander-voort/1397-metallographic-preparation-of-titanium-and-its-alloys.html
Stockham A, Smith J (2008) Comparison between a super Gaussian and a ”True” top hat. Laser beam shaping IX. 7062. https://doi.org/10.1117/12.796074
Metel A, Stebulyanin M, Fedorov S, Okunkova A (2018) Power density distribution for laser additive manufacturing (SLM): potential, fundamentals and advanced applications. Technologies 7(1):5. https://doi.org/10.3390/technologies7010005
Acknowledgements
This work was supported by the Quality Made program led by Lockheed Martin under prime contract N00014-18-C-1026 from the Office of Naval Research. Andrew Huck, Glynn P. Adams, Edward A. Pierson, Prof. Peter Collins, Brandon Abranovic, Elizabeth Chang-Davidson, and Prof. Jack Beuth are thanked for fruitful discussions. Furthermore, collaborators from Colorado School of Mines, Prof. Branden Kappes (now at KMMD.io), Prof. Craig Brice, and Brandon King, for providing part of the data studied in this article.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest (such as honoraria; educational grants; participation in speakers’ bureaus; membership, employment, consultancies, stock ownership, or other equity interest; and expert testimony or patent-licensing arrangements), or non-financial interest (such as personal or professional relationships, affiliations, knowledge or beliefs) in the subject matter or materials discussed in this manuscript.
Rights and permissions
About this article
Cite this article
Yang, Z., Verma, A.K., Smith, L. et al. Predicting Melt Pool Dimensions for Wire-Feed Directed Energy Deposition Process. Integr Mater Manuf Innov 11, 532–544 (2022). https://doi.org/10.1007/s40192-022-00278-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40192-022-00278-z