Abstract
We present a new computational approach for large-scale segmentation and spatially-resolved analysis of melt pools in complex 3D printed parts and qualification artifacts. Our hybrid segmentation includes human-in-the-loop image processing of a few representative optical images of melt pools that are then used for training machine learning models for automated segmentation of melt pool boundaries in large parts. Our approach specifically targets minimizing the need for manual annotation. Considering imperfect segmentation and errors unavoidable with most algorithms, we further propose chord length distribution as a statistical description of melt pool sizes relatively tolerant to segmentation errors. We first show and validate our new approach on optical images of melt pools in a simple 3D printed plate sample (IN718 alloy) as well as selected regions of a complex qualification artifact (AlSi10Mg alloy). We then demonstrate the application of our approach on an entire cross section of the artifact.
Similar content being viewed by others
Code availability
The codes for calculations of CLD/SR-CLD as well as for training/fine-tuning models for segmentation of melt pools are available at https://github.com/materialsinformaticsaz/meltpool_segment_and_chords.
Notes
We report the runtime of both models for a Lenovo NeXtScale nx360 M5 high-performance system with 28 CPU nodes having 6 GB memory/node.
References
Wohlers T, Caffrey T (2016) Additive manufacturing: the state of the industry. Manuf Eng 156(5):45–45
Wimpenny DI, Pandey PM, Kumar LJ et al (2017) Advances in 3D printing & additive manufacturing technologies. Springer, USA
Furton E, Nayir S, Beese AM (2023) Effect of size, location, and aspect ratio of internal pores on failure behavior of laser powder bed fusion Ti-6AL-4V. JOM 75(6):1953–1963
Luo Q, Yin L, Simpson TW, Beese AM (2022) Effect of processing parameters on pore structures, grain features, and mechanical properties in Ti-6AL-4V by laser powder bed fusion. Addit Manuf 56:102915
Ali H, Ghadbeigi H, Mumtaz K (2018) Processing parameter effects on residual stress and mechanical properties of selective laser melted Ti-6AL-4V. J Mater Eng Perform 27:4059–4068
Trapp J, Rubenchik AM, Guss G, Matthews MJ (2017) In situ absorptivity measurements of metallic powders during laser powder-bed fusion additive manufacturing. Appl Mater Today 9:341–349
Metelkova J, Kinds Y, Kempen K, de Formanoir C, Witvrouw A, Van Hooreweder B (2018) On the influence of laser defocusing in selective laser melting of 316L. Addit Manuf 23:161–169
Ioannidou C, König H-H, Semjatov N, Ackelid U, Staron P, Koerner C, Hedström P, Lindwall G (2022) In-situ synchrotron x-ray analysis of metal additive manufacturing: current state, opportunities and challenges. Mater Design 219:110790
Martin AA, Calta NP, Hammons JA, Khairallah SA, Nielsen MH, Shuttlesworth RM, Sinclair N, Matthews MJ, Jeffries JR, Willey TM et al (2019) Ultrafast dynamics of laser-metal interactions in additive manufacturing alloys captured by in situ x-ray imaging. Mater Today Adv 1:100002
Amato K, Gaytan S, Murr LE, Martinez E, Shindo P, Hernandez J, Collins S, Medina F (2012) Microstructures and mechanical behavior of Inconel 718 fabricated by selective laser melting. Acta Mater 60(5):2229–2239
Criales LE, Arısoy YM, Lane B, Moylan S, Donmez A, Özel T (2017) Laser powder bed fusion of nickel alloy 625: experimental investigations of effects of process parameters on melt pool size and shape with spatter analysis. Int J Mach Tools Manuf 121:22–36
Ghosh S, Ma L, Levine LE, Ricker RE, Stoudt MR, Heigel JC, Guyer JE (2018) Single-track melt-pool measurements and microstructures in Inconel 625. JOM 70:1011–1016
Ocylok S, Alexeev E, Mann S, Weisheit A, Wissenbach K, Kelbassa I (2014) Correlations of melt pool geometry and process parameters during laser metal deposition by coaxial process monitoring. Phys Procedia 56:228–238
Keshavarzkermani A, Marzbanrad E, Esmaeilizadeh R, Mahmoodkhani Y, Ali U, Enrique PD, Zhou NY, Bonakdar A, Toyserkani E (2019) An investigation into the effect of process parameters on melt pool geometry, cell spacing, and grain refinement during laser powder bed fusion. Optics Laser Technol 116:83–91
Mair P, Braun J, Kaserer L, March L, Schimbäck D, Letofsky-Papst I, Leichtfried G (2022) Unique microstructure evolution of a novel Ti-modified Al-Cu alloy processed using laser powder bed fusion. Mater Today Commun 31:103353
Moylan S, Cooke A, Donmez MA, Jurrens K, Slotwinski J (2012) A review of test artifacts for additive manufacturing
Monzón M, Ortega Z, Martínez A, Ortega F (2015) Standardization in additive manufacturing: activities carried out by international organizations and projects. Int J Adv Manufact Technol 76:1111–1121
Taylor H, Garibay E, Wicker R (2021) Toward a common laser powder bed fusion qualification test artifact. Addit Manuf 39:101803
Schmid S, Krabusch J, Schromm T, Jieqing S, Ziegelmeier S, Grosse CU, Schleifenbaum JH (2021) A new approach for automated measuring of the melt pool geometry in laser-powder bed fusion. Progress Addit Manuf 6:269–279
Global test artifact data exchange program. https://gtadexp.org/, accessed: 2023-08-16
Meijering E, Jacob M, Sarria J-C, Steiner P, Hirling H, Unser EM (2004) Design and validation of a tool for neurite tracing and analysis in fluorescence microscopy images. Cytom Part A J Int Soc Anal Cytol 58(2):167–176
Ng CC, Yap MH, Costen N, Li B (2015) Automatic wrinkle detection using hybrid hessian filter. In: Computer Vision–ACCV 2014: 12th Asian conference on computer vision, Singapore, Singapore, November 1-5, 2014, Revised Selected Papers, Part III 12, Springer, 2015, pp 609–622
Ridge operators. https://scikit-image.org/docs/stable/auto_examples/edges/plot_ridge_filter.html, accessed: 2023-08-16
Lorenz C, Carlsen IC, Buzug TM, Fassnacht C, Weese J (1997) A multi-scale line filter with automatic scale selection based on the hessian matrix for medical image segmentation. In: Scale-space theory in computer vision: first international conference, Scale-Space’97 Utrecht, The Netherlands, July 2–4, 1997 Proceedings 1, Springer, 1997, pp 152–163
Van der Walt S, Schönberger JL, Nunez-Iglesias J, Boulogne F, Warner JD, Yager N, Gouillart E, Yu T (2014) Scikit-image: image processing in python. PeerJ 2:e453
Stuckner J, Harder B, Smith TM (2022) Microstructure segmentation with deep learning encoders pre-trained on a large microscopy dataset. Npj Comput Mater 8(1):200
Buslaev A, Iglovikov VI, Khvedchenya E, Parinov A, Druzhinin M, Kalinin AA (2020) Albumentations: fast and flexible image augmentations. Information 11(2):125. https://doi.org/10.3390/info11020125
Taha AA, Hanbury A (2015) Metrics for evaluating 3d medical image segmentation: analysis, selection, and tool. BMC Med Imag 15(1):1–28
Torquato S, Lu B (1993) Chord-length distribution function for two-phase random media. Phys Rev E 47(4):2950
ASTM Standard, E112-13 (2013) Standard test methods for determining average grain size, ASTM International, West Conshohocken, PA. https://doi.org/10.1520/E0112
Standard ASTM, E1382–97 (2015) Standard test methods for determining average grain size using semiautomatic and automatic image analysis. ASTM International, West Conshohocken, PA. https://doi.org/10.1520/E1382-97R15
ASTM Standard, ASTM E1181-02 (2015) Standard test methods for characterizing duplex grain sizes, ASTM International, West Conshohocken, PA. https://doi.org/10.1520/E1181-02R15
Turner DM, Niezgoda SR, Kalidindi SR (2016) Efficient computation of the angularly resolved chord length distributions and lineal path functions in large microstructure datasets. Modell Simul Mater Sci Eng 24(7):075002
Latypov MI, Kühbach M, Beyerlein IJ, Stinville J-C, Toth LS, Pollock TM, Kalidindi SR (2018) Application of chord length distributions and principal component analysis for quantification and representation of diverse polycrystalline microstructures. Mater Charact 145:671–685
Whitman SE, Latypov MI, SR-CLD: spatially resolved chord length distribution for quantification and visualization of heterogeneous microstructures, Pending submission
Acknowledgements
SEW acknowledges the support by the National Science Foundation Graduate Research Fellowship Program under Grant No. DGE-2137419. The images used in this research were part of the Global Test Artifact Data Exchange Program (GTADExP)—an effort at The University of Texas at El Paso (UTEP) within the W.M. Keck Center for 3D Innovation. The authors are grateful to the many UTEP students associated with GTADExP and specifically Oscar Garcia and Luis Tarango, who prepared the samples and images for the study described here. For this research, the GTADExP program was sponsored, in part, through award 70NANB21H006 from the U.S. Department of Commerce, National Institute of Standards and Technology (NIST). Additional support at UTEP was provided by strategic investments via discretionary UTEP Keck Center funds and the Mr. and Mrs. MacIntosh Murchison Chair I in Engineering Endowment. Finally, the authors acknowledge High Performance Computing resources supported by the University of Arizona TRIF, UITS, and the Office of Research, Innovation, and Impact, and maintained by the UArizona Research Technologies Department. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the National Science Foundation, the U.S. Department of Commerce, NIST, or the U.S. Government.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Whitman, S.E., Hu, G., Taylor, H.C. et al. Automated Segmentation and Chord Length Distribution of Melt Pools in Complex 3D Printed Metal Artifacts. Integr Mater Manuf Innov 13, 229–243 (2024). https://doi.org/10.1007/s40192-023-00329-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40192-023-00329-z