Machine learning–aided real-time detection of keyhole pore generation in laser powder bed fusion

Ren, Zhongshu; Gao, Lin; Clark, Samuel J.; Fezzaa, Kamel; Shevchenko, Pavel; Choi, Ann; Everhart, Wes; Rollett, Anthony D.; Chen, Lianyi; Sun, Tao

doi:10.1126/science.add4667

Machine learning–aided real-time detection of keyhole pore generation in laser powder bed fusion

Journal Article · Thu Jan 05 23:00:00 EST 2023 · Science

DOI:https://doi.org/10.1126/science.add4667· OSTI ID:1963710

^[1]; ^[1]; ^[2]; ^[2]; ^[2]; ^[3]; ^[4]; ^[5]; ^[6]; ^[1]

Univ. of Virginia, Charlottesville, VA (United States)
Argonne National Laboratory (ANL), Argonne, IL (United States)
Kansas City National Security Campus (KCNSC), Kansas City, MO (United States); Carnegie Mellon Univ., Pittsburgh, PA (United States)
Kansas City National Security Campus (KCNSC), Kansas City, MO (United States)
Carnegie Mellon Univ., Pittsburgh, PA (United States)
Univ. of Wisconsin, Madison, WI (United States)

Porosity defects are currently a major factor that hinders the widespread adoption of laser-based metal additive manufacturing technologies. One common porosity occurs when an unstable vapor depression zone (keyhole) forms because of excess laser energy input. With simultaneous high-speed synchrotron x-ray imaging and thermal imaging, coupled with multiphysics simulations, we discovered two types of keyhole oscillation in laser powder bed fusion of Ti-6Al-4V. Amplifying this understanding with machine learning, we developed an approach for detecting the stochastic keyhole porosity generation events with submillisecond temporal resolution and near-perfect prediction rate. Finally, the highly accurate data labeling enabled by operando x-ray imaging allowed us to demonstrate a facile and practical way to adopt our approach in commercial systems.

View Accepted Manuscript (DOE)

Research Organization:: Kansas City Nuclear Security Campus (KCNSC), Kansas City, MO (United States); Argonne National Laboratory (ANL), Argonne, IL (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA); USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF)

Grant/Contract Number:: NA0002839; AC02-06CH11357

OSTI ID:: 1963710

Alternate ID(s):: OSTI ID: 2404323

Report Number(s):: NSC--614-4577

Journal Information:: Science, Journal Name: Science Journal Issue: 6627 Vol. 379; ISSN 0036-8075

Publisher:: AAASCopyright Statement

Country of Publication:: United States

Language:: English

References (49)

Cross-Validation Refaeilzadeh, Payam; Tang, Lei; Liu, Huan Encyclopedia of Database Systems https://doi.org/10.1007/978-0-387-39940-9_565	book	January 2009
Model Validation, Machine Learning Wang, Haiying; Zheng, Huiru Encyclopedia of Systems Biology https://doi.org/10.1007/978-1-4419-9863-7_233	book	January 2013
Thermophysical Properties of Solid and Liquid Ti-6Al-4V (TA6V) Alloy Boivineau, M.; Cagran, C.; Doytier, D. International Journal of Thermophysics, Vol. 27, Issue 2 https://doi.org/10.1007/PL00021868	journal	March 2006
In Situ Analysis of Laser Powder Bed Fusion Using Simultaneous High-Speed Infrared and X-ray Imaging Gould, Benjamin; Wolff, Sarah; Parab, Niranjan JOM, Vol. 73, Issue 1 https://doi.org/10.1007/s11837-020-04291-5	journal	July 2020
Laser powder-bed fusion additive manufacturing: Physics of complex melt flow and formation mechanisms of pores, spatter, and denudation zones Khairallah, Saad A.; Anderson, Andrew T.; Rubenchik, Alexander Acta Materialia, Vol. 108 https://doi.org/10.1016/j.actamat.2016.02.014	journal	April 2016
Fluid and particle dynamics in laser powder bed fusion Bidare, P.; Bitharas, I.; Ward, R. M. Acta Materialia, Vol. 142 https://doi.org/10.1016/j.actamat.2017.09.051	journal	January 2018
Onset of periodic oscillations as a precursor of a transition to pore-generating turbulence in laser melting Khairallah, Saad A.; Sun, Tao; Simonds, Brian J. Additive Manufacturing Letters, Vol. 1 https://doi.org/10.1016/j.addlet.2021.100002	journal	December 2021
An open-architecture metal powder bed fusion system for in-situ process measurements Bidare, P.; Maier, R. R. J.; Beck, R. J. Additive Manufacturing, Vol. 16 https://doi.org/10.1016/j.addma.2017.06.007	journal	August 2017
Acoustic emission for in situ quality monitoring in additive manufacturing using spectral convolutional neural networks Shevchik, S. A.; Kenel, C.; Leinenbach, C. Additive Manufacturing, Vol. 21 https://doi.org/10.1016/j.addma.2017.11.012	journal	May 2018
Keyhole-induced porosities in Laser-based Powder Bed Fusion (L-PBF) of Ti6Al4V: High-fidelity modelling and experimental validation Bayat, Mohamad; Thanki, Aditi; Mohanty, Sankhya Additive Manufacturing, Vol. 30 https://doi.org/10.1016/j.addma.2019.100835	journal	December 2019
Observing molten pool surface oscillations during keyhole processing in laser powder bed fusion as a novel method to estimate the penetration depth Caprio, Leonardo; Demir, Ali Gökhan; Previtali, Barbara Additive Manufacturing, Vol. 36 https://doi.org/10.1016/j.addma.2020.101470	journal	December 2020
Visualisation and numerical analysis of laser powder bed fusion under cross-flow Bitharas, I.; Burton, A.; Ross, A. J. Additive Manufacturing, Vol. 37 https://doi.org/10.1016/j.addma.2020.101690	journal	January 2021
Detection of keyhole pore formations in laser powder-bed fusion using acoustic process monitoring measurements Tempelman, Joshua R.; Wachtor, Adam J.; Flynn, Eric B. Additive Manufacturing, Vol. 55 https://doi.org/10.1016/j.addma.2022.102735	journal	July 2022
A physics-driven deep learning model for process-porosity causal relationship and porosity prediction with interpretability in laser metal deposition Guo, Weihong "Grace"; Tian, Qi; Guo, Shenghan CIRP Annals, Vol. 69, Issue 1 https://doi.org/10.1016/j.cirp.2020.04.049	journal	January 2020
Observation of keyhole-mode laser melting in laser powder-bed fusion additive manufacturing King, Wayne E.; Barth, Holly D.; Castillo, Victor M. Journal of Materials Processing Technology, Vol. 214, Issue 12 https://doi.org/10.1016/j.jmatprotec.2014.06.005	journal	December 2014
Monitoring and prediction of porosity in laser powder bed fusion using physics-informed meltpool signatures and machine learning Smoqi, Ziyad; Gaikwad, Aniruddha; Bevans, Benjamin Journal of Materials Processing Technology, Vol. 304 https://doi.org/10.1016/j.jmatprotec.2022.117550	journal	June 2022
Design of an interpretable Convolutional Neural Network for stress concentration prediction in rough surfaces Kantzos, Christopher; Lao, Jacky; Rollett, Anthony Materials Characterization, Vol. 158 https://doi.org/10.1016/j.matchar.2019.109961	journal	December 2019
Review of in-situ process monitoring and in-situ metrology for metal additive manufacturing Everton, Sarah K.; Hirsch, Matthias; Stravroulakis, Petros Materials & Design, Vol. 95 https://doi.org/10.1016/j.matdes.2016.01.099	journal	April 2016
Angular dependence of coaxial and quasi-coaxial monitoring systems for process radiation analysis in laser materials processing Brandau, Benedikt; Mai, Torsten; Brueckner, Frank Optics and Lasers in Engineering, Vol. 155 https://doi.org/10.1016/j.optlaseng.2022.107050	journal	August 2022
Dynamic features of plasma plume and molten pool in laser lap welding based on image monitoring and processing techniques Meng, Wei; Yin, Xiaohui; Fang, Junfei Optics & Laser Technology, Vol. 109 https://doi.org/10.1016/j.optlastec.2018.07.073	journal	January 2019
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
Dynamics of pore formation during laser powder bed fusion additive manufacturing Martin, Aiden A.; Calta, Nicholas P.; Khairallah, Saad A. Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-019-10009-2	journal	April 2019
Universal scaling laws of keyhole stability and porosity in 3D printing of metals Gan, Zhengtao; Kafka, Orion L.; Parab, Niranjan Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-22704-0	journal	April 2021
Keyhole fluctuation and pore formation mechanisms during laser powder bed fusion additive manufacturing Huang, Yuze; Fleming, Tristan G.; Clark, Samuel J. Nature Communications, Vol. 13, Issue 1 https://doi.org/10.1038/s41467-022-28694-x	journal	March 2022
Scientific, technological and economic issues in metal printing and their solutions DebRoy, T.; Mukherjee, T.; Milewski, J. O. Nature Materials, Vol. 18, Issue 10 https://doi.org/10.1038/s41563-019-0408-2	journal	July 2019
Metallurgy, mechanistic models and machine learning in metal printing DebRoy, T.; Mukherjee, T.; Wei, H. L. Nature Reviews Materials, Vol. 6, Issue 1 https://doi.org/10.1038/s41578-020-00236-1	journal	October 2020
Metal vapor micro-jet controls material redistribution in laser powder bed fusion additive manufacturing Ly, Sonny; Rubenchik, Alexander M.; Khairallah, Saad A. Scientific Reports, Vol. 7, Issue 1 https://doi.org/10.1038/s41598-017-04237-z	journal	June 2017
Supervised deep learning for real-time quality monitoring of laser welding with X-ray radiographic guidance Shevchik, Sergey; Le-Quang, Tri; Meylan, Bastian Scientific Reports, Vol. 10, Issue 1 https://doi.org/10.1038/s41598-020-60294-x	journal	February 2020
Assessment of optical emission analysis for in-process monitoring of powder bed fusion additive manufacturing Dunbar, Alexander J.; Nassar, Abdalla R. Virtual and Physical Prototyping, Vol. 13, Issue 1 https://doi.org/10.1080/17452759.2017.1392683	journal	October 2017
Differentiation of materials and laser powder bed fusion processing regimes from airborne acoustic emission combined with machine learning Drissi-Daoudi, Rita; Pandiyan, Vigneashwara; Logé, Roland Virtual and Physical Prototyping, Vol. 17, Issue 2 https://doi.org/10.1080/17452759.2022.2028380	journal	February 2022
A model of deep penetration laser welding based on calculation of the keyhole profile Kaplan, A. Journal of Physics D: Applied Physics, Vol. 27, Issue 9 https://doi.org/10.1088/0022-3727/27/9/002	journal	September 1994
Melt pool dynamics during laser welding Semak, V. V.; Hopkins, J. A.; McCay, M. H. Journal of Physics D: Applied Physics, Vol. 28, Issue 12 https://doi.org/10.1088/0022-3727/28/12/008	journal	December 1995
The role of recoil pressure in energy balance during laser materials processing Semak, Vladimir; Matsunawa, Akira Journal of Physics D: Applied Physics, Vol. 30, Issue 18 https://doi.org/10.1088/0022-3727/30/18/008	journal	September 1997
Experimental study of the dynamical coupling between the induced vapour plume and the melt pool for Nd–Yag CW laser welding Fabbro, Rémy; Slimani, Sonia; Doudet, Ivan Journal of Physics D: Applied Physics, Vol. 39, Issue 2 https://doi.org/10.1088/0022-3727/39/2/023	journal	January 2006
Implementation of real-time multiple reflection and Fresnel absorption of laser beam in keyhole Cho, Jung-Ho; Na, Suck-Joo Journal of Physics D: Applied Physics, Vol. 39, Issue 24 https://doi.org/10.1088/0022-3727/39/24/039	journal	December 2006
Process defects and in situ monitoring methods in metal powder bed fusion: a review Grasso, Marco; Colosimo, Bianca Maria Measurement Science and Technology, Vol. 28, Issue 4 https://doi.org/10.1088/1361-6501/aa5c4f	journal	February 2017
Time-Resolved Absorptance and Melt Pool Dynamics during Intense Laser Irradiation of a Metal Simonds, Brian J.; Sowards, Jeffrey; Hadler, Josh Physical Review Applied, Vol. 10, Issue 4 https://doi.org/10.1103/PhysRevApplied.10.044061	journal	October 2018
Effect of Laser-Matter Interaction on Molten Pool Flow and Keyhole Dynamics Kouraytem, Nadia; Li, Xuxiao; Cunningham, Ross Physical Review Applied, Vol. 11, Issue 6 https://doi.org/10.1103/PhysRevApplied.11.064054	journal	June 2019
Bulk-Explosion-Induced Metal Spattering During Laser Processing Zhao, Cang; Guo, Qilin; Li, Xuxiao Physical Review X, Vol. 9, Issue 2 https://doi.org/10.1103/PhysRevX.9.021052	journal	June 2019
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization Selvaraju, Ramprasaath R.; Cogswell, Michael; Das, Abhishek 2017 IEEE International Conference on Computer Vision (ICCV) https://doi.org/10.1109/ICCV.2017.74	conference	October 2017
Metal mirrors with metal-dielectric HR-coating for ultrashort laser pulses applied in scanner applications Schürmann, M.; Risse, S.; Kämmer, H. Laser-based Micro- and Nanoprocessing IX https://doi.org/10.1117/12.2079487	conference	March 2015
Keyhole threshold and morphology in laser melting revealed by ultrahigh-speed x-ray imaging Cunningham, Ross; Zhao, Cang; Parab, Niranjan Science, Vol. 363, Issue 6429 https://doi.org/10.1126/science.aav4687	journal	February 2019
Crystal symmetry determination in electron diffraction using machine learning Kaufmann, Kevin; Zhu, Chaoyi; Rosengarten, Alexander S. Science, Vol. 367, Issue 6477 https://doi.org/10.1126/science.aay3062	journal	January 2020
Controlling interdependent meso-nanosecond dynamics and defect generation in metal 3D printing Khairallah, Saad A.; Martin, Aiden A.; Lee, Jonathan R. I. Science, Vol. 368, Issue 6491 https://doi.org/10.1126/science.aay7830	journal	May 2020
Critical instability at moving keyhole tip generates porosity in laser melting Zhao, Cang; Parab, Niranjan D.; Li, Xuxiao Science, Vol. 370, Issue 6520 https://doi.org/10.1126/science.abd1587	journal	November 2020
In-process sensing in selective laser melting (SLM) additive manufacturing Spears, Thomas G.; Gold, Scott A. Integrating Materials and Manufacturing Innovation, Vol. 5, Issue 1 https://doi.org/10.1186/s40192-016-0045-4	journal	February 2016
In situ / operando synchrotron x-ray studies of metal additive manufacturing Sun, Tao; Tan, Wenda; Chen, Lianyi MRS Bulletin, Vol. 45, Issue 11 https://doi.org/10.1557/mrs.2020.275	journal	November 2020
Optical emission sensing for laser-based additive manufacturing—What are we actually measuring? Stutzman, Christopher B.; Mitchell, Wesley F.; Nassar, Abdalla R. Journal of Laser Applications, Vol. 33, Issue 1 https://doi.org/10.2351/7.0000321	journal	February 2021
ECG Classification Using Wavelet Packet Entropy and Random Forests Li, Taiyong; Zhou, Min Entropy, Vol. 18, Issue 8 https://doi.org/10.3390/e18080285	journal	August 2016

Similar Records

Critical instability at moving keyhole tip generates porosity in laser melting

Journal Article · Wed Nov 25 23:00:00 EST 2020 · Science · OSTI ID:1724317

Related Subjects

42 ENGINEERING

Machine learning–aided real-time detection of keyhole pore generation in laser powder bed fusion

Citation Formats

References (49)

Similar Records

Related Subjects