Photodiode-based machine learning for optimization of laser powder bed fusion parameters in complex geometries
Abstract
We report the quality of parts produced through laser powder bed fusion additive manufacturing can be irregular, with complex geometries sometimes exhibiting dimensional inaccuracies and defects. For optimal part quality, laser process parameters should be selected carefully prior to printing and adjusted during the print if necessary. This is challenging since approaches to control and optimize the build parameters need to take into account the part geometry, the material, and the complex physics of laser powder bed fusion. This work describes a data-driven approach using experimental diagnostics for the optimization of laser process parameters prior to printing. A training dataset is generated by collecting high speed photodiode signal data while printing simple parts containing key geometry features with various process parameter strategies. Supervised learning approaches are employed to train both a forward model and an inverse model. The forward model takes as inputs track-wise geometry features and laser parameters and outputs the photodiode signal along the scan path. The inverse model takes as inputs the geometry features and photodiode signal and predicts the laser parameters. Given the part geometry and a desired photodiode signal, the inverse model can thus determine the required laser parameters. Two test parts which contain defect-pronemore »
- Authors:
-
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
- Publication Date:
- Research Org.:
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA)
- OSTI Identifier:
- 1886148
- Alternate Identifier(s):
- OSTI ID: 1846997
- Report Number(s):
- LLNL-JRNL-821280
Journal ID: ISSN 2214-8604; 1033207
- Grant/Contract Number:
- AC52-07NA27344
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Additive Manufacturing
- Additional Journal Information:
- Journal Volume: 53; Journal Issue: N/A; Journal ID: ISSN 2214-8604
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 36 MATERIALS SCIENCE; additive manufacturing; laser powder bed fusion; photodiode; machine learning
Citation Formats
Lapointe, S., Guss, G., Reese, Z., Strantza, M., Matthews, M. J., and Druzgalski, C. L. Photodiode-based machine learning for optimization of laser powder bed fusion parameters in complex geometries. United States: N. p., 2022.
Web. doi:10.1016/j.addma.2022.102687.
Lapointe, S., Guss, G., Reese, Z., Strantza, M., Matthews, M. J., & Druzgalski, C. L. Photodiode-based machine learning for optimization of laser powder bed fusion parameters in complex geometries. United States. https://doi.org/10.1016/j.addma.2022.102687
Lapointe, S., Guss, G., Reese, Z., Strantza, M., Matthews, M. J., and Druzgalski, C. L. Sat .
"Photodiode-based machine learning for optimization of laser powder bed fusion parameters in complex geometries". United States. https://doi.org/10.1016/j.addma.2022.102687. https://www.osti.gov/servlets/purl/1886148.
@article{osti_1886148,
title = {Photodiode-based machine learning for optimization of laser powder bed fusion parameters in complex geometries},
author = {Lapointe, S. and Guss, G. and Reese, Z. and Strantza, M. and Matthews, M. J. and Druzgalski, C. L.},
abstractNote = {We report the quality of parts produced through laser powder bed fusion additive manufacturing can be irregular, with complex geometries sometimes exhibiting dimensional inaccuracies and defects. For optimal part quality, laser process parameters should be selected carefully prior to printing and adjusted during the print if necessary. This is challenging since approaches to control and optimize the build parameters need to take into account the part geometry, the material, and the complex physics of laser powder bed fusion. This work describes a data-driven approach using experimental diagnostics for the optimization of laser process parameters prior to printing. A training dataset is generated by collecting high speed photodiode signal data while printing simple parts containing key geometry features with various process parameter strategies. Supervised learning approaches are employed to train both a forward model and an inverse model. The forward model takes as inputs track-wise geometry features and laser parameters and outputs the photodiode signal along the scan path. The inverse model takes as inputs the geometry features and photodiode signal and predicts the laser parameters. Given the part geometry and a desired photodiode signal, the inverse model can thus determine the required laser parameters. Two test parts which contain defect-prone features are used to assess the validity of the inverse model. The use of the model leads to improved part quality (higher dimensional accuracy, reduced dross, reduced distortion) for both test geometries.},
doi = {10.1016/j.addma.2022.102687},
journal = {Additive Manufacturing},
number = N/A,
volume = 53,
place = {United States},
year = {Sat Feb 26 00:00:00 EST 2022},
month = {Sat Feb 26 00:00:00 EST 2022}
}
Works referenced in this record:
Process defects and in situ monitoring methods in metal powder bed fusion: a review
journal, February 2017
- Grasso, Marco; Colosimo, Bianca Maria
- Measurement Science and Technology, Vol. 28, Issue 4
Process observation in fiber laser–based selective laser melting
journal, October 2014
- Thombansen, Ulrich; Gatej, Alexander; Pereira, Milton
- Optical Engineering, Vol. 54, Issue 1
Livermore tomography tools: Accurate, fast, and flexible software for tomographic science
journal, March 2022
- Champley, Kyle M.; Willey, Trevor M.; Kim, Hyojin
- NDT & E International, Vol. 126
Parametric analysis of the selective laser melting process
journal, July 2007
- Yadroitsev, I.; Bertrand, Ph.; Smurov, I.
- Applied Surface Science, Vol. 253, Issue 19
Model assisted closed-loop control strategy for selective laser melting
journal, January 2018
- Renken, Volker; Lübbert, Lutz; Blom, Hendrik
- Procedia CIRP, Vol. 74
Controlling interdependent meso-nanosecond dynamics and defect generation in metal 3D printing
journal, May 2020
- Khairallah, Saad A.; Martin, Aiden A.; Lee, Jonathan R. I.
- Science, Vol. 368, Issue 6491
Temperature Profile and Imaging Analysis of Laser Additive Manufacturing of Stainless Steel
journal, January 2013
- Islam, M.; Purtonen, T.; Piili, H.
- Physics Procedia, Vol. 41
Investigation of Melt Pool Geometry Control in Additive Manufacturing Using Hybrid Modeling
journal, May 2020
- Mondal, Sudeepta; Gwynn, Daniel; Ray, Asok
- Metals, Vol. 10, Issue 5
Feedback control of Layerwise Laser Melting using optical sensors
journal, January 2010
- Craeghs, Tom; Bechmann, Florian; Berumen, Sebastian
- Physics Procedia, Vol. 5
Gaussian process-based surrogate modeling framework for process planning in laser powder-bed fusion additive manufacturing of 316L stainless steel
journal, September 2017
- Tapia, Gustavo; Khairallah, Saad; Matthews, Manyalibo
- The International Journal of Advanced Manufacturing Technology, Vol. 94, Issue 9-12
Metallurgy, mechanistic models and machine learning in metal printing
journal, October 2020
- DebRoy, T.; Mukherjee, T.; Wei, H. L.
- Nature Reviews Materials, Vol. 6, Issue 1
Adaptive Control of Thermal Processes: Laser Welding and Additive Manufacturing Paradigms
journal, January 2018
- Papacharalampopoulos, Alexios; Stavropoulos, Panagiotis; Stavridis, John
- Procedia CIRP, Vol. 67
Additive manufacturing: scientific and technological challenges, market uptake and opportunities
journal, January 2018
- Tofail, Syed A. M.; Koumoulos, Elias P.; Bandyopadhyay, Amit
- Materials Today, Vol. 21, Issue 1
Metal additive-manufacturing process and residual stress modeling
journal, February 2016
- Megahed, Mustafa; Mindt, Hans-Wilfried; N’Dri, Narcisse
- Integrating Materials and Manufacturing Innovation, Vol. 5, Issue 1
In-process sensing in selective laser melting (SLM) additive manufacturing
journal, February 2016
- Spears, Thomas G.; Gold, Scott A.
- Integrating Materials and Manufacturing Innovation, Vol. 5, Issue 1
Thermal field prediction for laser scanning paths in laser aided additive manufacturing by physics-based machine learning
journal, April 2020
- Ren, K.; Chew, Y.; Zhang, Y. F.
- Computer Methods in Applied Mechanics and Engineering, Vol. 362
Implementation of a thermomechanical model for the simulation of selective laser melting
journal, April 2014
- Hodge, N. E.; Ferencz, R. M.; Solberg, J. M.
- Computational Mechanics, Vol. 54, Issue 1
Review of laser welding monitoring
journal, December 2013
- You, D. Y.; Gao, X. D.; Katayama, S.
- Science and Technology of Welding and Joining, Vol. 19, Issue 3
In situ monitoring of selective laser melting using plume and spatter signatures by deep belief networks
journal, October 2018
- Ye, Dongsen; Hsi Fuh, Jerry Ying; Zhang, Yingjie
- ISA Transactions, Vol. 81
Research on molten pool temperature in the process of laser rapid forming
journal, March 2008
- Hua, Tan; Jing, Chen; Xin, Lin
- Journal of Materials Processing Technology, Vol. 198, Issue 1-3
Zoning additive manufacturing process histories using unsupervised machine learning
journal, March 2020
- Donegan, Sean P.; Schwalbach, Edwin J.; Groeber, Michael A.
- Materials Characterization, Vol. 161
Quality control of laser- and powder bed-based Additive Manufacturing (AM) technologies
journal, January 2010
- Berumen, Sebastian; Bechmann, Florian; Lindner, Stefan
- Physics Procedia, Vol. 5
Integration of physically-based and data-driven approaches for thermal field prediction in additive manufacturing
journal, February 2018
- Li, Jingran; Jin, Ran; Yu, Hang Z.
- Materials & Design, Vol. 139
Optical process monitoring for Laser-Powder Bed Fusion (L-PBF)
journal, November 2020
- Zouhri, W.; Dantan, J. Y.; Häfner, B.
- CIRP Journal of Manufacturing Science and Technology, Vol. 31
Scaling laws for the additive manufacturing
journal, July 2018
- Rubenchik, Alexander M.; King, Wayne E.; Wu, Sheldon S.
- Journal of Materials Processing Technology, Vol. 257
A methodology for precision additive manufacturing through compensation
journal, October 2017
- Afazov, Shukri; Okioga, Annestacy; Holloway, Adam
- Precision Engineering, Vol. 50
In situ quality control of the selective laser melting process using a high-speed, real-time melt pool monitoring system
journal, August 2014
- Clijsters, S.; Craeghs, T.; Buls, S.
- The International Journal of Advanced Manufacturing Technology, Vol. 75, Issue 5-8