skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Heterogeneous sensing and scientific machine learning for quality assurance in laser powder bed fusion – A single-track study

Abstract

Laser Powder Bed Fusion (LPBF) is the predominant metal additive manufacturing technique that benefits from a significant body of academic study and industrial investment given its ability to create complex geometry parts. Despite LPBF’s widespread use, there still exists a need for process monitoring to ensure reliable part production and reduce post-build quality assessments. Towards this end, we develop and evaluate machine learning-based predictive models using height map-derived quality metrics for single tracks and the accompanying pyrometer and high-speed video camera data collected under a wide range of laser power and laser velocity settings. We extract physically intuitive low-level features representative of the meltpool dynamics from these sensing modalities and explore how these vary with the linear energy density. We find our Sequential Decision Analysis Neural Network (SeDANN) model – a scientific machine learning model that incorporates physical process insights – outperforms other purely data-driven black box models in both accuracy and speed. The general approach to data curation and adaptable nature of SeDANN’s scientifically informed architecture should benefit LPBF systems with an evolving suite of sensing modalities and post-build quality measurements.

Authors:
; ; ; ; ;
Publication Date:
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1702002
Alternate Identifier(s):
OSTI ID: 1678853
Report Number(s):
LLNL-JRNL-808643
Journal ID: ISSN 2214-8604; S2214860420310319; 101659; PII: S2214860420310319
Grant/Contract Number:  
AC52-07NA27344
Resource Type:
Published Article
Journal Name:
Additive Manufacturing
Additional Journal Information:
Journal Name: Additive Manufacturing Journal Volume: 36 Journal Issue: C; Journal ID: ISSN 2214-8604
Publisher:
Elsevier
Country of Publication:
Netherlands
Language:
English
Subject:
36 MATERIALS SCIENCE; Laser powder bed fusion; in-situ quality monitoring; process-mapping; machine learning

Citation Formats

Gaikwad, Aniruddha, Giera, Brian, Guss, Gabriel M., Forien, Jean-Baptiste, Matthews, Manyalibo J., and Rao, Prahalada. Heterogeneous sensing and scientific machine learning for quality assurance in laser powder bed fusion – A single-track study. Netherlands: N. p., 2020. Web. https://doi.org/10.1016/j.addma.2020.101659.
Gaikwad, Aniruddha, Giera, Brian, Guss, Gabriel M., Forien, Jean-Baptiste, Matthews, Manyalibo J., & Rao, Prahalada. Heterogeneous sensing and scientific machine learning for quality assurance in laser powder bed fusion – A single-track study. Netherlands. https://doi.org/10.1016/j.addma.2020.101659
Gaikwad, Aniruddha, Giera, Brian, Guss, Gabriel M., Forien, Jean-Baptiste, Matthews, Manyalibo J., and Rao, Prahalada. Tue . "Heterogeneous sensing and scientific machine learning for quality assurance in laser powder bed fusion – A single-track study". Netherlands. https://doi.org/10.1016/j.addma.2020.101659.
@article{osti_1702002,
title = {Heterogeneous sensing and scientific machine learning for quality assurance in laser powder bed fusion – A single-track study},
author = {Gaikwad, Aniruddha and Giera, Brian and Guss, Gabriel M. and Forien, Jean-Baptiste and Matthews, Manyalibo J. and Rao, Prahalada},
abstractNote = {Laser Powder Bed Fusion (LPBF) is the predominant metal additive manufacturing technique that benefits from a significant body of academic study and industrial investment given its ability to create complex geometry parts. Despite LPBF’s widespread use, there still exists a need for process monitoring to ensure reliable part production and reduce post-build quality assessments. Towards this end, we develop and evaluate machine learning-based predictive models using height map-derived quality metrics for single tracks and the accompanying pyrometer and high-speed video camera data collected under a wide range of laser power and laser velocity settings. We extract physically intuitive low-level features representative of the meltpool dynamics from these sensing modalities and explore how these vary with the linear energy density. We find our Sequential Decision Analysis Neural Network (SeDANN) model – a scientific machine learning model that incorporates physical process insights – outperforms other purely data-driven black box models in both accuracy and speed. The general approach to data curation and adaptable nature of SeDANN’s scientifically informed architecture should benefit LPBF systems with an evolving suite of sensing modalities and post-build quality measurements.},
doi = {10.1016/j.addma.2020.101659},
journal = {Additive Manufacturing},
number = C,
volume = 36,
place = {Netherlands},
year = {2020},
month = {12}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1016/j.addma.2020.101659

Figures / Tables:

Figure 1 Figure 1: Optical microscopy images of single tracks deposited at different laser power and laser velocity. (a) a single-track with uniform edges and no discernable faults – characteristics that are desirable while building LPBF AM parts. (b) a single-track with inconsistent width, discontinuities, and surface damage. These single tracks aremore » not part of this work as they were deposited at different laser spot size, but the laser power and laser velocity settings were the same.« less

Save / Share:

Works referenced in this record:

Diode-based additive manufacturing of metals using an optically-addressable light valve
journal, January 2017

  • Matthews, Manyalibo J.; Guss, Gabe; Drachenberg, Derrek R.
  • Optics Express, Vol. 25, Issue 10
  • DOI: 10.1364/OE.25.011788

In-Process Monitoring of Material Cross-Contamination Defects in Laser Powder Bed Fusion
journal, July 2018

  • Montazeri, Mohammad; Yavari, Reza; Rao, Prahalada
  • Journal of Manufacturing Science and Engineering, Vol. 140, Issue 11
  • DOI: 10.1115/1.4040543

Single track formation in selective laser melting of metal powders
journal, September 2010


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
  • DOI: 10.1088/1361-6501/aa5c4f

Factor analysis of selective laser melting process parameters and geometrical characteristics of synthesized single tracks
journal, April 2012

  • Yadroitsev, Igor; Yadroitsava, Ina; Bertrand, Philippe
  • Rapid Prototyping Journal, Vol. 18, Issue 3
  • DOI: 10.1108/13552541211218117

On the limitations of Volumetric Energy Density as a design parameter for Selective Laser Melting
journal, January 2017


Deep Learning of Variant Geometry in Layerwise Imaging Profiles for Additive Manufacturing Quality Control
journal, September 2019

  • Imani, Farhad; Chen, Ruimin; Diewald, Evan
  • Journal of Manufacturing Science and Engineering, Vol. 141, Issue 11
  • DOI: 10.1115/1.4044420

Sensor-Based Build Condition Monitoring in Laser Powder Bed Fusion Additive Manufacturing Process Using a Spectral Graph Theoretic Approach
journal, June 2018

  • Montazeri, Mohammad; Rao, Prahalada
  • Journal of Manufacturing Science and Engineering, Vol. 140, Issue 9
  • DOI: 10.1115/1.4040264

In-process monitoring of porosity in additive manufacturing using optical emission spectroscopy
journal, October 2019


In-situ monitoring of melt pool images for porosity prediction in directed energy deposition processes
journal, March 2018


A review on measurement science needs for real-time control of additive manufacturing metal powder bed fusion processes
journal, February 2016

  • Mani, Mahesh; Lane, Brandon M.; Donmez, M. Alkan
  • International Journal of Production Research, Vol. 55, Issue 5
  • DOI: 10.1080/00207543.2016.1223378

The use of nano-computed tomography (nano-CT) in non-destructive testing of metallic parts made by laser powder-bed fusion additive manufacturing
journal, July 2018

  • Salarian, Mehrnaz; Toyserkani, Ehsan
  • The International Journal of Advanced Manufacturing Technology, Vol. 98, Issue 9-12
  • DOI: 10.1007/s00170-018-2421-z

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
  • DOI: 10.1126/science.aay7830

Layerwise Anomaly Detection in Laser Powder-Bed Fusion Metal Additive Manufacturing
journal, January 2019

  • Mahmoudi, Mohamad; Ezzat, Ahmed Aziz; Elwany, Alaa
  • Journal of Manufacturing Science and Engineering, Vol. 141, Issue 3
  • DOI: 10.1115/1.4042108

Modulating laser intensity profile ellipticity for microstructural control during metal additive manufacturing
journal, April 2017


Mapping and Modelling Single Scan Track Formation in Direct Metal Selective Laser Melting
journal, January 2004


Surface topography investigations on nickel alloy 625 fabricated via laser powder bed fusion
journal, October 2017

  • Özel, Tuğrul; Altay, Ayça; Donmez, Alkan
  • The International Journal of Advanced Manufacturing Technology, Vol. 94, Issue 9-12
  • DOI: 10.1007/s00170-017-1187-z

Observation of keyhole-mode laser melting in laser powder-bed fusion additive manufacturing
journal, December 2014


Progress Towards Metal Additive Manufacturing Standardization to Support Qualification and Certification
journal, February 2017


Selective laser melting of alumina: A single track study
journal, June 2018


Quality part production via multi-laser additive manufacturing
journal, August 2017


Denudation of metal powder layers in laser powder bed fusion processes
journal, August 2016


Additively manufactured hierarchical stainless steels with high strength and ductility
journal, October 2017

  • Wang, Y. Morris; Voisin, Thomas; McKeown, Joseph T.
  • Nature Materials, Vol. 17, Issue 1
  • DOI: 10.1038/nmat5021

Heat transfer modelling and stability analysis of selective laser melting
journal, December 2007


Energy input effect on morphology and microstructure of selective laser melting single track from metallic powder
journal, April 2013


Laser powder-bed fusion additive manufacturing: Physics of complex melt flow and formation mechanisms of pores, spatter, and denudation zones
journal, April 2016


In situ absorptivity measurements of metallic powders during laser powder-bed fusion additive manufacturing
journal, December 2017


A Computational Approach to Edge Detection
journal, November 1986

  • Canny, John
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-8, Issue 6
  • DOI: 10.1109/TPAMI.1986.4767851

Keyhole threshold and morphology in laser melting revealed by ultrahigh-speed x-ray imaging
journal, February 2019


Deep Residual Learning for Image Recognition
conference, June 2016

  • He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • DOI: 10.1109/CVPR.2016.90

The effect of laser focus shift on microstructural variation of Inconel 718 produced by selective laser melting
journal, July 2018


Quantifying Geometric Accuracy With Unsupervised Machine Learning: Using Self-Organizing Map on Fused Filament Fabrication Additive Manufacturing Parts
journal, December 2017

  • Khanzadeh, Mojtaba; Rao, Prahalada; Jafari-Marandi, Ruholla
  • Journal of Manufacturing Science and Engineering, Vol. 140, Issue 3
  • DOI: 10.1115/1.4038598

Process Mapping and In-Process Monitoring of Porosity in Laser Powder Bed Fusion Using Layerwise Optical Imaging
journal, July 2018

  • Imani, Farhad; Gaikwad, Aniruddha; Montazeri, Mohammad
  • Journal of Manufacturing Science and Engineering, Vol. 140, Issue 10
  • DOI: 10.1115/1.4040615

Additive Manufacturing: Current State, Future Potential, Gaps and Needs, and Recommendations
journal, February 2015

  • Huang, Yong; Leu, Ming C.; Mazumder, Jyoti
  • Journal of Manufacturing Science and Engineering, Vol. 137, Issue 1
  • DOI: 10.1115/1.4028725

Metal vapor micro-jet controls material redistribution in laser powder bed fusion additive manufacturing
journal, June 2017


Multiscale Modeling of Powder Bed–Based Additive Manufacturing
journal, July 2016


In-Process Monitoring of Selective Laser Melting: Spatial Detection of Defects Via Image Data Analysis
journal, November 2016

  • Grasso, Marco; Laguzza, Vittorio; Semeraro, Quirico
  • Journal of Manufacturing Science and Engineering, Vol. 139, Issue 5
  • DOI: 10.1115/1.4034715

Melt pool and keyhole behaviour analysis for deep penetration laser welding
journal, October 2010


In situ morphology-based defect detection of selective laser melting through inline coherent imaging
journal, May 2016


A multi-resolution framework for automated in-plane alignment and error quantification in additive manufacturing
journal, June 2020


Semi-Supervised Convolutional Neural Networks for In-Situ Video Monitoring of Selective Laser Melting
conference, January 2019

  • Yuan, Bodi; Giera, Brian; Guss, Gabe
  • 2019 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • DOI: 10.1109/WACV.2019.00084