skip to main content

DOE PAGESDOE PAGES

Title: Gaussian process-based surrogate modeling framework for process planning in laser powder-bed fusion additive manufacturing of 316L stainless steel

Here, Laser Powder-Bed Fusion (L-PBF) metal-based additive manufacturing (AM) is complex and not fully understood. Successful processing for one material, might not necessarily apply to a different material. This paper describes a workflow process that aims at creating a material data sheet standard that describes regimes where the process can be expected to be robust. The procedure consists of building a Gaussian process-based surrogate model of the L-PBF process that predicts melt pool depth in single-track experiments given a laser power, scan speed, and laser beam size combination. The predictions are then mapped onto a power versus scan speed diagram delimiting the conduction from the keyhole melting controlled regimes. This statistical framework is shown to be robust even for cases where experimental training data might be suboptimal in quality, if appropriate physics-based filters are applied. Additionally, it is demonstrated that a high-fidelity simulation model of L-PBF can equally be successfully used for building a surrogate model, which is beneficial since simulations are getting more efficient and are more practical to study the response of different materials, than to re-tool an AM machine for new material powder.
Authors:
 [1] ;  [2] ;  [2] ;  [2] ; ORCiD logo [1]
  1. Texas A & M Univ., College Station, TX (United States)
  2. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Publication Date:
Report Number(s):
LLNL-JRNL-726754
Journal ID: ISSN 0268-3768
Grant/Contract Number:
AC52-07NA27344
Type:
Accepted Manuscript
Journal Name:
International Journal of Advanced Manufacturing Technology
Additional Journal Information:
Journal Volume: 94; Journal Issue: 9-12; Journal ID: ISSN 0268-3768
Publisher:
Springer
Research Org:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org:
USDOE
Country of Publication:
United States
Language:
English
Subject:
42 ENGINEERING; 36 MATERIALS SCIENCE; 97 MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; Additive manufacturing; Laser powder-bed fusion; 316L stainless steel; Gaussian processes; Bayesian statistics
OSTI Identifier:
1420279

Tapia, Gustavo, Khairallah, Saad A., Matthews, Manyalibo J., King, Wayne E., and Elwany, Alaa. Gaussian process-based surrogate modeling framework for process planning in laser powder-bed fusion additive manufacturing of 316L stainless steel. United States: N. p., Web. doi:10.1007/s00170-017-1045-z.
Tapia, Gustavo, Khairallah, Saad A., Matthews, Manyalibo J., King, Wayne E., & Elwany, Alaa. Gaussian process-based surrogate modeling framework for process planning in laser powder-bed fusion additive manufacturing of 316L stainless steel. United States. doi:10.1007/s00170-017-1045-z.
Tapia, Gustavo, Khairallah, Saad A., Matthews, Manyalibo J., King, Wayne E., and Elwany, Alaa. 2017. "Gaussian process-based surrogate modeling framework for process planning in laser powder-bed fusion additive manufacturing of 316L stainless steel". United States. doi:10.1007/s00170-017-1045-z. https://www.osti.gov/servlets/purl/1420279.
@article{osti_1420279,
title = {Gaussian process-based surrogate modeling framework for process planning in laser powder-bed fusion additive manufacturing of 316L stainless steel},
author = {Tapia, Gustavo and Khairallah, Saad A. and Matthews, Manyalibo J. and King, Wayne E. and Elwany, Alaa},
abstractNote = {Here, Laser Powder-Bed Fusion (L-PBF) metal-based additive manufacturing (AM) is complex and not fully understood. Successful processing for one material, might not necessarily apply to a different material. This paper describes a workflow process that aims at creating a material data sheet standard that describes regimes where the process can be expected to be robust. The procedure consists of building a Gaussian process-based surrogate model of the L-PBF process that predicts melt pool depth in single-track experiments given a laser power, scan speed, and laser beam size combination. The predictions are then mapped onto a power versus scan speed diagram delimiting the conduction from the keyhole melting controlled regimes. This statistical framework is shown to be robust even for cases where experimental training data might be suboptimal in quality, if appropriate physics-based filters are applied. Additionally, it is demonstrated that a high-fidelity simulation model of L-PBF can equally be successfully used for building a surrogate model, which is beneficial since simulations are getting more efficient and are more practical to study the response of different materials, than to re-tool an AM machine for new material powder.},
doi = {10.1007/s00170-017-1045-z},
journal = {International Journal of Advanced Manufacturing Technology},
number = 9-12,
volume = 94,
place = {United States},
year = {2017},
month = {9}
}

Works referenced in this record:

Laser additive manufacturing of metallic components: materials, processes and mechanisms
journal, May 2012