Enabling rapid X-ray CT characterisation for additive manufacturing using CAD models and deep learning-based reconstruction

Amirkoushyar Ziabari; S. V. Venkatakrishnan; Zackary Snow; Aleksander Lisovich; Michael Sprayberry; Paul Brackman; Curtis Frederick; Pradeep Bhattad; Sarah Graham; Philip Bingham; Ryan Dehoff; Alex Plotkowski; Vincent Paquit

doi:10.1038/s41524-023-01032-5

Enabling rapid X-ray CT characterisation for additive manufacturing using CAD models and deep learning-based reconstruction

Amirkoushyar Ziabari, S. V. Venkatakrishnan, Zackary Snow, Aleksander Lisovich, Michael Sprayberry, Paul Brackman, Curtis Frederick, Pradeep Bhattad, Sarah Graham, Philip Bingham, Ryan Dehoff, Alex Plotkowski, Vincent Paquit

Research output: Contribution to journal › Article › peer-review

16 Scopus citations

Abstract

Metal additive manufacturing (AM) offers flexibility and cost-effectiveness for printing complex parts but is limited to few alloys. Qualifying new alloys requires process parameter optimisation to produce consistent, high-quality components. High-resolution X-ray computed tomography (XCT) has not been effective for this task due to artifacts, slow scan speed, and costs. We propose a deep learning-based approach for rapid XCT acquisition and reconstruction of metal AM parts, leveraging computer-aided design models and physics-based simulations of nonlinear interactions between X-ray radiation and metals. This significantly reduces beam hardening and common XCT artifacts. We demonstrate high-throughput characterisation of over a hundred AlCe alloy components, quantifying improvements in characterisation time and quality compared to high-resolution microscopy and pycnometry. Our approach facilitates investigating the impact of process parameters and their geometry dependence in metal AM.

Original language	English
Article number	91
Journal	npj Computational Materials
Volume	9
Issue number	1
DOIs	https://doi.org/10.1038/s41524-023-01032-5
State	Published - Dec 2023

Funding

This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE).Research sponsored by the US Department of Energy, Office of Energy Efficiency and Renewable Energy, Advanced Manufacturing Office and Technology Commercialisation Fund (TCF-21-24881), under contract DE-AC05-00OR22725 with UT-Battelle, LLC. The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan ( http://energy.gov/downloads/doe-public-access-plan ). This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE).Research sponsored by the US Department of Energy, Office of Energy Efficiency and Renewable Energy, Advanced Manufacturing Office and Technology Commercialisation Fund (TCF-21-24881), under contract DE-AC05-00OR22725 with UT-Battelle, LLC. The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan).

Funders	Funder number
Advanced Manufacturing Office and Technology Commercialisation Fund	TCF-21-24881
DOE Public Access Plan
U.S. Department of Energy
Office of Energy Efficiency and Renewable Energy

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1038/s41524-023-01032-5

Cite this

Ziabari, A., Venkatakrishnan, S. V., Snow, Z., Lisovich, A., Sprayberry, M., Brackman, P., Frederick, C., Bhattad, P., Graham, S., Bingham, P., Dehoff, R., Plotkowski, A., & Paquit, V. (2023). Enabling rapid X-ray CT characterisation for additive manufacturing using CAD models and deep learning-based reconstruction. npj Computational Materials, 9(1), Article 91. https://doi.org/10.1038/s41524-023-01032-5

@article{01415024cfa54e7da12251e463a550ac,

title = "Enabling rapid X-ray CT characterisation for additive manufacturing using CAD models and deep learning-based reconstruction",

abstract = "Metal additive manufacturing (AM) offers flexibility and cost-effectiveness for printing complex parts but is limited to few alloys. Qualifying new alloys requires process parameter optimisation to produce consistent, high-quality components. High-resolution X-ray computed tomography (XCT) has not been effective for this task due to artifacts, slow scan speed, and costs. We propose a deep learning-based approach for rapid XCT acquisition and reconstruction of metal AM parts, leveraging computer-aided design models and physics-based simulations of nonlinear interactions between X-ray radiation and metals. This significantly reduces beam hardening and common XCT artifacts. We demonstrate high-throughput characterisation of over a hundred AlCe alloy components, quantifying improvements in characterisation time and quality compared to high-resolution microscopy and pycnometry. Our approach facilitates investigating the impact of process parameters and their geometry dependence in metal AM.",

author = "Amirkoushyar Ziabari and Venkatakrishnan, {S. V.} and Zackary Snow and Aleksander Lisovich and Michael Sprayberry and Paul Brackman and Curtis Frederick and Pradeep Bhattad and Sarah Graham and Philip Bingham and Ryan Dehoff and Alex Plotkowski and Vincent Paquit",

note = "Publisher Copyright: {\textcopyright} 2023, This is a U.S. Government work and not under copyright protection in the US; foreign copyright protection may apply.",

year = "2023",

month = dec,

doi = "10.1038/s41524-023-01032-5",

language = "English",

volume = "9",

journal = "npj Computational Materials",

issn = "2057-3960",

publisher = "Nature Research",

number = "1",

}

Ziabari, A , Venkatakrishnan, SV , Snow, Z, Lisovich, A, Sprayberry, M, Brackman, P, Frederick, C, Bhattad, P, Graham, S, Bingham, P , Dehoff, R , Plotkowski, A & Paquit, V 2023, 'Enabling rapid X-ray CT characterisation for additive manufacturing using CAD models and deep learning-based reconstruction', npj Computational Materials, vol. 9, no. 1, 91. https://doi.org/10.1038/s41524-023-01032-5

TY - JOUR

T1 - Enabling rapid X-ray CT characterisation for additive manufacturing using CAD models and deep learning-based reconstruction

AU - Ziabari, Amirkoushyar

AU - Venkatakrishnan, S. V.

AU - Snow, Zackary

AU - Lisovich, Aleksander

AU - Sprayberry, Michael

AU - Brackman, Paul

AU - Frederick, Curtis

AU - Bhattad, Pradeep

AU - Graham, Sarah

AU - Bingham, Philip

AU - Dehoff, Ryan

AU - Plotkowski, Alex

AU - Paquit, Vincent

PY - 2023/12

Y1 - 2023/12

N2 - Metal additive manufacturing (AM) offers flexibility and cost-effectiveness for printing complex parts but is limited to few alloys. Qualifying new alloys requires process parameter optimisation to produce consistent, high-quality components. High-resolution X-ray computed tomography (XCT) has not been effective for this task due to artifacts, slow scan speed, and costs. We propose a deep learning-based approach for rapid XCT acquisition and reconstruction of metal AM parts, leveraging computer-aided design models and physics-based simulations of nonlinear interactions between X-ray radiation and metals. This significantly reduces beam hardening and common XCT artifacts. We demonstrate high-throughput characterisation of over a hundred AlCe alloy components, quantifying improvements in characterisation time and quality compared to high-resolution microscopy and pycnometry. Our approach facilitates investigating the impact of process parameters and their geometry dependence in metal AM.

AB - Metal additive manufacturing (AM) offers flexibility and cost-effectiveness for printing complex parts but is limited to few alloys. Qualifying new alloys requires process parameter optimisation to produce consistent, high-quality components. High-resolution X-ray computed tomography (XCT) has not been effective for this task due to artifacts, slow scan speed, and costs. We propose a deep learning-based approach for rapid XCT acquisition and reconstruction of metal AM parts, leveraging computer-aided design models and physics-based simulations of nonlinear interactions between X-ray radiation and metals. This significantly reduces beam hardening and common XCT artifacts. We demonstrate high-throughput characterisation of over a hundred AlCe alloy components, quantifying improvements in characterisation time and quality compared to high-resolution microscopy and pycnometry. Our approach facilitates investigating the impact of process parameters and their geometry dependence in metal AM.

UR - http://www.scopus.com/inward/record.url?scp=85160960587&partnerID=8YFLogxK

U2 - 10.1038/s41524-023-01032-5

DO - 10.1038/s41524-023-01032-5

M3 - Article

AN - SCOPUS:85160960587

SN - 2057-3960

VL - 9

JO - npj Computational Materials

JF - npj Computational Materials

IS - 1

M1 - 91

ER -

Enabling rapid X-ray CT characterisation for additive manufacturing using CAD models and deep learning-based reconstruction

Abstract

Funding

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this