Understanding structure-processing relationships in metal additive manufacturing via featurization of microstructural images

Dipayan Sanpui; Anirban Chandra; Sukriti Manna; Partha Sarathi Dutta; Maria K.Y. Chan; Henry Chan; Subramanian K.R.S. Sankaranarayanan

doi:10.1016/j.commatsci.2023.112566

Understanding structure-processing relationships in metal additive manufacturing via featurization of microstructural images

Dipayan Sanpui, Anirban Chandra, Sukriti Manna, Partha Sarathi Dutta, Maria K.Y. Chan, Henry Chan, Subramanian K.R.S. Sankaranarayanan^*

^*Corresponding author for this work

MRC - Materials Research Center

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

2 Scopus citations

Abstract

Understanding and predicting accurate property-structure-processing relationships for additively manufactured components is important for both forward and inverse design of robust, reliable parts and assemblies. While direct mapping of process parameters to properties is sometimes plausible, it is often rendered difficult due to poor microstructural control. Exploring the direct relationship between processing conditions and microstructural features can thus provide significant physical insights and aid the overall design process. Here, we develop an automated high-throughput framework to simulate an uncertainty-aware additive manufacturing (AM) process, characterize microstructural images, and extract meaningful features/descriptors. A kinetic Monte Carlo (KMC) based model of the AM process is used to simulate microstructural evolution for a diverse set of experimentally relevant processing conditions. We perform a parametric study to explore the relationship between microstructural features and processing conditions. Our results indicate that a many-to-one mapping can exist between processing conditions and typical descriptors; therefore, multiple descriptors are thus necessary to unambiguously represent microstructural images. Our work provides crucial quantitative and qualitative information that would aid in the selection of features for microstructural images. Featurized microstructures could then be utilized to build data-driven models for predictive control of microstructures and thereby properties of additively manufactured components.

Original language	English (US)
Article number	112566
Journal	Computational Materials Science
Volume	231
DOIs	https://doi.org/10.1016/j.commatsci.2023.112566
State	Published - Jan 5 2024

Funding

This work was supported by Argonne's LDRD Program. This work was performed in part at the Center for Nanoscale Materials, which is a US Department of Energy Office of Science User facilities supported by the US Department of Energy, Office of Science, Office of Basic Energy Sciences, under Contract No. DE-AC02-06CH11357. This research used resources of the National Energy Research Scientific Computing Center, which was supported by the Office of Science of the US Department of Energy under Contract No. DE-AC02-05CH11231. Authors would like to acknowledge the Air Force Office of Scientific Research (AFOSR) for funding this research under Award FA9550-20-1-0332, with Dr. Chipping Li as the program manager. SKRS would also like to acknowledge the support from the UIC faculty start-up fund. All authors thank Pierre Darancet for his helpful comments and suggestions. DS and AC contributed equally to this project. DS, AC and SKRS conceived the project. DS performed all the KMC calculations with input from AC. DS and AC performed all the feature extraction and data analysis with input from HC and PSD All the authors provided feedback on the workflow and feature extraction. DS, AC and SKRS wrote the manuscript with input from all co-authors. SM, HC, and MC provided feedback on the manuscript. All authors participated in discussing the results and provided comments and suggestions on the various sections of the manuscript. SKRS supervised and directed the overall project. This work was supported by Argonne’s LDRD Program. This work was performed in part at the Center for Nanoscale Materials, which is a US Department of Energy Office of Science User facilities supported by the US Department of Energy, Office of Science, Office of Basic Energy Sciences, under Contract No. DE-AC02-06CH11357. This research used resources of the National Energy Research Scientific Computing Center, which was supported by the Office of Science of the US Department of Energy under Contract No. DE-AC02-05CH11231. Authors would like to acknowledge the Air Force Office of Scientific Research (AFOSR) for funding this research under Award FA9550-20-1-0332, with Dr. Chipping Li as the program manager. SKRS would also like to acknowledge the support from the UIC faculty start-up fund. All authors thank Pierre Darancet for his helpful comments and suggestions.

Keywords

Additive manufacturing
Featurization
Inverse design
Machine Learning

ASJC Scopus subject areas

General Computer Science
General Chemistry
General Materials Science
Mechanics of Materials
General Physics and Astronomy
Computational Mathematics

UN SDGs

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

Access to Document

10.1016/j.commatsci.2023.112566

Cite this

@article{b37eb14091cf42c8927c5e42487c470b,

title = "Understanding structure-processing relationships in metal additive manufacturing via featurization of microstructural images",

abstract = "Understanding and predicting accurate property-structure-processing relationships for additively manufactured components is important for both forward and inverse design of robust, reliable parts and assemblies. While direct mapping of process parameters to properties is sometimes plausible, it is often rendered difficult due to poor microstructural control. Exploring the direct relationship between processing conditions and microstructural features can thus provide significant physical insights and aid the overall design process. Here, we develop an automated high-throughput framework to simulate an uncertainty-aware additive manufacturing (AM) process, characterize microstructural images, and extract meaningful features/descriptors. A kinetic Monte Carlo (KMC) based model of the AM process is used to simulate microstructural evolution for a diverse set of experimentally relevant processing conditions. We perform a parametric study to explore the relationship between microstructural features and processing conditions. Our results indicate that a many-to-one mapping can exist between processing conditions and typical descriptors; therefore, multiple descriptors are thus necessary to unambiguously represent microstructural images. Our work provides crucial quantitative and qualitative information that would aid in the selection of features for microstructural images. Featurized microstructures could then be utilized to build data-driven models for predictive control of microstructures and thereby properties of additively manufactured components.",

keywords = "Additive manufacturing, Featurization, Inverse design, Machine Learning",

author = "Dipayan Sanpui and Anirban Chandra and Sukriti Manna and \{Sarathi Dutta\}, Partha and Chan, \{Maria K.Y.\} and Henry Chan and Sankaranarayanan, \{Subramanian K.R.S.\}",

note = "Publisher Copyright: {\textcopyright} 2023",

year = "2024",

month = jan,

day = "5",

doi = "10.1016/j.commatsci.2023.112566",

language = "English (US)",

volume = "231",

journal = "Computational Materials Science",

issn = "0927-0256",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Understanding structure-processing relationships in metal additive manufacturing via featurization of microstructural images

AU - Sanpui, Dipayan

AU - Chandra, Anirban

AU - Manna, Sukriti

AU - Sarathi Dutta, Partha

AU - Chan, Maria K.Y.

AU - Chan, Henry

AU - Sankaranarayanan, Subramanian K.R.S.

PY - 2024/1/5

Y1 - 2024/1/5

N2 - Understanding and predicting accurate property-structure-processing relationships for additively manufactured components is important for both forward and inverse design of robust, reliable parts and assemblies. While direct mapping of process parameters to properties is sometimes plausible, it is often rendered difficult due to poor microstructural control. Exploring the direct relationship between processing conditions and microstructural features can thus provide significant physical insights and aid the overall design process. Here, we develop an automated high-throughput framework to simulate an uncertainty-aware additive manufacturing (AM) process, characterize microstructural images, and extract meaningful features/descriptors. A kinetic Monte Carlo (KMC) based model of the AM process is used to simulate microstructural evolution for a diverse set of experimentally relevant processing conditions. We perform a parametric study to explore the relationship between microstructural features and processing conditions. Our results indicate that a many-to-one mapping can exist between processing conditions and typical descriptors; therefore, multiple descriptors are thus necessary to unambiguously represent microstructural images. Our work provides crucial quantitative and qualitative information that would aid in the selection of features for microstructural images. Featurized microstructures could then be utilized to build data-driven models for predictive control of microstructures and thereby properties of additively manufactured components.

AB - Understanding and predicting accurate property-structure-processing relationships for additively manufactured components is important for both forward and inverse design of robust, reliable parts and assemblies. While direct mapping of process parameters to properties is sometimes plausible, it is often rendered difficult due to poor microstructural control. Exploring the direct relationship between processing conditions and microstructural features can thus provide significant physical insights and aid the overall design process. Here, we develop an automated high-throughput framework to simulate an uncertainty-aware additive manufacturing (AM) process, characterize microstructural images, and extract meaningful features/descriptors. A kinetic Monte Carlo (KMC) based model of the AM process is used to simulate microstructural evolution for a diverse set of experimentally relevant processing conditions. We perform a parametric study to explore the relationship between microstructural features and processing conditions. Our results indicate that a many-to-one mapping can exist between processing conditions and typical descriptors; therefore, multiple descriptors are thus necessary to unambiguously represent microstructural images. Our work provides crucial quantitative and qualitative information that would aid in the selection of features for microstructural images. Featurized microstructures could then be utilized to build data-driven models for predictive control of microstructures and thereby properties of additively manufactured components.

KW - Additive manufacturing

KW - Featurization

KW - Inverse design

KW - Machine Learning

UR - http://www.scopus.com/inward/record.url?scp=85173878712&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85173878712&partnerID=8YFLogxK

U2 - 10.1016/j.commatsci.2023.112566

DO - 10.1016/j.commatsci.2023.112566

M3 - Article

AN - SCOPUS:85173878712

SN - 0927-0256

VL - 231

JO - Computational Materials Science

JF - Computational Materials Science

M1 - 112566

ER -

Understanding structure-processing relationships in metal additive manufacturing via featurization of microstructural images

Abstract

Funding

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this