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

Title: Coupling physics in machine learning to predict properties of high-temperatures alloys

Abstract

High-temperature alloy design requires a concurrent consideration of multiple mechanisms at different length scales. We propose a workflow that couples highly relevant physics into machine learning (ML) to predict properties of complex high-temperature alloys with an example of the 9–12 wt% Cr steels yield strength. We have incorporated synthetic alloy features that capture microstructure and phase transformations into the dataset. Identified high impact features that affect yield strength of 9Cr from correlation analysis agree well with the generally accepted strengthening mechanism. As a part of the verification process, the consistency of sub-datasets has been extensively evaluated with respect to temperature and then refined for the boundary conditions of trained ML models. The predicted yield strength of 9Cr steels using the ML models is in excellent agreement with experiments. The current approach introduces physically meaningful constraints in interrogating the trained ML models to predict properties of hypothetical alloys when applied to data-driven materials.

Authors:
ORCiD logo [1]; ORCiD logo [1];  [2]; ORCiD logo [1]; ORCiD logo [1]
  1. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
  2. National Energy Technology Lab. (NETL), Albany, OR (United States)
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE Office of Fossil Energy (FE)
OSTI Identifier:
1666014
Grant/Contract Number:  
AC05-00OR22725
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
npj Computational Materials
Additional Journal Information:
Journal Volume: 6; Journal Issue: 1; Journal ID: ISSN 2057-3960
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English
Subject:
Computational methods; metals and alloys

Citation Formats

Peng, Jian, Yamamoto, Yukinori, Hawk, Jeffrey A., Lara-Curzio, Edgar, and Shin, Dongwon. Coupling physics in machine learning to predict properties of high-temperatures alloys. United States: N. p., 2020. Web. doi:10.1038/s41524-020-00407-2.
Peng, Jian, Yamamoto, Yukinori, Hawk, Jeffrey A., Lara-Curzio, Edgar, & Shin, Dongwon. Coupling physics in machine learning to predict properties of high-temperatures alloys. United States. doi:10.1038/s41524-020-00407-2.
Peng, Jian, Yamamoto, Yukinori, Hawk, Jeffrey A., Lara-Curzio, Edgar, and Shin, Dongwon. Fri . "Coupling physics in machine learning to predict properties of high-temperatures alloys". United States. doi:10.1038/s41524-020-00407-2. https://www.osti.gov/servlets/purl/1666014.
@article{osti_1666014,
title = {Coupling physics in machine learning to predict properties of high-temperatures alloys},
author = {Peng, Jian and Yamamoto, Yukinori and Hawk, Jeffrey A. and Lara-Curzio, Edgar and Shin, Dongwon},
abstractNote = {High-temperature alloy design requires a concurrent consideration of multiple mechanisms at different length scales. We propose a workflow that couples highly relevant physics into machine learning (ML) to predict properties of complex high-temperature alloys with an example of the 9–12 wt% Cr steels yield strength. We have incorporated synthetic alloy features that capture microstructure and phase transformations into the dataset. Identified high impact features that affect yield strength of 9Cr from correlation analysis agree well with the generally accepted strengthening mechanism. As a part of the verification process, the consistency of sub-datasets has been extensively evaluated with respect to temperature and then refined for the boundary conditions of trained ML models. The predicted yield strength of 9Cr steels using the ML models is in excellent agreement with experiments. The current approach introduces physically meaningful constraints in interrogating the trained ML models to predict properties of hypothetical alloys when applied to data-driven materials.},
doi = {10.1038/s41524-020-00407-2},
journal = {npj Computational Materials},
issn = {2057-3960},
number = 1,
volume = 6,
place = {United States},
year = {2020},
month = {9}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share:

Works referenced in this record:

Hot strength of creep resistant ferritic steels and relationship to creep rupture data
journal, September 2007

  • Dimitriu, R. C.; Bhadeshia, H. K. D. H.
  • Materials Science and Technology, Vol. 23, Issue 9
  • DOI: 10.1179/174328407X213332

Five High-Impact Research Areas in Machine Learning for Materials Science
journal, December 2019


Thermodynamically Based Prediction of the Martensite Start Temperature for Commercial Steels
journal, June 2012

  • Stormvinter, Albin; Borgenstam, Annika; Ågren, John
  • Metallurgical and Materials Transactions A, Vol. 43, Issue 10
  • DOI: 10.1007/s11661-012-1171-z

The Thermo-Calc databank system
journal, April 1985


Mapping Multivariate Influence of Alloying Elements on Creep Behavior for Design of New Martensitic Steels
journal, April 2019

  • Verma, Amit K.; Hawk, Jeffery A.; Bruckman, Laura S.
  • Metallurgical and Materials Transactions A, Vol. 50, Issue 7
  • DOI: 10.1007/s11661-019-05234-9

CALPHAD-Is It Ready for Superalloy Design?
journal, July 2002


Advanced data science toolkit for non-data scientists – A user guide
journal, March 2020


Detecting Novel Associations in Large Data Sets
journal, December 2011


Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel
journal, October 2019


Driving force for f.c.c. → b.c.c. martensites in FeX alloys
journal, May 1997


A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics
journal, May 2019


Neural Networks in Materials Science.
journal, January 1999


Bayesian Interpolation
journal, May 1992


Neural network model of creep strength of austenitic stainless steels
journal, June 2002

  • Sourmail, T.; Bhadeshia, H. K. D. H.; MacKay, D. J. C.
  • Materials Science and Technology, Vol. 18, Issue 6
  • DOI: 10.1179/026708302225002065

Petascale supercomputing to accelerate the design of high-temperature alloys
journal, January 2017


ASCENDS: Advanced data SCiENce toolkit for Non-Data Scientists
journal, February 2020

  • Lee, Sangkeun; Peng, Jian; Williams, Andrew
  • Journal of Open Source Software, Vol. 5, Issue 46
  • DOI: 10.21105/joss.01656

Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters
journal, April 2014

  • Agrawal, Ankit; Deshpande, Parijat D.; Cecen, Ahmet
  • Integrating Materials and Manufacturing Innovation, Vol. 3, Issue 1
  • DOI: 10.1186/2193-9772-3-8

Modern data analytics approach to predict creep of high-temperature alloys
journal, April 2019


Key computational modeling issues in Integrated Computational Materials Engineering
journal, January 2013

  • Panchal, Jitesh H.; Kalidindi, Surya R.; McDowell, David L.
  • Computer-Aided Design, Vol. 45, Issue 1
  • DOI: 10.1016/j.cad.2012.06.006

Machine learning in materials informatics: recent applications and prospects
journal, December 2017

  • Ramprasad, Rampi; Batra, Rohit; Pilania, Ghanshyam
  • npj Computational Materials, Vol. 3, Issue 1
  • DOI: 10.1038/s41524-017-0056-5

The 2019 materials by design roadmap
journal, October 2018

  • Alberi, Kirstin; Nardelli, Marco Buongiorno; Zakutayev, Andriy
  • Journal of Physics D: Applied Physics, Vol. 52, Issue 1
  • DOI: 10.1088/1361-6463/aad926

Materials Data Science: Current Status and Future Outlook
journal, July 2015


High cycle fatigue life prediction of laser additive manufactured stainless steel: A machine learning approach
journal, November 2019


Machine learning assisted design of high entropy alloys with desired property
journal, May 2019


Materials informatics
journal, October 2005


Data science and cyberinfrastructure: critical enablers for accelerated development of hierarchical materials
journal, October 2014


Thermo-Calc & DICTRA, computational tools for materials science
journal, June 2002


The random subspace method for constructing decision forests
journal, January 1998

  • Tin Kam Ho,
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, Issue 8
  • DOI: 10.1109/34.709601

Pearson's correlation coefficient
journal, July 2012


Materials informatics
journal, January 2018

  • Ramakrishna, Seeram; Zhang, Tong-Yi; Lu, Wen-Cong
  • Journal of Intelligent Manufacturing, Vol. 30, Issue 6
  • DOI: 10.1007/s10845-018-1392-0

Machine-learning phase prediction of high-entropy alloys
journal, May 2019