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

Title: A predictive machine learning approach for microstructure optimization and materials design

Journal Article · · Scientific Reports
DOI:https://doi.org/10.1038/srep11551· OSTI ID:1259699
 [1];  [2];  [3];  [1];  [4];  [1]
  1. Northwestern Univ., Evanston, IL (United States). EECS Dept.
  2. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
  3. Northwestern Univ., Evanston, IL (United States). EECS Dept.; NEC Lab. America, Inc., Princeton, NJ (United States)
  4. Univ. of Michigan, Ann Arbor, MI (United States)
+ Show Author Affiliations

This paper addresses an important materials engineering question: How can one identify the complete space (or as much of it as possible) of microstructures that are theoretically predicted to yield the desired combination of properties demanded by a selected application? We present a problem involving design of magnetoelastic Fe-Ga alloy microstructure for enhanced elastic, plastic and magnetostrictive properties. While theoretical models for computing properties given the microstructure are known for this alloy, inversion of these relationships to obtain microstructures that lead to desired properties is challenging, primarily due to the high dimensionality of microstructure space, multi-objective design requirement and non-uniqueness of solutions. These challenges render traditional search-based optimization methods incompetent in terms of both searching efficiency and result optimality. In this paper, a route to address these challenges using a machine learning methodology is proposed. A systematic framework consisting of random data generation, feature selection and classification algorithms is developed. As a result, experiments with five design problems that involve identification of microstructures that satisfy both linear and nonlinear property constraints show that our framework outperforms traditional optimization methods with the average running time reduced by as much as 80% and with optimality that would not be achieved otherwise.

Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE
Grant/Contract Number:
SC0007456; 70NANB14H012; FA9550-12-1-0458; AC05-00OR22725
OSTI ID:
1259699
Alternate ID(s):
OSTI ID: 1331083
Journal Information:
Scientific Reports, Vol. 5; ISSN 2045-2322
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 142 works
Citation information provided by
Web of Science

References (27)

Materials selection in mechanical design journal November 1993
Line search algorithms with guaranteed sufficient decrease journal September 1994
Combinatorial Search for Optimal Hydrogen-Storage Nanomaterials Based on Polymers journal August 2006
Combinatorial search for advanced luminescence materials journal January 1999
Characterization and energy-based model of the magnetomechanical behavior of polycrystalline iron–gallium alloys journal July 2007
Ductility, texture and large magnetostriction of Fe–Ga-based sheets journal July 2010
Microstructure-sensitive design of a compliant beam journal August 2001
Linear analysis of texture–property relationships using process-based representations of Rodrigues space journal March 2007
Crystallographic textures in rolled and annealed Fe-Ga and Fe-Al alloys journal September 2004
A bidirectionally coupled magnetoelastic model and its validation using a Galfenol unimorph sensor journal March 2008
Combinatorial Search for Optimal Hydrogen-Storage Nanomaterials Based on Polymers text January 2006
Concurrent design of hierarchical materials and structures journal April 2008
Analysis of Generalized Pattern Searches report January 2006
Optimization by Simulated Annealing journal May 1983
Texture development in the cold rolling of IF steel journal August 2004
Magnetostrictive Vibration Sensor based on Iron-Gallium Alloy journal January 2005
Nonlinear behavior of magnetostrictive particle actuated composite materials journal March 2000
On the synergy between texture classification and deformation process sequence selection for the control of texture-dependent properties journal February 2005
A new structural optimization method based on the harmony search algorithm journal April 2004
Microstructure sensitive design of an orthotropic plate subjected to tensile load journal August 2004
Integrated Genetic Algorithm for Optimization of Space Structures journal October 1993
A computational procedure for rate-independent crystal plasticity journal April 1996
Magnetoelastic bending of Galfenol for sensor applications journal May 2005
Analysis of Generalized Pattern Searches journal January 2002
Heuristics for Integer Programming Using Surrogate Constraints journal January 1977
Secondary recrystallization, crystallographic texture and magnetostriction in rolled Fe–Ga based alloys journal May 2007
Deformation behavior of polycrystalline Galfenol at elevated temperatures conference April 2007

Cited By (17)

Crystal Plasticity Model Calibration for Ti-7Al Alloy with a Multi-fidelity Computational Scheme journal November 2018
Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science journal April 2016
Identifying an efficient, thermally robust inorganic phosphor host via machine learning journal October 2018
A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics journal May 2019
Modeling Macroscopic Material Behavior With Machine Learning Algorithms Trained by Micromechanical Simulations journal August 2019
PRISMS: An Integrated, Open-Source Framework for Accelerating Predictive Structural Materials Science journal August 2018
Adaptive Strategies for Materials Design using Uncertainties journal January 2016
Perspectives on the Impact of Machine Learning, Deep Learning, and Artificial Intelligence on Materials, Processes, and Structures Engineering journal August 2018
Algorithmic-driven design of shark denticle bioinspired structures for superior aerodynamic properties journal January 2020
Qualitative Decision Methods for Multi-Attribute Decision Making preprint January 2015
3DMaterialGAN: Learning 3D Shape Representation from Latent Space for Materials Science Applications preprint January 2020
A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions journal September 2018
Characterization of the Optical Properties of Turbid Media by Supervised Learning of Scattering Patterns journal November 2017
A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions preprint January 2018
ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition journal December 2018
A review of the application of machine learning and data mining approaches in continuum materials mechanics text January 2019
Understanding and designing magnetoelectric heterostructures guided by computation: progresses, remaining questions, and perspectives journal May 2017

Similar Records

Prediction of seebeck coefficient for compounds without restriction to fixed stoichiometry: A machine learning approach
Journal Article · Wed Sep 27 00:00:00 EDT 2017 · Journal of Computational Chemistry · OSTI ID:1259699
+3 more
Microstructure optimization with constrained design objectives using machine learning-based feedback-aware data-generation
Journal Article · Thu Jan 24 00:00:00 EST 2019 · Computational Materials Science · OSTI ID:1259699
+3 more
Heuristic methods and performance bounds for photonic design
Journal Article · Fri Jan 15 00:00:00 EST 2021 · Optics Express · OSTI ID:1259699

Related Subjects

36 MATERIALS SCIENCE
computer science
information technology
metals and alloys
42 ENGINEERING