Microstructure optimization with constrained design objectives using machine learning-based feedback-aware data-generation

Paul, Arindam; Acar, Pinar; Liao, Wei-keng; Choudhary, Alok; Sundararaghavan, Veera; Agrawal, Ankit

doi:10.1016/j.commatsci.2019.01.015

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

DOI:https://doi.org/10.1016/j.commatsci.2019.01.015· OSTI ID:1610952

^[1]; ^[2]; Liao, Wei-keng ^[3]; Choudhary, Alok ^[3]; ^[4]; ^[3]

Northwestern Univ., Evanston, IL (United States); DOE/OSTI
Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)
Northwestern Univ., Evanston, IL (United States)
Univ. of Michigan, Ann Arbor, MI (United States)

Microstructure sensitive design has a critical impact on the performance of engineering materials. The safety and performance requirements of critical components, as well as the cost of material and machining of Titanium components, make dovetailing of the microstructure imperative. This paper addresses the optimization of several microstructure design problems for Titanium components under specific design constraints using a feedback-aware data-driven solution methodology. In this study, the microstructure is modeled with an orientation distribution function (ODF) that measures the volumes of different crystallographic orientations. Two algorithms are used to sample the entire microstructure space followed by machine learning-aided identification of a minimal subset of ODF dimensions which is subsequently explored by targeted sampling. Conventional optimization methods lead to a unique microstructure rather than yielding a comprehensive space of optimal or near-optimal microstructures. Multiple solutions are crucial for the deployment of materials design for manufacturing as traditional manufacturing processes can only generate a limited set of microstructures. Our data sampling-based methodology not only outperforms or is on par with other optimization techniques in terms of the optimal property value, but also provides numerous near-optimal solutions, 3–4 orders of magnitude more than previous methods. Consequently, the proposed framework delivers a spectrum of optimal solutions in the microstructure space which can accelerate materials development and reduce manufacturing costs.

View Accepted Manuscript (DOE)

Research Organization:: Northwestern Univ., Evanston, IL (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

Grant/Contract Number:: SC0007456; SC0014330

OSTI ID:: 1610952

Journal Information:: Computational Materials Science, Journal Name: Computational Materials Science Vol. 160; ISSN 0927-0256

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (30)

Titanium for aerospace: Rationale and applications Boyer, R. R. Advanced Performance Materials, Vol. 2, Issue 4 https://doi.org/10.1007/BF00705316	journal	October 1995
Titanium alloys and processing for high speed aircraft Brewer, William D.; Bird, R. Keith; Wallace, Terryl A. Materials Science and Engineering: A, Vol. 243, Issue 1-2 https://doi.org/10.1016/S0921-5093(97)00818-6	journal	March 1998
Titanium alloys and their machinability—a review Ezugwu, E. O.; Wang, Z. M. Journal of Materials Processing Technology, Vol. 68, Issue 3 https://doi.org/10.1016/S0924-0136(96)00030-1	journal	August 1997
Computational modeling of f.c.c. deformation textures over Rodrigues' space Kumar, A.; Dawson, P. R. Acta Materialia, Vol. 48, Issue 10 https://doi.org/10.1016/S1359-6454(00)00044-6	journal	June 2000
Linear analysis of texture–property relationships using process-based representations of Rodrigues space Sundararaghavan, V.; Zabaras, N. Acta Materialia, Vol. 55, Issue 5 https://doi.org/10.1016/j.actamat.2006.10.019	journal	March 2007
Multi-fidelity machine learning models for accurate bandgap predictions of solids Pilania, G.; Gubernatis, J. E.; Lookman, T. Computational Materials Science, Vol. 129 https://doi.org/10.1016/j.commatsci.2016.12.004	journal	March 2017
Machine learning for predicting occurrence of interphase precipitation in HSLA steels Rahnama, Alireza; Clark, Sam; Sridhar, Seetharaman Computational Materials Science, Vol. 154 https://doi.org/10.1016/j.commatsci.2018.07.055	journal	November 2018
An efficient machine learning approach to establish structure-property linkages Jung, Jaimyun; Yoon, Jae Ik; Park, Hyung Keun Computational Materials Science, Vol. 156 https://doi.org/10.1016/j.commatsci.2018.09.034	journal	January 2019
Microstructural diagram for steel based on crystallography with machine learning Tsutsui, Kazumasa; Terasaki, Hidenori; Maemura, Tatsuya Computational Materials Science, Vol. 159 https://doi.org/10.1016/j.commatsci.2018.12.003	journal	March 2019
Data-driven prediction of the high-dimensional thermal history in directed energy deposition processes via recurrent neural networks Mozaffar, Mojtaba; Paul, Arindam; Al-Bahrani, Reda Manufacturing Letters, Vol. 18 https://doi.org/10.1016/j.mfglet.2018.10.002	journal	October 2018
Extracting Grain Orientations from EBSD Patterns of Polycrystalline Materials Using Convolutional Neural Networks Jha, Dipendra; Singh, Saransh; Al-Bahrani, Reda Microscopy and Microanalysis, Vol. 24, Issue 5 https://doi.org/10.1017/S1431927618015131	journal	October 2018
Rapid and Accurate Machine Learning Recognition of High Performing Metal Organic Frameworks for CO ₂ Capture Fernandez, Michael; Boyd, Peter G.; Daff, Thomas D. The Journal of Physical Chemistry Letters, Vol. 5, Issue 17 https://doi.org/10.1021/jz501331m	journal	August 2014
A general-purpose machine learning framework for predicting properties of inorganic materials Ward, Logan; Agrawal, Ankit; Choudhary, Alok npj Computational Materials, Vol. 2, Issue 1 https://doi.org/10.1038/npjcompumats.2016.28	journal	August 2016
Machine learning in materials informatics: recent applications and prospects Ramprasad, Rampi; Batra, Rohit; Pilania, Ghanshyam npj Computational Materials, Vol. 3, Issue 1 https://doi.org/10.1038/s41524-017-0056-5	journal	December 2017
ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition Jha, Dipendra; Ward, Logan; Paul, Arindam Scientific Reports, Vol. 8, Issue 1 https://doi.org/10.1038/s41598-018-35934-y	journal	December 2018
On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets Kusne, Aaron Gilad; Gao, Tieren; Mehta, Apurva Scientific Reports, Vol. 4, Issue 1 https://doi.org/10.1038/srep06367	journal	September 2014
A predictive machine learning approach for microstructure optimization and materials design Liu, Ruoqian; Kumar, Abhishek; Chen, Zhengzhang Scientific Reports, Vol. 5, Issue 1 https://doi.org/10.1038/srep11551	journal	June 2015
Optimizing transition states via kernel-based machine learning Pozun, Zachary D.; Hansen, Katja; Sheppard, Daniel The Journal of Chemical Physics, Vol. 136, Issue 17 https://doi.org/10.1063/1.4707167	journal	May 2012
Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science Agrawal, Ankit; Choudhary, Alok APL Materials, Vol. 4, Issue 5 https://doi.org/10.1063/1.4946894	journal	April 2016
Combinatorial screening for new materials in unconstrained composition space with machine learning Meredig, B.; Agrawal, A.; Kirklin, S. Physical Review B, Vol. 89, Issue 9 https://doi.org/10.1103/PhysRevB.89.094104	journal	March 2014
Representation of orientation and disorientation data for cubic, hexagonal, tetragonal and orthorhombic crystals Heinz, A.; Neumann, P. Acta Crystallographica Section A Foundations of Crystallography, Vol. 47, Issue 6 https://doi.org/10.1107/S0108767391006864	journal	November 1991
Integrated Strength and Manufacturing Process Design Using a Shape Optimization Approach Grandhi, R. V.; Modukuru, S. C.; Malas, J. C. Journal of Mechanical Design, Vol. 115, Issue 1 https://doi.org/10.1115/1.2919308	journal	March 1993
A Descriptor-Based Design Methodology for Developing Heterogeneous Microstructural Materials System Xu, Hongyi; Li, Yang; Brinson, Catherine Journal of Mechanical Design, Vol. 136, Issue 5 https://doi.org/10.1115/1.4026649	journal	March 2014
A Machine Learning-Based Design Representation Method for Designing Heterogeneous Microstructures Xu, Hongyi; Liu, Ruoqian; Choudhary, Alok Journal of Mechanical Design, Vol. 137, Issue 5 https://doi.org/10.1115/1.4029768	journal	May 2015
Microstructure Representation and Reconstruction of Heterogeneous Materials Via Deep Belief Network for Computational Material Design Cang, Ruijin; Xu, Yaopengxiao; Chen, Shaohua Journal of Mechanical Design, Vol. 139, Issue 7 https://doi.org/10.1115/1.4036649	journal	May 2017
Computational Design of Hierarchically Structured Materials Olson, G. B. Science, Vol. 277, Issue 5330 https://doi.org/10.1126/science.277.5330.1237	journal	August 1997
Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters Agrawal, Ankit; Deshpande, Parijat D.; Cecen, Ahmet Integrating Materials and Manufacturing Innovation, Vol. 3, Issue 1 https://doi.org/10.1186/2193-9772-3-8	journal	April 2014
Utilization of a Linear Solver for Multiscale Design and Optimization of Microstructures Acar, Pinar; Sundararaghavan, Veera AIAA Journal, Vol. 54, Issue 5 https://doi.org/10.2514/1.J054822	journal	May 2016
Linear Solution Scheme for Microstructure Design with Process Constraints Acar, Pinar; Sundararaghavan, Veera AIAA Journal, Vol. 54, Issue 12 https://doi.org/10.2514/1.J055247	journal	December 2016
Data Sampling Schemes for Microstructure Design with Vibrational Tuning Constraints Paul, Arindam; Acar, Pinar; Liu, Ruoqian AIAA Journal, Vol. 56, Issue 3 https://doi.org/10.2514/1.J056170	journal	March 2018

Cited By (3)

Property Prediction of Organic Donor Molecules for Photovoltaic Applications using Extremely Randomized Trees Paul, Arindam; Furmanchuk, Alona; Liao, Wei-Keng Unpublished https://doi.org/10.13140/rg.2.2.27973.40167	text	January 2019
Machine learning for composite materials Chen, Chun-Teh; Gu, Grace X. MRS Communications, Vol. 9, Issue 02 https://doi.org/10.1557/mrc.2019.32	journal	March 2019
Improving the Dimensional Stability and Mechanical Properties of AISI 316L + B Sinters by Si3N4 Addition Skałoń, Mateusz; Buzolin, Ricardo; Kazior, Jan Materials, Vol. 12, Issue 11 https://doi.org/10.3390/ma12111798	journal	June 2019

Similar Records

Stochastic Design Optimization of Microstructural Features Using Linear Programming for Robust Design

Journal Article · Sat Sep 29 20:00:00 EDT 2018 · AIAA Journal · OSTI ID:1611109

Microstructural Materials Design Via Deep Adversarial Learning Methodology

Journal Article · Mon Oct 01 00:00:00 EDT 2018 · Journal of Mechanical Design · OSTI ID:1610954

Explicit Backscattering Coefficient for Ultrasonic Wave Propagating in Hexagonal Polycrystals with Fiber Texture

Journal Article · Sat Sep 15 00:00:00 EDT 2018 · Journal of Nondestructive Evaluation · OSTI ID:22809925

Related Subjects

36 MATERIALS SCIENCE

Microstructure optimization with constrained design objectives using machine learning-based feedback-aware data-generation

Citation Formats

References (30)

Cited By (3)

Similar Records

Related Subjects