Using machine-learning to understand complex microstructural effects on the mechanical behavior of Ti-6Al-4V alloys
Abstract
Structural materials properties are highly dependent on their microstructure. Their microstructure is in turn affected by multiple fabrication and thermo-mechanical treatment parameters, all of which conform a highly-dimensional parametric space with often hidden correlations that are difficult to extract by experimentation alone. This is particularly true for alloys of the dual-phase Ti-6Al-4V family, with their greatly complex and rich microstructures, which combine several intrinsic length scales associated with multiple grain and subgrain structures, grains with different crystal lattices (α and β phases), and complex chemistry. In this paper we use a comprehensive set of machine learning techniques to develop predictive tools relating the yield strength and hardening rate of these alloys to a set of input parameters covering extensive ranges. The data generator is a finite-element crystal plasticity model for polycrystal deformation that takes into account slip anisotropy and employs standard dislocation evolution models for the α and β phases of Ti-based alloys. Our dataset includes over two thousand independent simulations and is used to train the machine learning models, which are then used to establish correlations between microstructural parameters and the alloys’ mechanical response. Our results point to the most influential parameters affecting yield strength and hardening rate, informationmore »
- Authors:
-
- University of California, Los Angeles, CA (United States)
- Publication Date:
- Research Org.:
- Univ. of California, Los Angeles, CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Fusion Energy Sciences (FES); National Science Foundation (NSF)
- OSTI Identifier:
- 1977003
- Grant/Contract Number:
- SC0012774; DMR-1611342
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Computational Materials Science
- Additional Journal Information:
- Journal Volume: 208; Journal Issue: C; Journal ID: ISSN 0927-0256
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 36 MATERIALS SCIENCE; Ti-6Al-4V alloys; yield strength; polycrystal plasticity; dual-phase Ti alloys; machine learning; hardening rate
Citation Formats
McElfresh, Cameron, Roberts, Collin, He, Sicong, Prikhodko, Sergey, and Marian, Jaime. Using machine-learning to understand complex microstructural effects on the mechanical behavior of Ti-6Al-4V alloys. United States: N. p., 2022.
Web. doi:10.1016/j.commatsci.2022.111267.
McElfresh, Cameron, Roberts, Collin, He, Sicong, Prikhodko, Sergey, & Marian, Jaime. Using machine-learning to understand complex microstructural effects on the mechanical behavior of Ti-6Al-4V alloys. United States. https://doi.org/10.1016/j.commatsci.2022.111267
McElfresh, Cameron, Roberts, Collin, He, Sicong, Prikhodko, Sergey, and Marian, Jaime. Thu .
"Using machine-learning to understand complex microstructural effects on the mechanical behavior of Ti-6Al-4V alloys". United States. https://doi.org/10.1016/j.commatsci.2022.111267. https://www.osti.gov/servlets/purl/1977003.
@article{osti_1977003,
title = {Using machine-learning to understand complex microstructural effects on the mechanical behavior of Ti-6Al-4V alloys},
author = {McElfresh, Cameron and Roberts, Collin and He, Sicong and Prikhodko, Sergey and Marian, Jaime},
abstractNote = {Structural materials properties are highly dependent on their microstructure. Their microstructure is in turn affected by multiple fabrication and thermo-mechanical treatment parameters, all of which conform a highly-dimensional parametric space with often hidden correlations that are difficult to extract by experimentation alone. This is particularly true for alloys of the dual-phase Ti-6Al-4V family, with their greatly complex and rich microstructures, which combine several intrinsic length scales associated with multiple grain and subgrain structures, grains with different crystal lattices (α and β phases), and complex chemistry. In this paper we use a comprehensive set of machine learning techniques to develop predictive tools relating the yield strength and hardening rate of these alloys to a set of input parameters covering extensive ranges. The data generator is a finite-element crystal plasticity model for polycrystal deformation that takes into account slip anisotropy and employs standard dislocation evolution models for the α and β phases of Ti-based alloys. Our dataset includes over two thousand independent simulations and is used to train the machine learning models, which are then used to establish correlations between microstructural parameters and the alloys’ mechanical response. Our results point to the most influential parameters affecting yield strength and hardening rate, information that can then be used to guide experimental synthesis and characterization efforts to save time and resources.},
doi = {10.1016/j.commatsci.2022.111267},
journal = {Computational Materials Science},
number = C,
volume = 208,
place = {United States},
year = {Thu Mar 17 00:00:00 EDT 2022},
month = {Thu Mar 17 00:00:00 EDT 2022}
}
Works referenced in this record:
Plastic deformation and fracture behaviour of Ti–6Al–4V alloy loaded with high strain rate under various temperatures
journal, January 1998
- Lee, Woei-Shyan; Lin, Chi-Feng
- Materials Science and Engineering: A, Vol. 241, Issue 1-2
On Miller–Bravais indices and four-dimensional vectors
journal, May 1965
- Frank, F. C.
- Acta Crystallographica, Vol. 18, Issue 5
Effects of strain rate and stress state on mechanical properties of Ti-6Al-4V alloy
journal, November 2020
- Hu, Hongzhi; Xu, Zejian; Dou, Wang
- International Journal of Impact Engineering, Vol. 145
Dislocation dynamics in hexagonal close-packed crystals
journal, September 2016
- Aubry, S.; Rhee, M.; Hommes, G.
- Journal of the Mechanics and Physics of Solids, Vol. 94
The influence of microstructure and strain rate on the compressive deformation behavior of Ti-6Al-4V
journal, February 2003
- Wagoner Johnson, A. J.; Bull, C. W.; Kumar, K. S.
- Metallurgical and Materials Transactions A, Vol. 34, Issue 2
Deformation induced anisotropic responses of Ti–6Al–4V alloy Part II: A strain rate and temperature dependent anisotropic yield criterion
journal, November 2012
- Khan, Akhtar S.; Yu, Shaojuan; Liu, Haowen
- International Journal of Plasticity, Vol. 38
A study of the microstructural evolution during selective laser melting of Ti–6Al–4V
journal, May 2010
- Thijs, Lore; Verhaeghe, Frederik; Craeghs, Tom
- Acta Materialia, Vol. 58, Issue 9
Neural Networks in Materials Science.
journal, January 1999
- Bhadeshia, H. K. D. H.
- ISIJ International, Vol. 39, Issue 10
Influence of processing parameters on mechanical properties of Ti–6Al–4V alloy fabricated by MIM
journal, June 2010
- Obasi, G. C.; Ferri, O. M.; Ebel, T.
- Materials Science and Engineering: A, Vol. 527, Issue 16-17
Effects of microstructural factors on quasi-static and dynamic deformation behaviors of Ti-6Al-4V alloys with widmanstätten structures
journal, November 2003
- Lee, Dong-Geun; Lee, Sunghak; Lee, Chong Soo
- Metallurgical and Materials Transactions A, Vol. 34, Issue 11
Stochastic gradient boosting
journal, February 2002
- Friedman, Jerome H.
- Computational Statistics & Data Analysis, Vol. 38, Issue 4
Constitutive modeling and the effects of strain-rate and temperature on the formability of Ti–6Al–4V alloy sheet
journal, March 2014
- Li, Xiaoqiang; Guo, Guiqiang; Xiao, Junjie
- Materials & Design, Vol. 55
Manganese (Mn) removal prediction using extreme gradient model
journal, November 2020
- Bhagat, Suraj Kumar; Tiyasha, Tiyasha; Tung, Tran Minh
- Ecotoxicology and Environmental Safety, Vol. 204
Effects of alloying elements on the elastic properties of bcc Ti-X alloys from first-principles calculations
journal, February 2018
- Marker, Cassie; Shang, Shun-Li; Zhao, Ji-Cheng
- Computational Materials Science, Vol. 142
Feature Importance of Stabilised Rammed Earth Components Affecting the Compressive Strength Calculated with Explainable Artificial Intelligence Tools
journal, May 2020
- Anysz, Hubert; Brzozowski, Łukasz; Kretowicz, Wojciech
- Materials, Vol. 13, Issue 10
Effect of strain rate and temperature on strain hardening behavior of a dissimilar joint between Ti–6Al–4V and Ti17 alloys
journal, April 2014
- Wang, S. Q.; Liu, J. H.; Chen, D. L.
- Materials & Design (1980-2015), Vol. 56
Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors)
journal, April 2000
- Friedman, Jerome; Hastie, Trevor; Tibshirani, Robert
- The Annals of Statistics, Vol. 28, Issue 2
XGBoost: A Scalable Tree Boosting System
conference, January 2016
- Chen, Tianqi; Guestrin, Carlos
- Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16
Adaptive machine learning framework to accelerate ab initio molecular dynamics
journal, December 2014
- Botu, Venkatesh; Ramprasad, Rampi
- International Journal of Quantum Chemistry, Vol. 115, Issue 16
Crystal Plasticity Analysis of Microscopic Deformation Mechanisms and GN Dislocation Accumulation Depending on Vanadium Content in β Phase of Two-Phase Ti Alloy
journal, June 2019
- Kawano, Yoshiki; Ohashi, Tetsuya; Mayama, Tsuyoshi
- MATERIALS TRANSACTIONS, Vol. 60, Issue 6
Machine learning of mechanical properties of steels
journal, May 2020
- Xiong, Jie; Zhang, TongYi; Shi, SanQiang
- Science China Technological Sciences, Vol. 63, Issue 7
Bias in random forest variable importance measures: Illustrations, sources and a solution
journal, January 2007
- Strobl, Carolin; Boulesteix, Anne-Laure; Zeileis, Achim
- BMC Bioinformatics, Vol. 8, Issue 1
Machine Learning Reinforced Crystal Plasticity Modeling Under Experimental Uncertainty
journal, August 2020
- Acar, Pinar
- AIAA Journal, Vol. 58, Issue 8
Discovery of high-entropy ceramics via machine learning
journal, May 2020
- Kaufmann, Kevin; Maryanovsky, Daniel; Mellor, William M.
- npj Computational Materials, Vol. 6, Issue 1
Unraveling the temperature dependence of the yield strength in single-crystal tungsten using atomistically-informed crystal plasticity calculations
journal, March 2016
- Cereceda, David; Diehl, Martin; Roters, Franz
- International Journal of Plasticity, Vol. 78
Micro-cantilever testing of microstructural effects on plastic behavior of Ti–6Al–4V alloy
journal, August 2021
- Tanaka, Yukimi; Hattori, Koichiro; Harada, Yoshihisa
- Materials Science and Engineering: A, Vol. 823
Crystal Plasticity Finite Element Study of Incompatible Deformation Behavior in Two Phase Microstructure in Near β Titanium Alloy
journal, March 2015
- Bin, Tang; Shao, Xie; Yi, Liu
- Rare Metal Materials and Engineering, Vol. 44, Issue 3
Crystal plasticity modeling of β phase deformation in Ti-6Al-4V
journal, August 2017
- Moore, John A.; Barton, Nathan R.; Florando, Jeff
- Modelling and Simulation in Materials Science and Engineering, Vol. 25, Issue 7
Evolution of lattice strain in Ti–6Al–4V during tensile loading at room temperature
journal, December 2008
- Stapleton, Adam M.; Raghunathan, Seema L.; Bantounas, Ioannis
- Acta Materialia, Vol. 56, Issue 20
Factors determining room temperature mechanical properties of bimodal microstructures in Ti-6Al-4V alloy
journal, July 2018
- Chong, Yan; Bhattacharjee, Tilak; Park, Myeong-Heom
- Materials Science and Engineering: A, Vol. 730
Machine learning recommends affordable new Ti alloy with bone-like modulus
journal, April 2020
- Wu, Chun-Te; Chang, Hsiao-Tzu; Wu, Chien-Yu
- Materials Today, Vol. 34
A polycrystal plasticity model of strain localization in irradiated iron
journal, February 2013
- Barton, Nathan R.; Arsenlis, Athanasios; Marian, Jaime
- Journal of the Mechanics and Physics of Solids, Vol. 61, Issue 2
Modelling and prediction of mechanical properties for materials with hexagonal symmetry (zinc, titanium and zirconium alloys)
journal, October 1997
- Fundenberger, J. J.; Philippe, M. J.; Wagner, F.
- Acta Materialia, Vol. 45, Issue 10
Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling
journal, November 2003
- Svetnik, Vladimir; Liaw, Andy; Tong, Christopher
- Journal of Chemical Information and Computer Sciences, Vol. 43, Issue 6
Effect of microstructure on deformation behavior of Ti–6Al–4V alloy during compressing process
journal, April 2012
- Guan, Ren Guo; Je, Young Tae; Zhao, Zhan Yong
- Materials & Design (1980-2015), Vol. 36
Effect of cooling rate on microstructure of Ti-6Al-4V forging
journal, December 2002
- Senkov, O. N.; Valencia, J. J.; Senkova, S. V.
- Materials Science and Technology, Vol. 18, Issue 12
Opportunities and Challenges for Machine Learning in Materials Science
journal, July 2020
- Morgan, Dane; Jacobs, Ryan
- Annual Review of Materials Research, Vol. 50, Issue 1
Machine learning in materials science
journal, August 2019
- Wei, Jing; Chu, Xuan; Sun, Xiang‐Yu
- InfoMat, Vol. 1, Issue 3
A steel property optimization model based on the XGBoost algorithm and improved PSO
journal, March 2020
- Song, Kai; Yan, Feng; Ding, Ting
- Computational Materials Science, Vol. 174
Constitutive analysis of compressive deformation behavior of ELI-grade Ti–6Al–4V with different microstructures
journal, December 2011
- Park, Chan Hee; Son, Young Il; Lee, Chong Soo
- Journal of Materials Science, Vol. 47, Issue 7
Diffuse-interface polycrystal plasticity: expressing grain boundaries as geometrically necessary dislocations
journal, July 2017
- Admal, Nikhil Chandra; Po, Giacomo; Marian, Jaime
- Materials Theory, Vol. 1, Issue 1
Effect of Strain Rate on Microstructure Evolution and Mechanical Behavior of Titanium-Based Materials
journal, October 2020
- Markovsky, Pavlo E.; Janiszewski, Jacek; Bondarchuk, Vadim I.
- Metals, Vol. 10, Issue 11
Prediction of tensile strength of polymer carbon nanotube composites using practical machine learning method
journal, September 2020
- Le, Tien-Thinh
- Journal of Composite Materials, Vol. 55, Issue 6
A three-dimensional crystal plasticity model for duplex Ti–6Al–4V
journal, September 2007
- Mayeur, J. R.; McDowell, D. L.
- International Journal of Plasticity, Vol. 23, Issue 9
A titanium alloys design method based on high-throughput experiments and machine learning
journal, March 2021
- Zhu, Chengpeng; Li, Chao; Wu, Di
- Journal of Materials Research and Technology, Vol. 11
Effect of subtransus heat treatment on the microstructure and mechanical properties of additively manufactured Ti-6Al-4V alloy
journal, February 2018
- Zhang, Xiang-Yu; Fang, Gang; Leeflang, Sander
- Journal of Alloys and Compounds, Vol. 735
Machine learning prediction of elastic properties and glass-forming ability of bulk metallic glasses
journal, April 2019
- Xiong, Jie; Zhang, Tong-Yi; Shi, San-Qiang
- MRS Communications, Vol. 9, Issue 02
A Comparative Study of Feature Selection Methods for Stress Hotspot Classification in Materials
journal, June 2018
- Mangal, Ankita; Holm, Elizabeth A.
- Integrating Materials and Manufacturing Innovation, Vol. 7, Issue 3
A predicting model for properties of steel using the industrial big data based on machine learning
journal, April 2019
- Guo, Shun; Yu, Jinxin; Liu, Xingjun
- Computational Materials Science, Vol. 160
Elastic constants of body-centered-cubic titanium monocrystals
journal, May 2004
- Ledbetter, Hassel; Ogi, Hirotsugu; Kai, Satoshi
- Journal of Applied Physics, Vol. 95, Issue 9
Effect of texture and slip mode on the anisotropy of plastic flow and flow softening during hot working of Ti-6Al-4V
journal, July 2001
- Semiatin, S. L.; Bieler, T. R.
- Metallurgical and Materials Transactions A, Vol. 32, Issue 7
Constitutive equations for elevated temperature flow stress of Ti–6Al–4V alloy considering the effect of strain
journal, March 2011
- Cai, Jun; Li, Fuguo; Liu, Taiying
- Materials & Design, Vol. 32, Issue 3
An empirical comparison of supervised learning algorithms
conference, January 2006
- Caruana, Rich; Niculescu-Mizil, Alexandru
- Proceedings of the 23rd international conference on Machine learning - ICML '06
Modeling Ti–6Al–4V using crystal plasticity, calibrated with multi-scale experiments, to understand the effect of the orientation and morphology of the α and β phases on time dependent cyclic loading
journal, January 2021
- Kapoor, Kartik; Ravi, Priya; Noraas, Ryan
- Journal of the Mechanics and Physics of Solids, Vol. 146
Machine Learning-Based Classification of Dislocation Microstructures
journal, June 2019
- Steinberger, Dominik; Song, Hengxu; Sandfeld, Stefan
- Frontiers in Materials, Vol. 6
Microplasticity at Room Temperature in α/β Titanium Alloys
journal, August 2020
- Hémery, S.; Villechaise, P.; Banerjee, D.
- Metallurgical and Materials Transactions A
An analysis of the low temperature, low and high strain-rate deformation of Ti−6Al−4V
journal, May 1989
- Follansbee, P. S.; Gray, G. T.
- Metallurgical Transactions A, Vol. 20, Issue 5
Effect of microstructure on the fatigue properties of Ti–6Al–4V titanium alloys
journal, April 2013
- Wu, G. Q.; Shi, C. L.; Sha, W.
- Materials & Design, Vol. 46
Dislocation density based model for plastic deformation and globularization of Ti-6Al-4V
journal, November 2013
- Babu, Bijish; Lindgren, Lars-Erik
- International Journal of Plasticity, Vol. 50
Constitutive modeling of Ti-6Al-4V at a wide range of temperatures and strain rates
journal, May 2017
- Tabei, A.; Abed, F. H.; Voyiadjis, G. Z.
- European Journal of Mechanics - A/Solids, Vol. 63
Effect of heat treatment on mechanical properties of Ti–6Al–4V ELI alloy
journal, April 2009
- Venkatesh, B. D.; Chen, D. L.; Bhole, S. D.
- Materials Science and Engineering: A, Vol. 506, Issue 1-2
Microstructural effects on the mechanical behavior of B-modified Ti–6Al–4V alloys
journal, September 2007
- Sen, I.; Tamirisakandala, S.; Miracle, D.
- Acta Materialia, Vol. 55, Issue 15