Data Augmentation of Micrographs and Prediction of Impact Toughness for Cast Austenitic Steel by Machine Learning
Abstract
:1. Introduction
2. Methods and Model
2.1. Data Augmentation Module
2.2. Microstructure–Property Linkage Module
3. Results and Discussion
3.1. Data Preparation
3.2. Data Augmentation Processing
3.3. Microstructure–Property Linkage
3.4. Predicted Results of Microstructure–Property Model
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Rajan, K. Materials Informatics: The Materials “Gene” and Big Data. Annu. Rev. Mater. Res. 2015, 45, 153. [Google Scholar] [CrossRef] [Green Version]
- Ge, M.; Su, F.; Zhao, Z.; Su, D. Deep learning analysis on microscopic imaging in materials science. Mater. Today Nano 2020, 11, 100087. [Google Scholar] [CrossRef]
- Konda, N.; Verma, R.; Jayaganthan, R. Machine Learning based predictions of fatigue crack growth rate of additively manufactured Ti6Al4V. Metals 2022, 12, 50. [Google Scholar] [CrossRef]
- Honysz, R. Modeling the Chemical Composition of Ferritic Stainless Steels with the Use of Artificial Neural Networks. Metals 2021, 11, 724. [Google Scholar] [CrossRef]
- Choi, W.; Won, S.; Kim, G.-S.; Kang, N. Artificial Neural NetworkModelling of the Effect of Vanadium Addition on the Tensile Properties and Microstructure of High-Strength Tempcore Rebars. Materials 2022, 15, 3781. [Google Scholar] [CrossRef] [PubMed]
- Churyumov, A.; Kazakova, A.; Churyumova, T. Modelling of the Steel High-Temperature Deformation Behaviour Using Artificial Neural Network. Metals 2022, 12, 447. [Google Scholar] [CrossRef]
- Chen, S.; Kaufmann, T. Development of data-driven machine learning models for the prediction of casting surface defects. Metals 2022, 12, 1. [Google Scholar] [CrossRef]
- Wang, C.S.; Fu, H.D.; Jiang, L.; Xue, D.Z.; Xie, J.X. A property-oriented design strategy for high performance copper alloys via machine learning. npj Comput. Mater. 2019, 5, 87. [Google Scholar] [CrossRef] [Green Version]
- Wu, Y.J.; Fang, L.; Xu, Y.B. Predicting interfacial thermal resistance by machine learning. npj Comput. Mater. 2019, 5, 56. [Google Scholar] [CrossRef] [Green Version]
- Ward, L.; O’Keeffe, S.C.; Stevick, J.; Jelbert, G.R.; Aykol, M.; Wolverton, C. A machine learning approach for engineering bulk metallic glass alloys. Acta Mater. 2018, 159, 102. [Google Scholar] [CrossRef]
- Shin, D.; Yamamoto, Y.; Brady, M.P.; Lee, S.; Haynes, J.A. Modern data analytics approach to predict creep of high-temperature alloys. Acta Mater. 2019, 168, 321. [Google Scholar] [CrossRef] [Green Version]
- Yabansu, Y.C.; Steinmetz, P.; Hötzer, J.; Kalidindi, S.R.; Nestler, B. Extraction of reduced-order process-structure linkages from phase-field simulations. Acta Mater. 2017, 124, 182–194. [Google Scholar] [CrossRef]
- Yucel, B.; Yucel, S.; Ray, A.; Duprez, L.; Kalidindi, S.R. Mining the correlations between optical micrographs and mechanical properties of cold-rolled HSLA steels using machine learning approaches. Integr. Mater. Manuf. Innov. 2020, 9, 240–256. [Google Scholar] [CrossRef]
- Khatavkar, N.; Swetlana, S.; Singh, A.K. Accelerated prediction of Vickers hardness of Co- and Ni-based superalloys from microstructure and composition using advanced image processing techniques and machine learning. Acta Mater. 2020, 196, 295–303. [Google Scholar] [CrossRef]
- Fan, Y.; Yang, X.; Shi, D.; Tan, L.; Huang, W. Quantitative mapping of service process-microstructural degradation-property deterioration for a Ni-based superalloy based on chord length distribution imaging process. Mater. Des. 2021, 203, 109561. [Google Scholar] [CrossRef]
- Paulson, N.H.; Priddy, M.W.; McDowell, D.L.; Kalidindi, S.R. Reduced-order structure-property linkages for polycrystalline microstructures based on 2-point statistics. Acta Mater. 2017, 129, 428. [Google Scholar] [CrossRef] [Green Version]
- Fernandez-Zelaia, P.; Joseph, V.; Kalidindi, S.R.; Melkote, S.N. Estimating mechanical properties from spherical indentation using Bayesian approaches. Mater. Des. 2018, 147, 92. [Google Scholar] [CrossRef]
- Hart, G.L.W.; Mueller, T.; Toher, C.; Curtarolo, S. Machine learning for alloys. Nat. Rev. Mater. 2021, 6, 730. [Google Scholar] [CrossRef]
- Morgan, D.; Jacobs, R. Opportunities and challenges for machine learning in materials science. Annu. Rev. Mater. Res. 2020, 50, 71. [Google Scholar] [CrossRef]
- Thankachan, T.; Prakash, K.S.; Pleass, C.D.; Rammasamy, D.; Prabakaran, B.; Jothi, S. Artificial neural network to predict the degraded mechanical properties of metallic materials due to the presence of hydrogen. Int. J. Hydrogen Energy 2017, 42, 28612. [Google Scholar] [CrossRef]
- Feng, S.; Zhou, H.; Dong, H. Using deep neural network with small dataset to predict material defects. Mater. Des. 2019, 162, 300–310. [Google Scholar] [CrossRef]
- Kondo, R.; Yamakawa, S.; Masuoka, Y.; Tajima, S.; Asahi, R. Microstructure recognition using convolutional neural networks for prediction of ionic conductivity in ceramics. Acta Mater. 2017, 141, 29–38. [Google Scholar] [CrossRef]
- Cecena, A.; Daia, H.; Yabansub, C.Y.C.; Kalidindia, S.R.; Song, L. Material structure-property linkages using three-dimensional convolutional neural networks. Acta Mater. 2017, 11, 53. [Google Scholar] [CrossRef]
- Nouira, A.; Crivello, J.C.; Sokolovska, N. Crystal GAN: Learning to discover crystallographic structures with generative adversarial networks. arXiv 2019, arXiv:1810.11203. [Google Scholar]
- Xie, T.; Grossman, J.C. Hierarchical visualization of materials space with graph convolutional neural networks. J. Chem. Phys. 2018, 149, 174111. [Google Scholar] [CrossRef]
- Chen, C.; Ye, W.; Zuo, Y.; Zheng, C.; Ong, S.P. Graph networks as a universal machine learning framework for molecules and crystals. Chem. Mater. 2019, 31, 3564. [Google Scholar] [CrossRef] [Green Version]
- Wang, C.; Shi, D.; Li, S. A study on establishing a microstructure-related hardness model with precipitate segmentation using deep learning method. Materials 2020, 13, 1256. [Google Scholar] [CrossRef] [Green Version]
- Reiter, J.; Bernhard, C.; Presslinger, H. Austenite grain size in the continuous casting process: Metallographic methods and evaluation. Mater. Charact. 2008, 59, 737–746. [Google Scholar] [CrossRef]
- Gatys, L.; Ecker, A.S.; Bethge, M. Image Style Transfer Using Convolutional Neural Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016; pp. 2414–2423. [Google Scholar]
Operation | Filter Size and Parameters | Input | Output |
---|---|---|---|
Conv2D | 1 × 1, S = 1, P = 0 | X | X1 |
Conv2D | 3 × 3, S = 1, P = 1 | X1 | X2 |
Concat1 | - | X1 + X2 | Conc1 |
Conv2D | 5 × 5, S = 1, P = 2 | Conc1 | X3 |
Concat2 | - | X2 + X3 | Conc2 |
Conv2D | 7 × 7, S = 1, P = 1 | Conc2 | X4 |
Concat3 | - | X1 + X2 + X3 + X4 | Conc3 |
Conv2D | 3 × 3, S = 1, P = 1 | Conc3 | X5 |
Final output | ReLu(X5*X-X5) | - | - |
Operation | Filter Size and Parameters | Output Size (W × H × C) |
---|---|---|
Input | - | 200 × 200 × 1 |
Conv2D | 3 × 3, S = 1, P = 1 | 200 × 200 × 8 |
Conv2D | 3 × 3, S = 1, P = 1 | 200 × 200 × 8 |
MaxPool | 2 × 2, S = 2 | 100 × 100 × 8 |
Conv2D | 3 × 3, S = 1, P = 1 | 100 × 100 × 16 |
Conv2D | 3 × 3, S = 1, P = 1 | 100 × 100 × 16 |
MaxPool | 2 × 2, S = 2 | 50 × 50 × 16 |
Conv2D | 3 × 3, S = 1, P = 1 | 50 × 50 × 32 |
Conv2D | 3 × 3, S = 1, P = 1 | 50 × 50 × 32 |
AAP | 5 × 5 | 10 × 10 × 1 |
FC | - | 100 × 1 |
FC | - | 50 × 1 |
Output | - | 1 × 1 |
1030 (°C) | 1080 (°C) | 1130 (°C) | 1180 (°C) | 1230 (°C) | 1280 (°C) | ||||||
328.4 (J) | 368.4 (J) | 374.3 (J) | 353.9 (J) | 341.2 (J) | 310.6 (J) |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Xu, G.; Zhang, X.; Xu, J. Data Augmentation of Micrographs and Prediction of Impact Toughness for Cast Austenitic Steel by Machine Learning. Metals 2023, 13, 107. https://doi.org/10.3390/met13010107
Xu G, Zhang X, Xu J. Data Augmentation of Micrographs and Prediction of Impact Toughness for Cast Austenitic Steel by Machine Learning. Metals. 2023; 13(1):107. https://doi.org/10.3390/met13010107
Chicago/Turabian StyleXu, Gang, Xiaotong Zhang, and Jinwu Xu. 2023. "Data Augmentation of Micrographs and Prediction of Impact Toughness for Cast Austenitic Steel by Machine Learning" Metals 13, no. 1: 107. https://doi.org/10.3390/met13010107