journal article·2023-10

Prediction and characterization of microstructure evolution based on deep learning method and in-situ scanning electron microscope

Ni Wang, Jianli Zhou, Guanghao Guo, Yixu Zhang, Wenjie Gao, Jin Wang, Liang Tang, Yuefei Zhang, Ze Zhang

Publisher page

Abstract

Microstructure significantly affects materials` physical properties. Predicting and characterizing temporal microstructural evolution is valuable and helpful for understanding the processing-structure-property relationship but is rarely conducted on experimental data for its scarcity, unevenness, and uncontrollability. As such, a self-designed in-situ tensile system in conjunction with a scanning electron microscope was adopted to observe the grain evolution during the tensile process. We then used a deep learning-based model to capture grain growth behavior from the experimental data and characterize grain boundary and orientation evolution. We validated the framework`s effectiveness by comparing the predictions and ground truths from quantitative and qualitative perspectives, using data from (1) a tensile experimental dataset and (2) a phase-field simulation dataset. Based on the two datasets, the model`s predicted results showed good agreement with ground truths in the short term, and local differences emerged in the long term. This pipeline opened an opportunity for the characterization of microstructure evolution and could be easily extended to other scenarios, such as dendrite growth and martensite transformation.
Source: expertdata · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Machine Learning in Materials Science · Solidification and crystal growth phenomena · Microstructure and Mechanical Properties of Steels

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (36)

Show source-provided references
1. Effect of grain size on deformation and fracture of Inconel718: an in-situ SEM-EBSD-DIC investigation[J]10.1016/j.msea.2022.144361 ↗
2. Effects of pre-treatments on mechanical properties and fracture mechanism of a nickel-based superalloy[J]10.1016/j.msea.2016.10.058 ↗
3. Selective anisotropy of mechanical properties in Inconel718 alloy10.3390/ma14143869 ↗
4. Self-supervised learning and prediction of microstructure evolution with convolutional recurrent neural networks[J]10.1016/j.patter.2021.100243 ↗
5. Prediction and mechanism explain of austenite-grain growth during reheating of alloy steel using XAI[J]10.1016/j.jmrt.2022.09.119 ↗
6. Phase-field models for microstructure evolution[J]10.1146/annurev.matsci.32.112001.132041 ↗
7. A deep learning method for predicting microvoid growth in heterogeneous polycrystals[J]10.1016/j.engfracmech.2022.108332 ↗
8. Phase-field modeling of microstructure evolution: recent applications, perspectives and challenges[J]10.1016/j.pmatsci.2021.100810 ↗
9. A full-scale Monte Carlo Potts model and real time conversion under non-uniform temperature distribution[J]10.1016/j.matdes.2022.111439 ↗
10. Predictive model for austenite grain growth during reheating of alloy steels[J]10.2355/isijinternational.53.1902 ↗
11. Phase field modelling of abnormal grain growth[J]10.3390/ma12244048 ↗
12. Role of inclination dependence of grain boundary energy on the microstructure evolution during grain growth[J]10.1016/j.actamat.2020.02.043 ↗
13. Three-dimensional phase-field simulation of microstructural evolution in three-phase materials with different interfacial energies and different diffusivities[J]10.1007/s10853-017-1465-z ↗
14. Analysis of grain topology and volumetric growth rate relation in three-dimensional normal grain growth[J]10.1016/j.actamat.2018.04.056 ↗
15. Computer simulation of grain growth—I. kinetics[J]10.1016/0001-6160(84)90151-2 ↗
16. Recrystallization and grain growth[J]10.1016/0502-8205(52)90009-9 ↗
17. Mullins · 1999
18. A novel physics-regularized interpretable machine learning model for grain growth[J]10.1016/j.matdes.2022.111032 ↗
19. Accelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods[J]
20. Computer simulation of grain growth using a continuum field model[J]10.1016/S1359-6454(96)00200-5 ↗
21. Grain growth in four dimensions: a comparison between simulation and experiment[J]10.1016/j.actamat.2014.06.028 ↗
22. Grain boundary velocity and curvature are not correlated in Ni polycrystals[J]10.1126/science.abj3210 ↗
23. Simulation and theory of abnormal grain growth—anisotropic grain boundary energies and mobilities[J]10.1016/0001-6160(89)90117-X ↗
24. Crystal structure prediction via deep learning[J]10.1021/jacs.8b03913 ↗
25. Microstructural materials design via deep adversarial learning methodology[J]10.1115/1.4041371 ↗
26. Deep neural networks for accurate predictions of crystal stability[J]10.1038/s41467-018-06322-x ↗
27. Deep learning approaches for mining structure-property linkages in high contrast composites from simulation datasets[J]10.1016/j.commatsci.2018.05.014 ↗
28. Deep learning and crystal plasticity: A preconditioning approach for accurate orientation evolution prediction[J]
29. Studying the micromechanical behaviors of a polycrystalline metal by artificial neural networks[J]10.1016/j.actamat.2021.117006 ↗
30. A novel instrument for investigating the dynamic microstructure evolution of high temperature service materials up to 1150 degrees C in scanning electron microscope[J]10.1063/1.5142807 ↗
31. Quantitative analysis of grain boundary properties in a generalized phase field model for grain growth in anisotropic systems[J]
32. 2022 · 2023
33. PredRNN: a recurrent neural network for spatiotemporal predictive learning
34. Wang · 2018
35. PredRNN: Recurrent neural networks for predictive learning using spatiotemporal LSTMs
36. Yunbo · 2020