journal article·2025-11

Machine learning for complex microstructures - latent features as an alternative to physical features in steel structure-property relationships

Kurt Lejaeghere, Joshua Stuckner, Koenraad Theuwissen, Steven M. Arnold, Lode Duprez

Publisher page

Abstract

No abstract is available for this record. The assistant can identify its topic from the title, but cannot infer the study’s results.

Source: Not provided · Quality: missing

Research context

OpenAlex topics: Manufacturing Process and Optimization

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

References (54)

Show source-provided references
1. ASTM E112-10 · 2013
2. Digital fingerprinting of microstructures
3. AQUAMI: an open source Python package and GUI for the automatic quantitative analysis of morphologically complex multiphase materials
4. Microstructure reconstructions from 2-point statistics using phase-recovery algorithms10.1016/j.actamat.2007.10.044 ↗
5. Microstructure-based knowledge systems for capturing process-structure evolution linkages10.1016/j.cossms.2016.05.002 ↗
6. Design of 3D statistically similar representative volume elements based on Minkowski functionals10.1016/j.mechmat.2015.03.005 ↗
7. Novel microstructure quantification framework for databasing, visualization, and analysis of microstructure data10.1186/2193-9772-2-3 ↗
8. A new framework for rotationally invariant two-point spatial correlations in microstructure datasets10.1016/j.actamat.2018.07.056 ↗
9. Reduced-order models correlating Ti Beta 21S microstructures and Vickers hardness measurements10.37256/est.4220233136 ↗
10. Accelerated prediction of Vickers hardness of co- and Ni-based superalloys from microstructure and composition using advanced image processing techniques and machine learning10.1016/j.actamat.2020.06.042 ↗
11. Distinctive image features from scale-invariant keypoints10.1023/B:VISI.0000029664.99615.94 ↗
12. A computer vision approach for automated analysis and classification of microstructural image data10.1016/j.commatsci.2015.08.011 ↗
13. Exploring the microstructure manifold: image texture representations applied to ultrahigh carbon steel microstructures10.1016/j.actamat.2017.05.014 ↗
14. Recent advances and applications of machine learning in solid-state materials science10.1038/s41524-019-0221-0 ↗
15. Applying improved optical recognition with machine learning on sorting Cu impurities in steel scrap10.1007/s40831-020-00300-8 ↗
16. Localization of the slab information in factory scenes using deep convolutional neural networks10.1016/j.eswa.2017.01.026 ↗
17. Image-based surface defect detection using deep learning: a review10.1115/1.4049535 ↗
18. Deep learning-based method for microstructure-property linkage of dual-phase steel10.1016/j.commatsci.2023.112285 ↗
19. Image regression analysis for linking the microstructure and property of steel
20. Towards accurate processing-structure-property links using deep learning10.1016/j.scriptamat.2021.114478 ↗
21. Feature extraction and microstructural classification of hot stamping ultra-high strength steel by machine learning10.1007/s11837-022-05265-5 ↗
22. Unsupervised machine learning via transfer learning and k-means clustering to classify materials image data10.1007/s40192-021-00205-8 ↗
23. Compact representations of microstructure images using triplet networks10.1038/s41524-020-00423-2 ↗
24. Microstructure segmentation with deep learning encoders pre-trained on a large microscopy dataset10.1038/s41524-022-00878-5 ↗
25. Efficient reconstruction of prior austenite grains in steel from etched light optical micrographs using deep learning and annotations from correlative microscopy10.3389/fmats.2022.1033505 ↗
26. Alrfou · 2023 · arXiv:2308.13917
27. Inverse design of dual-phase steel microstructures using generative machine learning model and Bayesian optimization10.1016/j.ijplas.2023.103776 ↗
28. Microstructure estimation by combining deep learning and phase transformation model10.2355/isijinternational.ISIJINT-2023-365 ↗
29. Super-resolving material microstructure image via deep learning for microstructure characterization and mechanical behavior analysis10.1038/s41524-021-00568-8 ↗
30. Machine learning of microstructure–property relationships in materials leveraging microstructure representation from foundational vision transformers
31. ImageNet: A large-scale hierarchical image database
32. UHCSDB: UltraHigh Carbon Steel Micrograph DataBase. Tools for exploring large heterogeneous microstructure datasets10.1007/s40192-017-0097-0 ↗
33. The morphology of martensite in iron alloys10.1007/BF02814873 ↗
34. The morphology and crystallography of lath martensite in Fe-C alloys10.1016/S1359-6454(02)00577-3 ↗
35. The morphology and crystallography of lath martensite in alloy steels10.1016/j.actamat.2006.07.009 ↗
36. Stuckner · 2025
37. Deep residual learning for image recognition
38. Aggregated residual transformations for deep neural networks
39. Squeeze-and-excitation networks
40. Simonyan · 2014
41. Batch normalization: accelerating deep network training by reducing internal covariate shift
42. Inception-v4, inception-ResNet and the impact of residual connections on learning
43. LIII. On lines and planes of closest fit to systems of points in space10.1080/14786440109462720 ↗
44. Random decision forests
45. Krige · 1951
46. Scikit-learn: machine learning in Python
47. UMAP: uniform manifold approximation and projection10.21105/joss.00861 ↗
48. A unified approach to interpreting model predictions
49. Catastrophic interference in connectionist networks: the sequential learning problem10.1016/S0079-7421(08)60536-8 ↗
50. Grad-CAM: Visual explanations from deep networks via gradient-based localization
51. Understanding deep networks via extremal perturbations and smooth masks
52. Learning important features through propagating activation differences
53. Effect of microstructure on strength and toughness of heat-treated low alloy structural steels10.1007/BF02665319 ↗
54. Effect of block size on the strength of lath martensite in low carbon steels10.1016/j.msea.2005.12.048 ↗