Determining crystallographic orientation via hybrid convolutional neural network

Ding, Zegang; Zhu, Chaoyi; Graef, Marc De

doi:10.1016/j.matchar.2021.111213

Cited by 8 publications

(3 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As model architectures and training algorithms become mature and modularized, it is exciting to see more and more applications in science and engineering fields, including those in material characterization. Specifically in EBSD, we have proposed two models, EBSD-CNN 18 and EBSDDI-CNN 19 , to realize end-to-end and hybrid pattern indexing, respectively. Other groups have put forth models with various output spaces to predict other attributes from EBSD patterns, such as crystal symmetry 20 and phase identification 21 .…”

Section: Introductionmentioning

confidence: 99%

Parametric simulation of electron backscatter diffraction patterns through generative models

Ding,

De Graef

2023

npj Comput Mater

Self Cite

View full text Add to dashboard Cite

Recently, discriminative machine learning models have been widely used to predict various attributes from Electron Backscatter Diffraction (EBSD) patterns. However, there has never been any generative model developed for EBSD pattern simulation. On one hand, the training of generative models is much harder than that of discriminative ones; On the other hand, numerous variables affecting EBSD pattern formation make the input space high-dimensional and its relationship with the distribution of backscattered electrons complicated. In this study, we propose a framework (EBSD-CVAE/GAN) with great flexibility and scalability to realize parametric simulation of EBSD patterns. Compared with the frequently used forward model, EBSD-CVAE/GAN can take variables more than just orientation and generate corresponding EBSD patterns in a single run. The accuracy and quality of generated patterns are systematically evaluated. The model does not only summarize a distribution of backscattered electrons at a higher level, but also mitigates data scarcity in this field.

show abstract

Section: Introductionmentioning

confidence: 99%

Parametric simulation of electron backscatter diffraction patterns through generative models

Ding,

De Graef

2023

npj Comput Mater

Self Cite

View full text Add to dashboard Cite

show abstract

“…To improve indexing accuracy, multiple algorithmic approaches have been developed for better Kikuchi pattern mapping 22,23 , which improves both the precision and accuracy of the orientations shown at each pixel. Machine learning approaches have also been used to accelerate several tasks in the EBSD map construction process, including Kikuchi pattern indexing 24 , classification 25 , and crystal identification 26 . Recently, a residual-based neural network with traditional L 1 loss (ResNet) was used to produce superresolved EBSD maps from inverse pole figure (IPF) color and Euler angles as an image input 27 .…”

Section: Introductionmentioning

confidence: 99%

Adaptable physics-based super-resolution for electron backscatter diffraction maps

et al. 2022

View full text Add to dashboard Cite

In computer vision, single-image super-resolution (SISR) has been extensively explored using convolutional neural networks (CNNs) on optical images, but images outside this domain, such as those from scientific experiments, are not well investigated. Experimental data is often gathered using non-optical methods, which alters the metrics for image quality. One such example is electron backscatter diffraction (EBSD), a materials characterization technique that maps crystal arrangement in solid materials, which provides insight into processing, structure, and property relationships. We present a broadly adaptable approach for applying state-of-art SISR networks to generate super-resolved EBSD orientation maps. This approach includes quaternion-based orientation recognition, loss functions that consider rotational effects and crystallographic symmetry, and an inference pipeline to convert network output into established visualization formats for EBSD maps. The ability to generate physically accurate, high-resolution EBSD maps with super-resolution enables high-throughput characterization and broadens the capture capabilities for three-dimensional experimental EBSD datasets.

show abstract

“…CNNs are important in a variety of activities/functions such as image processing, computer vision tasks such as localization and segmentation, and predicting cracks on materials using microscope techniques by identifying grains and boundaries. CNNs are particularly popular in DL because they play a vital role in these rapidly increasing and new domains [5]. In addition, one of the most advanced techniques in material creation and investigation is Electron Backscatter Diffraction (EBSD).…”

Section: Introductionmentioning

confidence: 99%

Deep Learning CNN for the Prediction of Grain Orientations on EBSD Patterns of AA5083 Alloy

Suker

2022

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

Indexing of Electron Backscatter Diffraction (EBSD) is a well-established method of crystalline material characterization that provides phase and orientation information about the crystals on the material surface. A deep learning Convolutional Neural Network was trained to predict crystal orientation from the EBSD patterns based on the mean disorientation error between the predicted crystal orientation and the ground truth. The CNN is trained using EBSD images for different deformation conditions of AA5083.

show abstract

Determining crystallographic orientation via hybrid convolutional neural network

Cited by 8 publications

References 57 publications

Parametric simulation of electron backscatter diffraction patterns through generative models

Parametric simulation of electron backscatter diffraction patterns through generative models

Adaptable physics-based super-resolution for electron backscatter diffraction maps

Deep Learning CNN for the Prediction of Grain Orientations on EBSD Patterns of AA5083 Alloy

Contact Info

Product

Resources

About