Exploring 2D X-ray diffraction phase fraction analysis with convolutional neural networks: Insights from kinematic-diffraction simulations

Yue, Weiqi; Mehdi, Mohommad Redad; Tripathi, Pawan K.; Willard, Matthew A.; Ernst, Frank; French, Roger H.

doi:10.1557/s43580-024-00862-9

Exploring 2D X-ray diffraction phase fraction analysis with convolutional neural networks: Insights from kinematic-diffraction simulations

Journal Article · Thu May 23 00:00:00 EDT 2024 · MRS Advances

DOI:https://doi.org/10.1557/s43580-024-00862-9· OSTI ID:2356950

Yue, Weiqi; Mehdi, Mohommad Redad; Tripathi, Pawan K.; Willard, Matthew A.; Ernst, Frank;

Abstract

Deep-learning models are effective for analyzing the complex information in 2D X-ray diffraction (XRD) patterns. Accurately collecting parameters of the material sample is crucial during model training, significantly impacting model performance. In this study, we employ a kinematic-diffraction simulator to generate simulated 2D XRD patterns for Ti–6Al–4V alloy, allowing precise control of sample parameters. These simulated patterns are used to train convolutional neural networks, predicting $$$$\upbeta$$$$ $β$ -phase volume fractions. The training data set consists exclusively of 2D XRD patterns with pure $$$$\upalpha$$$$ $α$ - or pure $$$$\upbeta$$$$ $β$ -phase, while the testing set incorporates patterns with intermediate phase volume fraction. In particular, we investigate how the architectures of the model influence prediction reliability and computational performance. Experimental results reveal that, with appropriate training, the convolutional neural network accurately detects intermediate phase volume fractions even trained with only pure-phase patterns, achieving a mean square error accuracy of $$$$9.4 \times 10^{-4}$$$$ $9.4 \times 10^{- 4}$ .

Graphical abstract

View Journal Article

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: NA0004104

OSTI ID:: 2356950

Journal Information:: MRS Advances, Journal Name: MRS Advances Journal Issue: 11 Vol. 9; ISSN 2059-8521

Publisher:: Cambridge University Press (CUP)Copyright Statement

Country of Publication:: United States

Language:: English

References (21)

Early Stopping - But When? Prechelt, Lutz Lecture Notes in Computer Science https://doi.org/10.1007/3-540-49430-8_3	book	January 1998
Benchmarking the NVIDIA V100 GPU and Tensor Cores Martineau, Matt; Atkinson, Patrick; McIntosh-Smith, Simon Euro-Par 2018: Parallel Processing Workshops, p. 444-455 https://doi.org/10.1007/978-3-030-10549-5_35	book	December 2018
Evolution of the Microstructure of Laser Powder Bed Fusion Ti-6Al-4V During Post-Build Heat Treatment Brown, D. W.; Anghel, V.; Balogh, L. Metallurgical and Materials Transactions A, Vol. 52, Issue 12 https://doi.org/10.1007/s11661-021-06455-7	journal	October 2021
Phase Identification in Synchrotron X-ray Diffraction Patterns of Ti–6Al–4V Using Computer Vision and Deep Learning Yue, Weiqi; Tripathi, Pawan K.; Ponon, Gabriel Integrating Materials and Manufacturing Innovation, Vol. 13, Issue 1 https://doi.org/10.1007/s40192-023-00328-0	journal	January 2024
Synchrotron X-ray diffraction study of the phase transformations in titanium alloys Malinov, S.; Sha, W.; Guo, Z. Materials Characterization, Vol. 48, Issue 4 https://doi.org/10.1016/S1044-5803(02)00286-3	journal	June 2002
A tutorial on automatic hyperparameter tuning of deep spectral modelling for regression and classification tasks Passos, Dário; Mishra, Puneet Chemometrics and Intelligent Laboratory Systems, Vol. 223 https://doi.org/10.1016/j.chemolab.2022.104520	journal	April 2022
Effect of heat treatment on microstructure evolution and mechanical properties of selective laser melted Ti–6Al–4V and TiB/Ti–6Al–4V composite: A comparative study Li, Hailiang; Jia, Dechang; Yang, Zhihua Materials Science and Engineering: A, Vol. 801 https://doi.org/10.1016/j.msea.2020.140415	journal	January 2021
Effect of pressure on stacking fault energy and deformation behavior of face-centered cubic metals Linda, Albert; Tripathi, Pawan Kumar; Nagar, Sainyam Materialia, Vol. 26 https://doi.org/10.1016/j.mtla.2022.101598	journal	December 2022
A deep-learning technique for phase identification in multiphase inorganic compounds using synthetic XRD powder patterns Lee, Jin-Woong; Park, Woon Bae; Lee, Jin Hee Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-019-13749-3	journal	January 2020
A deep convolutional neural network for real-time full profile analysis of big powder diffraction data Dong, Hongyang; Butler, Keith T.; Matras, Dorota npj Computational Materials, Vol. 7, Issue 1 https://doi.org/10.1038/s41524-021-00542-4	journal	May 2021
Automated classification of big X-ray diffraction data using deep learning models Salgado, Jerardo E.; Lerman, Samuel; Du, Zhaotong npj Computational Materials, Vol. 9, Issue 1 https://doi.org/10.1038/s41524-023-01164-8	journal	December 2023
Fraunhofer Diffraction Guenther, B. D. Modern Optics, p. 384-458 https://doi.org/10.1093/acprof:oso/9780198738770.003.0010	book	October 2015
Classification of crystal structure using a convolutional neural network Park, Woon Bae; Chung, Jiyong; Jung, Jaeyoung IUCrJ, Vol. 4, Issue 4 https://doi.org/10.1107/S205225251700714X	journal	June 2017
CNN based high performance computing for real time image processing on GPU Potluri, Sasanka; Fasih, Alireza; Vutukuru, Laxminand Kishore Proceedings of the Joint INDS'11 & ISTET'11 https://doi.org/10.1109/INDS.2011.6024781	conference	July 2011
Object Detection Networks on Convolutional Feature Maps Ren, Shaoqing; He, Kaiming; Girshick, Ross IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, Issue 7 https://doi.org/10.1109/TPAMI.2016.2601099	journal	July 2017
Temperature-Dependent Superplasticity and Strengthening in CoNiCrFeMn High Entropy Alloy Nanowires Using Atomistic Simulations Tripathi, Pawan Kumar; Chiu, Yu-Chen; Bhowmick, Somnath Nanomaterials, Vol. 11, Issue 8 https://doi.org/10.3390/nano11082111	journal	August 2021
Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks Wu, Yanzhao; Liu, Ling; Bae, Juhyun arXiv https://doi.org/10.48550/arXiv.1908.06477	preprint	January 2019
CNN Hyperparameter tuning applied to Iris Liveness Detection Kimura, Gabriela Y.; Lucio, Diego R.; Britto, Alceu S. arXiv https://doi.org/10.48550/arXiv.2003.00833	preprint	January 2020
Hyper-Parameter Optimization: A Review of Algorithms and Applications Yu, Tong; Zhu, Hong arXiv https://doi.org/10.48550/arXiv.2003.05689	preprint	January 2020
The Limit of the Batch Size You, Yang; Wang, Yuhui; Zhang, Huan arXiv https://doi.org/10.48550/arXiv.2006.08517	preprint	January 2020
TensorFlow No authors listed https://doi.org/10.5281/zenodo.8256979	software	August 2023

Similar Records

Precision measurement of the electron energy-loss function in tritium and deuterium gas for the KATRIN experiment

Journal Article · Sun Jul 04 20:00:00 EDT 2021 · European Physical Journal. C, Particles and Fields · OSTI ID:1805117

In-beam $$\gamma $$-ray spectroscopy of $$^{94}$$Ag

Journal Article · Tue Mar 14 20:00:00 EDT 2023 · European Physical Journal. A, Hadrons and Nuclei (Online) · OSTI ID:1961435

Hyperon III: $$K^{-}p - \pi \varSigma $$ coupled-channel dynamics in the $$\varLambda (1405)$$ mass region

Journal Article · Mon May 18 20:00:00 EDT 2020 · European Physical Journal. A · OSTI ID:1783419

Exploring 2D X-ray diffraction phase fraction analysis with convolutional neural networks: Insights from kinematic-diffraction simulations

Citation Formats

References (21)

Similar Records

Related Subjects