Fast extraction of three-dimensional nanofiber orientation from WAXD patterns using machine learning

被引:4
作者
Sun, Minghui [1 ,2 ]
Dong, Zheng [1 ,2 ]
Wu, Liyuan [1 ]
Yao, Haodong [1 ]
Niu, Wenchao [1 ]
Xu, Deting [1 ,2 ]
Chen, Ping [1 ,2 ]
Gupta, Himadri S. [3 ]
Zhang, Yi [1 ,2 ]
Dong, Yuhui [1 ,2 ]
Chen, Chunying [2 ,4 ]
Zhao, Lina [1 ,2 ]
机构
[1] Chinese Acad Sci, Inst High Energy Phys, Multidisciplinary Initiat Ctr, Beijing 100049, Peoples R China
[2] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
[3] Queen Mary Univ London, Sch Engn & Mat Sci, London E1 4NS, England
[4] Natl Ctr Nanosci & Technol China, Beijing 10084, Peoples R China
来源
IUCRJ | 2023年 / 10卷
基金
中国国家自然科学基金;
关键词
machine learning; synchrotron microfocus X-ray diffraction; biological materials; nanofiber networks; TENSOR; CLOSURE;
D O I
10.1107/S205225252300204X
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Structural disclosure of biological materials can help our understanding of design disciplines in nature and inspire research for artificial materials. Synchrotron microfocus X-ray diffraction is one of the main techniques for characterizing hierarchically structured biological materials, especially the 3D orientation distribution of their interpenetrating nanofiber networks. However, extraction of 3D fiber orientation from X-ray patterns is still carried out by iterative parametric fitting, with disadvantages of time consumption and demand for expertise and initial parameter estimates. When faced with high-throughput experiments, existing analysis methods cannot meet the real time analysis challenges. In this work, using the assumption that the X-ray illuminated volume is dominated by two groups of nanofibers in a gradient biological composite, a machine-learning based method is proposed for fast and automatic fiber orientation metrics prediction from synchrotron X-ray micro-focused diffraction data. The simulated data were corrupted in the training procedure to guarantee the prediction ability of the trained machine-learning algorithm in real-world experimental data predictions. Label transformation was used to resolve the jump discontinuity problem when predicting angle parameters. The proposed method shows promise for application in the automatic data-processing pipeline for fast analysis of the vast data generated from multiscale diffraction-based tomography characterization of textured biomaterials.
引用
收藏
页码:297 / 308
页数:12
相关论文
共 47 条
  • [1] Bioinspired approaches for toughening of fi bre reinforced polymer composites
    Amorim, L.
    Santos, A.
    Nunes, J. P.
    Viana, J. C.
    [J]. MATERIALS & DESIGN, 2021, 199
  • [2] Bao Hangbo, 2021, arXiv, DOI [10.48550/arXiv.2106.08254, DOI 10.48550/ARXIV.2106.08254]
  • [3] Analysis and Evaluation of Fiber Orientation Reconstruction Methods
    Breuer, Kevin
    Stommel, Markus
    Korte, Wolfgang
    [J]. JOURNAL OF COMPOSITES SCIENCE, 2019, 3 (03):
  • [4] Machine-Learning X-Ray Absorption Spectra to Quantitative Accuracy
    Carbone, Matthew R.
    Topsakal, Mehmet
    Lu, Deyu
    Yoo, Shinjae
    [J]. PHYSICAL REVIEW LETTERS, 2020, 124 (15)
  • [5] Invariant-based optimal fitting closure approximation for the numerical prediction of flow-induced fiber orientation
    Chung, DH
    Kwon, TH
    [J]. JOURNAL OF RHEOLOGY, 2002, 46 (01) : 169 - 194
  • [6] A deep convolutional neural network for real-time full profile analysis of big powder diffraction data
    Dong, Hongyang
    Butler, Keith T.
    Matras, Dorota
    Price, Stephen W. T.
    Odarchenko, Yaroslav
    Khatry, Rahul
    Thompson, Andrew
    Middelkoop, Vesna
    Jacques, Simon D. M.
    Beale, Andrew M.
    Vamvakeros, Antonis
    [J]. NPJ COMPUTATIONAL MATERIALS, 2021, 7 (01)
  • [7] Exascale image processing for next-generation beamlines in advanced light sources
    Dong, Yuhui
    Li, Chun
    Zhang, Yi
    Li, Pengcheng
    Qi, Fazhi
    [J]. NATURE REVIEWS PHYSICS, 2022, 4 (07) : 427 - 428
  • [8] Hammersley A.P., 1997, FIT2D INTRO OVERVIEW
  • [9] He K., 2021, arXiv
  • [10] He K. M., 2014, P 14 EUR C COMP VIS, P630