Abstract
X-ray diffraction based microscopy techniques such as high-energy diffraction microscopy (HEDM) rely on knowledge of the position of diffraction peaks with high precision. These positions are typically computed by fitting the observed intensities in detector data to a theoretical peak shape such as pseudo-Voigt. As experiments become more complex and detector technologies evolve, the computational cost of such peak-shape fitting becomes the biggest hurdle to the rapid analysis required for real-time feedback in experiments. To this end, we propose BraggNN, a deep-learning based method that can determine peak positions much more rapidly than conventional pseudo-Voigt peak fitting. When applied to a test dataset, peak center-of-mass positions obtained from BraggNN deviate less than 0.29 and 0.57 pixels for 75 and 95% of the peaks, respectively, from positions obtained using conventional pseudo-Voigt fitting (Euclidean distance). When applied to a real experimental dataset and using grain positions from near-field HEDM reconstruction as ground-truth, grain positions using BraggNN result in 15% smaller errors compared with those calculated using pseudo-Voigt. Recent advances in deep-learning method implementations and special-purpose model inference accelerators allow BraggNN to deliver enormous performance improvements relative to the conventional method, running, for example, more than 200 times faster on a consumer-class GPU card with out-of-the-box software.
Highlights
Advanced materials affect every aspect of our daily lives, including the generation, transmission and use of energy
We describe the BraggNN framework as applied to FF-high-energy diffraction microscopy (HEDM), it is useful for other diffraction techniques dealing with single or polycrystal diffraction
Once the model was trained, we evaluated its performance from two perspectives: (1) we measured the distance between each BraggNN-estimated center and the corresponding center obtained via the conventional pseudoVoigt profile; (2) we applied BraggNN to an experiment of a different sample, reconstructed grains using peak information by BraggNN and compared the reconstructed grain size and position with those reconstructed using conventional methods (Sharma et al, 2012a)
Summary
Advanced materials affect every aspect of our daily lives, including the generation, transmission and use of energy. HEDM techniques have enabled breakthroughs in understanding of various processes, through carefully designed experiments that are tractable for analysis by researchers (Naragani et al, 2017; Bernier et al, 2020; Wang et al, 2020) These methods use diffraction and tomographic imaging of up to centimetre-sized objects with resolutions down to the micrometre level. Depending on sample properties and the extent of the mechanical, thermal, electromagnetic or chemical stimuli applied to the sample, processing time can range from 10 min to a few weeks, even when using an HPC cluster with thousands of CPU cores These long data analysis times are more than just an incon-. The data and source code that support the findings of this study are openly available at https://github.com/lzhengchun/BraggNN
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
