X-ray diffraction crystallography allows non-destructive examination of crystal structures. Furthermore, it has low requirements regarding the surface preparation, especially compared to electron backscatter diffraction. However, up to now, X-ray diffraction is highly time-consuming in standard laboratory conditions since we have to record intensities on multiple lattice planes by rotating and tilting the sample. In this article, we propose a method based on deep learning that allows faster experimentation due to accurate reconstructions of pole figure regions, which we did not probe experimentally. To speed up the development of our proposed method and further machine learning algorithms, we introduce a GPU-based simulation for data generation. Furthermore, we present a pole widths standardization technique using a custom deep learning architecture that makes algorithms more robust against influences from the experiment setup and material.

X-ray diffraction crystallography allows non-destructive examination of crystal structures. Furthermore, it has low requirements regarding surface preparation, especially compared to electron backscatter diffraction. However, up to now, X-ray diffraction has been highly time-consuming in standard laboratory conditions since intensities on multiple lattice planes have to be recorded by rotating and tilting. Furthermore, examining oligocrystalline materials is challenging due to the limited number of diffraction spots. Moreover, commonly used evaluation methods for crystallographic orientation analysis need multiple lattice planes for a reliable pole figure reconstruction. In this article, we propose a deep-learning-based method for oligocrystalline specimens, i.e., specimens with up to three grains of arbitrary crystal orientations. Our approach allows faster experimentation due to accurate reconstructions of pole figure regions, which we did not probe experimentally. In contrast to other methods, the pole figure is reconstructed based on only a single incomplete pole figure. To speed up the development of our proposed method and for usage in other machine learning algorithms, we introduce a GPU-based simulation for data generation. Furthermore, we present a pole widths standardization technique using a custom deep learning architecture that makes algorithms more robust against influences from the experiment setup and material.