Machine learning clustering technique applied to powder X-ray diffraction patterns to distinguish alloy substitutions

Abstract

We applied the clustering technique using DTW (dynamic time wrapping) analysis to XRD (X-ray diffraction) spectrum patterns in order to identify the microscopic structures of substituents introduced in the main phase of magnetic alloys. The clustering is found to perform well to identify the concentrations of the substituents with successful rates (around 90%). The sufficient performance is attributed to the nature of DTW processing to filter out irrelevant informations such as the peak intensities (due to the incontrollability of diffraction conditions in polycrystalline samples) and the uniform shift of peak positions (due to the thermal expansions of lattices).

References in corpus (7)

• Unsupervised Phase Mapping of X-ray Diffraction Data by Nonnegative Matrix Factorization Integrated with Custom Clustering
• Calculation of magnetic anisotropy energy in SmCo5
• First-principles study on stability and magnetism of NdFe11M and NdFe11MN for M=Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn
• Nitrogen as the best interstitial dopant among $X$=B, C, N, O and F for strong permanent magnet NdFe${}_{11}$Ti$X$: First-principles study
• Stabilization mechanism of tetragonal structure in hydrothermal synthesized BaTiO${}_3$ nanocrystal
• A computational scheme to evaluate Hamaker constants of molecules with practical size and anisotropy
• New Insight into the Ground State of FePc: A Diffusion Monte Carlo Study

Cited by in corpus (3)

• Application of canonical augmentation to the atomic substitution problem
• Feature space of XRD patterns constructed by auto-encorder
• Stochastic estimations of a total number of classes for the clusterings with too enormous samples to be accommodate into a clustering engine