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

TL;DR

This paper demonstrates that clustering using dynamic time warping effectively analyzes powder X-ray diffraction patterns to identify alloy substitutions and their concentrations with high accuracy, despite variability in peak intensities and positions.

Contribution

The study introduces a novel application of DTW-based clustering to XRD data for distinguishing alloy substitutions and quantifying their concentrations.

Findings

Achieved around 90% success rate in identifying substituent concentrations.

DTW filtering effectively handles peak intensity variability and peak position shifts.

Clustering accurately differentiates microscopic structures in magnetic alloys.

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).