Classification of EBSD Kikuchi patterns for stainless steel by unsupervised learning methods to investigate grain boundaries

EBSD indexing based on Kikuchi diffraction patterns, which indicate the types and orientation of the crystal lattice, is generally effective for characterizing crystals. Most regions in a sample can be indexed owing to the simulation of diffraction patterns of possible crystal types, orientations, and angles. However, indexing some of the complex regions related to the grain boundaries, dislocations, and strain areas is difficult.
By analyzing all the Kikuchi patterns, subtle information from mixed crystal conditions can be extracted. In this study, all Kikuchi patterns at all pixels in a measurement area of stainless steel were analyzed simultaneously using unsupervised learning methods, such as principal component analysis and multivariate curve resolution, and the pixels of the measurement area were classified based on the Kikuchi patterns to investigate the grain boundaries and dislocations in detail.