Interpretable MA-island clusters and fingerprints relating bainite microstructures to composition and processing temperature

TL;DR

This paper develops interpretable deep learning methods to classify bainite microstructures based on MA-island features, creating fingerprints that relate microstructure characteristics to composition and processing temperature.

Contribution

It introduces a novel deep learning approach that produces interpretable clusters of MA islands, enabling microstructure fingerprinting linked to processing conditions.

Findings

Deep learning yields five distinct MA-island clusters.

Clustering based on geometric features alone is ineffective.

Microstructure fingerprints effectively relate to composition and temperature.

Abstract

Realising the affect of composition and processing condition on bainite microstructures is often challenging, owing to the intricate distribution of the constituent phases. In this work, scanning electron micrographs of non-isothermally transformed bainite, with martensite-austenite (MA) islands, are analysed to relate the microstructures to the composition and quench-stop temperature. The inadequacy of the MA-islands' geometric features, namely aspect ratio, polygon area and compactness, in establishing this relation is made evident from Kullback-Leibler (KL) divergence at the outset. Clustering the bainite microstructures, following a combination of feature extraction and dimensionality reduction, further fails to realise the affect of composition and processing temperature. Deep-learning analysis of the individual MA islands, in contrast to the bainite microstructures, yields interpretable clusters with characteristically distinct size and morphology. These five clusters, referred to as fine- and coarse-dendrite, fine- and coarse-polygon and elongated, are exceptionally discernible and can be adopted to describe any MA island. Characterising the bainite microstructures, based on the distribution of the interpretable MA-island clusters, generates \textit{fingerprints} that sufficiently relates the composition and processing conditions with the microstructures.