TopTemp: Parsing Precipitate Structure from Temper Topology
This work addresses the labor-intensive challenge of evaluating new manufacturing processes for materials science, though it appears incremental as a first step towards broader understanding.
The authors tackled the problem of linking manufacturing process parameters to material microstructures by introducing TopTemp, a topological representation for temper-dependent microstructures, which outperformed conventional deep learning baselines in temper classification tasks.
Technological advances are in part enabled by the development of novel manufacturing processes that give rise to new materials or material property improvements. Development and evaluation of new manufacturing methodologies is labor-, time-, and resource-intensive expensive due to complex, poorly defined relationships between advanced manufacturing process parameters and the resulting microstructures. In this work, we present a topological representation of temper (heat-treatment) dependent material micro-structure, as captured by scanning electron microscopy, called TopTemp. We show that this topological representation is able to support temper classification of microstructures in a data limited setting, generalizes well to previously unseen samples, is robust to image perturbations, and captures domain interpretable features. The presented work outperforms conventional deep learning baselines and is a first step towards improving understanding of process parameters and resulting material properties.