Database development and exploration of microstructure versus process relationships using variational autoencoders

TL;DR

This paper uses variational autoencoders to create a visual, two-dimensional representation of a large database linking manufacturing processes to microstructural features, aiding process design.

Contribution

It introduces a novel application of variational autoencoders for visualizing complex process-microstructure relationships in a large, open-source database.

Findings

Latent space effectively visualizes process-microstructure relationships.

Proximity analysis identifies multiple process solutions.

Database supports collaborative development of process design algorithms.

Abstract

The paper demonstrates the use of variational autoencoders for graphical representation of a large database containing process-microstructure relationships. Correlating microstructural features to processing is an essential first step to answer the difficult problem of process sequence design. In this paper, a large database of 346,200 orientation distribution functions resulting from a variety of process sequences is constructed, where each sequence comprises up to four stages of tension, compression and rolling along different directions in various permutations. This opensource database is constructed for collaborative development of process design algorithms. The paper demonstrates a novel application of the large database: graphical representation of texture-process relationships. A variational autoencoder is used to reduce the entire database to a two dimensional latent space where variations in processes and properties can be visualized. Using proximity analysis in this latent space, we can quickly unearth multiple process solutions to the problem of texture or property design.