The Computing Division Technical Meetings are a platform for

  • presenting Pinboard papers under review for journal or conference publication,
  • inviting speakers who are current or prospective UKAEA collaborators at external organisations,
  • presenting work done in PhD projects funded by or co-supervised by UKAEA,
  • presenting work done during summer placements or other secondments to UKAEA.

 

If you would like to invite a speaker on a topic that would be of interest to one or more Units within the Computing Division, but is not currently collaborating on a UKAEA project, please consider nominating them for a Computing Division Cross-Disciplinary Seminar.

These meetings are normally recorded. Recordings of past meetings can be found here:

CD Technical Meetings Archive on UKAEA Sharepoint

CD Technical Meeting (ML4): 3D variational autoencoder for fingerprinting microstructure volume elements

→ Europe/London
Mike White (Advanced Engineering Simulation)
Description
Machine Learning, Uncertainty Quantification and Data Science 

 

Abstract

Microstructure quantification is an important step towards establishing structure-property relationships in materials. Machine learning-based image processing methods have been shown to outperform conventional image processing techniques and are increasingly applied to microstructure quantification tasks. In this work, we present a 3D variational autoencoder (VAE) for encoding microstructure volume elements (VEs) comprising voxelated crystallographic orientation data. Crystal symmetries in the orientation space are accounted for by mapping to the crystallographic fundamental zone as a preprocessing step, which allows for a continuous loss function to be used and improves the training convergence rate. The VAE is then used to encode a training set of VEs with an equiaxed polycrystalline microstructure with random texture. Accurate reconstructions are achieved with a relative average misorientation error of 9x10-3 on the test dataset, for a continuous latent space with dimension 256. We show that the model generalises well to microstructures with textures, grain sizes and aspect ratios outside the training distribution.

 

The main aim of this project is to present the 3D VAE as an application-agnostic method for parameterising microstructure for input into downstream tasks where microstructure dependence is required. As a proof of concept, a simple surrogate model for uniaxial crystal plasticity (CP) simulations, with a fixed load path and microstructural dependence is presented. Microstructural fingerprints, obtained by encoding VEs with the trained VAE encoder, parameterise the VEs in a low-dimensional latent space and are stored alongside the volume-averaged stress response, at each strain increment. This is then used to train a fully connected neural network mapping the input fingerprint to the resulting stress response, which acts as a surrogate model for the CP simulation. The fingerprint-based surrogate model is shown to accurately predict the microstructural dependence in the CP stress response, with a mean relative error of 2.75 MPa on unseen test data. This approach offers a significant speed-up on the order of 108 for a stress-strain curve prediction, compared to running a CP simulation.

 

Paper