A heteroencoder architecture for prediction of failure locations in porous metals using variational inference

TL;DR

This paper introduces a heteroencoder neural network architecture with variational inference to predict failure locations in porous metals, effectively handling class imbalance and providing uncertainty estimates.

Contribution

It develops a novel encoder-decoder CNN with variational inference for failure prediction and uncertainty quantification in porous metals.

Findings

Effective regularization with data- and loss-based methods

Variational inference provides meaningful uncertainty estimates

Predicted variances successfully rank failure-prone locations

Abstract

In this work we employ an encoder-decoder convolutional neural network to predict the failure locations of porous metal tension specimens based only on their initial porosities. The process we model is complex, with a progression from initial void nucleation, to saturation, and ultimately failure. The objective of predicting failure locations presents an extreme case of class imbalance since most of the material in the specimens do not fail. In response to this challenge, we develop and demonstrate the effectiveness of data- and loss-based regularization methods. Since there is considerable sensitivity of the failure location to the particular configuration of voids, we also use variational inference to provide uncertainties for the neural network predictions. We connect the deterministic and Bayesian convolutional neural networks at a theoretical level to explain how variational inference regularizes the training and predictions. We demonstrate that the resulting predicted variances are effective in ranking the locations that are most likely to fail in any given specimen.