Machine learning approach to force reconstruction in photoelastic materials

TL;DR

This paper introduces a convolutional neural network-based method for efficiently reconstructing forces in photoelastic granular materials, overcoming computational challenges of traditional approaches by leveraging synthetic training data and fine-tuning on limited experimental data.

Contribution

The novel approach combines synthetic data pretraining with fine-tuning on experimental data to accurately reconstruct forces from photoelastic images using neural networks.

Findings

Pretraining on synthetic data improves force reconstruction accuracy.

Fine-tuning on small experimental datasets is effective.

The method can handle variations in particle size affecting photoelastic patterns.

Abstract

Photoelastic techniques have a long tradition in both qualitative and quantitative analysis of the stresses in granular materials. Over the last two decades, computational methods for reconstructing forces between particles from their photoelastic response have been developed by many different experimental teams. Unfortunately, all of these methods are computationally expensive. This limits their use for processing extensive data sets that capture the time evolution of granular ensembles consisting of a large number of particles. In this paper, we present a novel approach to this problem which leverages the power of convolutional neural networks to recognize complex spatial patterns. The main drawback of using neural networks is that training them usually requires a large labeled data set which is hard to obtain experimentally. We show that this problem can be successfully circumvented by pretraining the networks on a large synthetic data set and then fine-tuning them on much smaller experimental data sets. Due to our current lack of experimental data, we demonstrate the potential of our method by changing the size of the considered particles which alters the exhibited photoelastic patterns more than typical experimental errors.