Machine learning approach to force reconstruction in photoelastic materials
This addresses a bottleneck in processing large-scale granular material data for experimental researchers, though it is incremental as it builds on existing computational methods.
The paper tackles the computationally expensive problem of reconstructing forces between particles in photoelastic materials by introducing a convolutional neural network approach that uses synthetic data for pretraining and fine-tuning on smaller experimental sets, demonstrating its potential through particle size variations.
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.