Variational Autoencoding the Lagrangian Trajectories of Particles in a Combustion System
This work addresses particle simulation in combustion systems, but it is incremental as it applies an existing deep learning method to a new domain-specific dataset.
The authors tackled the problem of simulating particle motion in a chaotic combustion system by developing a variational autoencoder (VAE) with convolutional layers, trained on experimental 3D trajectory data, and showed it could generate statistically representative trajectories.
We introduce a deep learning method to simulate the motion of particles trapped in a chaotic recirculating flame. The Lagrangian trajectories of particles, captured using a high-speed camera and subsequently reconstructed in 3-dimensional space, were used to train a variational autoencoder (VAE) which comprises multiple layers of convolutional neural networks. We show that the trajectories, which are statistically representative of those determined in experiments, can be generated using the VAE network. The performance of our model is evaluated with respect to the accuracy and generalization of the outputs.