Flow reconstruction over a SUBOFF model based on LBM-generated data and physics-informed neural networks

Flow reconstruction from sparse velocity measurements (either from simulation or experiment) is essential in the study of SUBOFF models for the purpose of developing advanced submarines. To address the challenge of limited data especially in experimental technologies such as particle image velocimetry, we present a deep learning model based on physics -informed neural networks for flow reconstruction task. We first generate a dataset of the flow over a SUBOFF model by using lattice Boltzmann method (LBM). The neural networks are trained by feeding with the velocities down -sampled from the high-fidelity LBM dataset, and are expected to perform superresolution of the velocity and infer the pressure field simultaneously. The results show that the reconstructed flow fields (including the pressure) are comparable to the full -resolution references from LBM, indicating that the method is promising in reconstruction task for complex flow motion, which can help with the simulation and experiment in the study of SUBOFF.