Data from fluid flow measurements are typically sparse, noisy, and heterogeneous, often from mixed pressure and velocity measurements, resulting in incomplete datasets. In this paper, we develop a physics-constrained convolutional neural network, which is a deterministic tool, to reconstruct the full flow field from incomplete data. We explore three loss functions, both from machine learning literature and newly proposed: (i) the softly-constrained loss, which allows the prediction to take any value; (ii) the snapshot-enforced loss, which constrains the prediction at the sensor locations; and (iii) the mean-enforced loss, which constrains the mean of the prediction at the sensor locations. The proposed methods do not require the full flow field during training, making it suitable for reconstruction from incomplete data. We apply the method to reconstruct a laminar wake of a bluff body and a turbulent Kolmogorov flow. First, we assume that measurements are not noisy and reconstruct both the laminar wake and the Kolmogorov flow from sensors located at fewer than 1% of all grid points. The snapshot-enforced loss reduces the reconstruction error of the Kolmogorov flow by approximately 25% compared to the softly-constrained loss. Second, we assume that measurements are noisy and propose the mean-enforced loss to reconstruct the laminar wake and the Kolmogorov flow at three different signal-to-noise ratios. We find that, across the ratios tested, the loss functions with harder constraints are more robust to both the random initialization of the networks and the noise levels in the measurements. At high noise levels, the mean-enforced loss can recover the instantaneous snapshots accurately, making it the suitable choice when reconstructing flows from data corrupted with an unknown amount of noise. The proposed method opens opportunities for physical flow reconstruction from sparse, noisy data.
Reduced-order modelling of parametrized unsteady Navier-Stokes equations and application to flow around cylinders with periodic changing boundary conditions
Bayesian minimisation of energy consumption in turbulent pipe flow via unsteady driving
University of Bremen, Center of Applied Space Technology and Microgravity (ZARM)(不来梅大学,应用空间技术与微重力中心(ZARM));University of Bremen, MAPEX Center for Materials and Processes(不来梅大学,MAPEX材料与工艺中心)
Physics-informed neural networks for shock capturing in inviscid flows around an airfoil
School of Aeronautics, Northwestern Polytechnical University(西北工业大学航空学院);International Joint Institute of Artificial Intelligence on Fluid Mechanics, Northwestern Polytechnical University(西北工业大学流体力学人工智能国际联合研究院);National Key Laboratory of Aircraft Configuration Design(飞机构型设计全国重点实验室)
SnapPINN: Pressure and Energy Dissipation Reconstruction from a Sparse and Noisy Velocity Snapshot
Institute of Aerodynamics and Flow Technology, German Aerospace Center (DLR)(德国航空航天中心空气动力学与流动技术研究所);Max Planck Institute for Dynamics and Self-Organization(马克斯·普朗克动态与自组织研究所)