Reconstruction of dynamic wind turbine wake flow fields from virtual Lidar measurements via physics-informed neural networks

Accurate characterisation of wind turbine wakes is important for the optimal design and operation of wind farms. However, current techniques for full-scale wind measurements are still limited to point characterisation. To address the research challenge in obtaining field characterisation of real-world wind turbine wakes, this work investigates the reconstruction of the dynamic wake flow fields based on a virtual turbine-mounted Lidar and physics-informed neural networks. Specifically, the wake flow field is reconstructed by fusing the sparse measurements with the two-dimensional Navier-Stokes equations without imposing any models for the unsteady wake. Different from supervised machine learning approaches which need the measured values for the quantities of interest in the first place, the proposed method can achieve the prediction of the wind velocity at new locations where there is no measurement available. The reconstruction performance is evaluated via high-fidelity numerical experiments and it is shown that the dynamic wind turbine wake flow fields are predicted accurately, where the main wake features, including the downwind development and crosswind meandering of the wake, are both captured. This work thus paves the way for investigating full-scale in situ wake flow dynamics in real-world wind energy sites.