Ensemble-based, large-eddy reconstruction of wind turbine inflow in a near-stationary atmospheric boundary layer through generative artificial intelligence

TL;DR

This paper introduces a novel ensemble-based large-eddy simulation method using generative AI to accurately reconstruct wind inflow for wind turbines, improving validation of turbine dynamics in atmospheric boundary layers.

Contribution

It develops a large-eddy reconstruction technique that combines observations with atmospheric models via machine learning, enabling probabilistic inflow reconstructions for wind turbine analysis.

Findings

Reconstructed inflows show high correlation with ground-truth data.

Method produces visually similar inflows to measurements.

Reconstructed inflows accurately follow power spectra and second-by-second behavior.

Abstract

To validate the second-by-second dynamics of turbines in field experiments, it is necessary to accurately reconstruct the winds going into the turbine. Current time-resolved inflow reconstruction techniques estimate wind behavior in unobserved regions using relatively simple spectral-based models of the atmosphere. Here, we develop a technique for time-resolved inflow reconstruction that is rooted in a large-eddy simulation model of the atmosphere. Our "large-eddy reconstruction" technique blends observations and atmospheric model information through a diffusion model machine learning algorithm, allowing us to generate probabilistic ensembles of reconstructions for a single 10-min observational period. Our generated inflows can be used directly by aeroelastic codes or as inflow boundary conditions in a large-eddy simulation. We verify the second-by-second reconstruction capability of our technique in three synthetic field campaigns, finding positive Pearson correlation coefficient values (0.20>r>0.85) between ground-truth and reconstructed streamwise velocity, as well as smaller positive correlation coefficient values for unobserved fields (spanwise velocity, vertical velocity, and temperature). We validate our technique in three real-world case studies by driving large-eddy simulations with reconstructed inflows and comparing to independent inflow measurements. The reconstructions are visually similar to measurements, follow desired power spectra properties, and track second-by-second behavior (0.25 > r > 0.75).