An official website of the United States government
Light detection and ranging (LiDAR) measurements of isolated wakes generated by wind turbines installed at an onshore wind farm are leveraged to characterize the variability of the wake mean velocity and turbulence intensity during typical operations, which encompass a breadth of atmospheric stability regimes and rotor thrust coefficients. The LiDAR measurements are clustered through the k-means algorithm, which enables identifying the most representative realizations of wind turbine wakes while avoiding the imposition of thresholds for the various wind and turbine parameters. Considering the large number of LiDAR samples collected to probe the wake velocity field, the dimensionality of the experimental dataset is reduced by projecting the LiDAR data on an intelligently truncated basis obtained with the proper orthogonal decomposition (POD). The coefficients of only five physics-informed POD modes are then injected in the k-means algorithm for clustering the LiDAR dataset. The analysis of the clustered LiDAR data and the associated supervisory control and data acquisition and meteorological data enables the study of the variability of the wake velocity deficit, wake extent, and wake-added turbulence intensity for different thrust coefficients of the turbine rotor and regimes of atmospheric stability. Furthermore, the cluster analysis of the LiDAR data allows for the identification of systematic off-design operations with a certain yaw misalignment of the turbine rotor with the mean wind direction.
more »
« less
A Call for Enhanced Data-Driven Insights into Wind Energy Flow Physics
With the increased availability of experimental measurements aiming at probing wind resources and wind turbine operations, machine learning (ML) models are poised to advance our understanding of the physics underpinning the interaction between the atmospheric boundary layer and wind turbine arrays, the generated wakes and their interactions, and wind energy harvesting. However, the majority of the existing ML models for predicting wind turbine wakes merely recreate CFD-simulated data with analogous accuracy but reduced computational costs, thus providing surrogate models rather than enhanced data-enabled physics insights. Although ML-based surrogate models are useful to overcome current limitations associated with the high computational costs of CFD models, using ML to unveil processes from experimental data or enhance modeling capabilities is deemed a potential research direction to pursue. In this letter, we discuss recent achievements in the realm of ML modeling of wind turbine wakes and operations, along with new promising research strategies.
more »
« less
- Award ID(s):
- 2046160
- PAR ID:
- 10483310
- Publisher / Repository:
- Elsevier
- Date Published:
- Journal Name:
- Theoretical and Applied Mechanics Letters
- ISSN:
- 2095-0349
- Page Range / eLocation ID:
- 100488
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Abstract. Engineering wake models provide the invaluable advantage to predict wind turbine wakes, power capture, and, in turn, annual energy production for an entire wind farm with very low computational costs compared to higher-fidelity numerical tools. However, wake and power predictions obtained with engineering wake models can be insufficiently accurate for wind farm optimization problems due to the ad hoc tuning of the model parameters, which are typically strongly dependent on the characteristics of the site and power plant under investigation. In this paper, lidar measurements collected for individual turbine wakes evolving over a flat terrain are leveraged to perform optimal tuning of the parameters of four widely used engineering wake models. The average wake velocity fields, used as a reference for the optimization problem, are obtained through a cluster analysis of lidar measurements performed under a broad range of turbine operative conditions, namely rotor thrust coefficients, and incoming wind characteristics, namely turbulence intensity at hub height. The sensitivity analysis of the optimally tuned model parameters and the respective physical interpretation are presented. The performance of the optimally tuned engineering wake models is discussed, while the results suggest that the optimally tuned Bastankhah and Ainslie wake models provide very good predictions of wind turbine wakes. Specifically, the Bastankhah wake model should be tuned only for the far-wake region, namely where the wake velocity field can be well approximated with a Gaussian profile in the radial direction. In contrast, the Ainslie model provides the advantage of using as input an arbitrary near-wake velocity profile, which can be obtained through other wake models, higher-fidelity tools, or experimental data. The good prediction capabilities of the Ainslie model indicate that the mixing-length model is a simple yet efficient turbulence closure to capture effects of incoming wind and wake-generated turbulence on the wake downstream evolution and predictions of turbine power yield.more » « less
-
null (Ed.)Wind turbine wakes are responsible for power losses and added fatigue loads of wind turbines. Providing capabilities to predict accurately wind-turbine wakes for different atmospheric conditions and turbine settings with low computational requirements is crucial for the optimization of wind-farm layout, and for improving wind-turbine controls aiming to increase annual energy production (AEP) and reduce the levelized cost of energy (LCOE) for wind power plants. In this work, wake measurements collected with a scanning Doppler wind Li- DAR for broad ranges of the atmospheric static stability regime and incoming wind speed are processed through K-means clustering. For computational feasibility, the cluster analysis is performed on a low-dimensional embedding of the collected data, which is obtained through proper orthogonal decomposition (POD). After data compression, we perform K-means of the POD modes to identify cluster centers and corresponding members from the LiDAR data. The different cluster centers allow us to visualize wake variability over ranges of atmospheric, wind, and turbine parameters. The results show that accurate mapping of the wake variability can be achieved with K-means clustering, which represents an initial step to develop data-driven wake models for accurate and low-computational-cost simulations of wind farms.more » « less
-
Next-generation models of wind farm flows are increasingly needed to assist the design, operation, and performance diagnostic of modern wind power plants. Accuracy in the descriptions of the wind farm aerodynamics, including the effects of atmospheric stability, coalescing wakes, and the pressure field induced by the turbine rotors are necessary attributes for such tools as well as low computational costs. The Pseudo-2D RANS model is formulated to provide an efficient solution of the Navier–Stokes equations governing wind-farm flows installed in flat terrain and offshore. The turbulence closure and actuator disk model are calibrated based on wind light detection and ranging measurements of wind turbine wakes collected under different operative and atmospheric conditions. A shallow-water formulation is implemented to achieve a converged solution for the velocity and pressure fields across a farm with computational costs comparable to those of mid-fidelity engineering wake models. The theoretical foundations and numerical scheme of the Pseudo-2D RANS model are provided, together with a detailed description of the verification and validation processes. The model is assessed against a large dataset of power production for an onshore wind farm located in North Texas showing a normalized mean absolute error of 5.6% on the 10-min-averaged active power and 3% on the clustered wind farm efficiency, which represent 8% and 24%, respectively, improvements with respect to the best-performing engineering wake model tested in this work.more » « less
-
For energy-assisted compression ignition (EACI) engine propulsion at high-altitude operating conditions using sustainable jet fuels with varying cetane numbers, it is essential to develop an efficient engine control system for robust and optimal operation. Control systems are typically trained using experimental data, which can be costly and time consuming to generate due to setup time of experiments, unforeseen delays/issues with manufacturing, mishaps/engine failures and the consequent repairs (which can take weeks), and errors in measurements. Computational fluid dynamics (CFD) simulations can overcome such burdens by complementing experiments with simulated data for control system training. Such simulations, however, can be computationally expensive. Existing data-driven machine learning (ML) models have shown promise for emulating the expensive CFD simulator, but encounter key limitations here due to the expensive nature of the training data and the range of differing combustion behaviors (e.g. misfires and partial/delayed ignition) observed at such broad operating conditions. We thus develop a novel physics-integrated emulator, called the Misfire-Integrated GP (MInt-GP), which integrates important auxiliary information on engine misfires within a Gaussian process surrogate model. With limited CFD training data, we show the MInt-GP model can yield reliable predictions of in-cylinder pressure evolution profiles and subsequent heat release profiles and engine CA50 predictions at a broad range of input conditions. We further demonstrate much better prediction capabilities of the MInt-GP at different combustion behaviors compared to existing data-driven ML models such as kriging and neural networks, while also observing up to 80 times computational speed-up over CFD, thus establishing its effectiveness as a tool to assist CFD for fast data generation in control system training.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1016/j.taml.2023.100488
