Efficient Loads Surrogates for Waked Turbines in an Array

Abstract

Accurately and efficiently predicting wind turbine structural loading is a crucial step in wind farm design. Without considering structural loading, wind farm optimization could negatively impact turbine fatigue and ultimate loads, especially for waked and partially waked turbines, which could result in higher maintenance costs and reduced turbine lifetime. However, predicting turbine loads throughout an array is a costly step, as these quantities require time-accurate results across long time histories, which is often intractable for large array optimization. Therefore, surrogate models that link array spacing to load outputs are often used, but the surrogates are then unique to the inflow conditions and array configurations in the training library. This work develops surrogate models for many wind turbine load outputs based solely on rotor plane velocity measurements, with no required input about array configuration or freestream inflow parameters. Surrogate models were constructed for many turbine quantities of interest (QoI), considering mean, standard deviation, ultimate, and fatigue loads. In general, most QoI statistics were accurately captured, as measured by predicted vs. actual correlation coefficient, confirming the suitability of the approach. Temporal mean values of the QoI required only temporal mean measurements of the rotor plane inflow velocity. However, accurate prediction of temporal standard deviation, ultimate, and fatigue values of QoI also required temporal standard deviations of the rotor plane velocity field. Poor surrogate performance was observed when too many correlated inputs were used, such as multiple velocity components. If the fewest inflow parameters are used to construct the surrogates, the average correlation coefficient value for all output QoI statistics is 0.89. Surrogates for standard deviations and damage equivalent loads (DELs) of turbine QoIs generally had lower accuracy and tower-base and shaft load channels posed the most difficult to capture accurately. The results suggest that these surrogates could be easily paired with analytic wake models, which are frequently used for pre-construction wind farm array optimization, to account for turbine loading in addition to power production. By including the optimal inflow conditions, the surrogate accuracy can improve to an average correlation coefficient value for all output QoI statistics of 0.92. This work has established the ability to build accurate surrogates for mean, standard deviation, ultimate load, and DEL turbine QoI values based on the rotor plane inflow velocity, and identified which inflow conditions lead to greater surrogate accuracy.

A control-oriented load surrogate model based on sector-averaged inflow quantities: capturing damage for unwaked, waked, wake-steering and curtailed wind turbines

“…Overall, minimal scatter is observed, confirming the validity of this surrogate approach. The resulting root mean squared percentage errors (RMSPE, see [7]) are relatively low compared to other surrogate approaches [3,13,20]. The surrogate for blade root DEL performs the best, with a validation RMSPE value of only 0.48%.…”

“…While polynomial chaos expansion is a viable option, it requires an expensive training process and may not perform as well as artificial neural networks (ANNs). Extensive tests reported in [20] favored the latter option. Therefore, an ANN is selected as a surrogate fitting function, demonstrating efficient training and good predictive performance.…”

“…For each specific ambient condition, multiple turbulent realizations must be run to ensure convergence of the fatigue quantities. To address this computational challenge, prior research has proposed various surrogate modeling approaches [3,5,13,19,20]. However, these models are either site-specific (requiring repetition of training when the layout changes) or do not include the various complex effects of yaw misalignment and curtailment on self-induced loads and loads experienced by downstream turbines.…”

Efficient Mann turbulence generation for offshore wind farms with applications in fatigue load surrogate modelling

“…For example, when a turbine is partially waked, the fatigue loads of some components can be either increased or decreased depending on the wake centre position. For this reason, other literature has considered both lateral and vertical shear as input parameters [18], as well as several spatial moments across the rotor [19]. In this study, we present two wind field parameterisation methods.…”

Wind Farm Control Optimisation Under Load Constraints Via Surrogate Modelling

“…Bertelè considers both lateral and vertical shear as well as inflow direction in their wind field decomposition [15]. Shaler et al uses the first three spatial moments in various directions [16]. Dimitrov, instead, uses properties of the farm (turbine spacing, wind incident angle, number of affected turbines) as inputs to the surrogate model [17].…”