A surrogate model approach for associating wind farm load variations with turbine failures

Schröder, Laura; Dimitrov, Nikolay Krasimirov; Verelst, David Robert

doi:10.5194/wes-2020-79

Cited by 3 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural network models have been used to build efficient surrogate models based on measured operational data or high-fidelity simulation data. These surrogate models are capable of estimating wake-induced effects on wind turbine power [1,2,3], loads [4,5], damage and failures [6]. These surrogate models, among other applications, enable efficient optimization of wind farm layout and control strategy [5,7].…”

Section: Introductionmentioning

confidence: 99%

Modelling of turbine power and local wind conditions in wind farm using an autoencoder neural network

Dou

Dimitrov

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Neural network models have been widely applied in wind energy to enable data-driven modelling of turbine’s power, loads, damage, and other quantities in wind farm. They have shown advantages in the flexibility, robustness, and efficiency, as well as the ease of application. An important task in data-driven modelling of wind farm is the characterization of wake-induced effects within wind farm. Because of the large number of wind turbines in wind farm and the broad range of conditions required for power output assessment, it has become relevant to use computationally efficient surrogate models that are based on parameterizations of the wind farm layout. Previous studies on surrogate models of wake-induced effects have focused on parameterizations based on manually extracted features from the wind farm geometry. The present study applies an autoencoder neural network to automatically learn the features representing the wind farm layout. Specifically, two autoencoders are studied and compared. The autoencoder provides dimension reduction and feature learning that allow representing the entire wind farm layout in just a few latent variables, thus allowing efficient and accurate surrogate models of wake-induced effects. The outputs of the autoencoder, together with any ambient wind condition variables, serve as inputs to a standard feedforward neural network that predicts the wake-induced effects for any turbine in the wind farm. Our results show that the autoencoder provides an automatic and effective way to parameterize the wind farm geometry, and facilitates the building of efficient surrogate models that are capable of accurate modeling of wake-induced effects in a wind farm with arbitrary layout.

show abstract

Section: Introductionmentioning

confidence: 99%

Modelling of turbine power and local wind conditions in wind farm using an autoencoder neural network

Dou

Dimitrov

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…Ashuri et al (2016), Murcia et al (2018), and Schröder et al (2020a) used surrogate models for uncertainty propagation through the wind turbine models. More recently, the surrogate models have been used for the wind turbines' reliability assessments (Slot et al, 2020;Schröder et al, 2020b). Also, Wang et al (2020) and Barlas et al (2021) showed the application of the surrogate model in wind turbine optimization.…”

Section: Introductionmentioning

confidence: 99%

Surrogate models for the blade element momentum aerodynamic model using non-intrusive polynomial chaos expansions

Haghi

Crawford²

2022

Wind Energ. Sci.

View full text Add to dashboard Cite

Abstract. In typical industrial practice based on IEC standards, wind turbine simulations are computed in the time domain for each mean wind speed bin using a few unsteady wind seeds. Software such as FAST, BLADED, or HAWC2 can be used to capture the unsteadiness and uncertainties of the wind in the simulations. The statistics of these aeroelastic simulation outputs are extracted and used to calculate fatigue and extreme loads on the wind turbine components. The minimum requirement of having six seeds does not guarantee an accurate estimation of the overall statistics. One solution might be running more seeds; however, this will increase the computation cost. Moreover, to move beyond blade element momentum (BEM)-based tools toward vortex/potential flow formulations, a reduction in the computational cost associated with the unsteady flow and uncertainty handling is required. This study illustrates the unsteady wind aerodynamic statistics' stationary character based on the standard turbulence models. This character is shown based on the output of National Renewable Energy Lab (NREL) 5MW reference machine BEM simulations. Afterwards, we propose a non-intrusive polynomial chaos expansion (PCE) to build a surrogate model of the loads' statistics, the rotor thrust, and torque, at each time step, to estimate the extreme statistics more accurately and efficiently.

show abstract

“…Initiating from a physics-based approach, research in [12] and in similar works [41,37] exploits a surrogate approach, relying on Polynomial Chaos Expansions (PCE) and Artificial Neural networks (ANN), trained on pre-simulated load scenarios, to predict the fatigue load variation on WTs for a wind farm with arbitrary layout under wake effects. ANNs are shown to outperform PCE in terms of prediction accuracy and computational speed [40], albeit being prone to overfitting, while further require significantly more data for achieving acceptable performance. Both methods allow for obtaining analytical derivatives, which is a useful trait in optimization and sensitivity analysis.…”

Section: Introductionmentioning

confidence: 99%

Virtual fatigue diagnostics of wake-affected wind turbine via Gaussian Process Regression

Avendaño-Valencia¹,

Abdallah²,

Chatzi³

2020

Preprint

View full text Add to dashboard Cite

We propose a data-driven model to predict the short-term fatigue Damage Equivalent Loads (DEL) on a wake-affected wind turbine based on wind field inflow sensors and/or loads sensors deployed on an adjacent up-wind wind turbine. Gaussian Process Regression (GPR) with Bayesian hyperparameters calibration is proposed to obtain a surrogate from input random variables to output DELs in the blades and towers of the up-wind and wake-affected wind turbines. A sensitivity analysis based on the hyperparameters of the GPR and Kullback-Leibler divergence is conducted to assess the effect of different input on the obtained DELs. We provide qualitative recommendations for a minimal set of necessary and sufficient input random variables to minimize the error in the DEL predictions on the wake-affected wind turbine. Extensive simulations are performed comprising different random variables, including wind speed, turbulence intensity, shear exponent and inflow horizontal skewness. Furthermore, we include random variables related to the blades lift and drag coefficients with direct impact on the rotor aerodynamic induction, which governs the evolution and transport of the meandering wake. In addition, different spacing between the wind turbines and Wöhler exponents for calculation of DELs are considered. The maximum prediction normalized mean squared error, obtained in the tower base DELs in the fore-aft direction of the wake affected wind turbine, is less than 4%. In the case of the blade root DELs, the overall prediction error is less than 1%. The proposed scheme promotes utilization of sparse structural monitoring (loads) measurements for improving diagnostics on wake-affected turbines.

show abstract

A surrogate model approach for associating wind farm load variations with turbine failures

Cited by 3 publications

References 8 publications

Modelling of turbine power and local wind conditions in wind farm using an autoencoder neural network

Modelling of turbine power and local wind conditions in wind farm using an autoencoder neural network

Surrogate models for the blade element momentum aerodynamic model using non-intrusive polynomial chaos expansions

Virtual fatigue diagnostics of wake-affected wind turbine via Gaussian Process Regression

Contact Info

Product

Resources

About