Surrogate Models for Wind Turbine Electrical Power and Fatigue Loads in Wind Farm

Gasparis, Georgios; Lio, Wai Hou; Meng, Fanzhong

doi:10.3390/en13236360

Cited by 13 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The resulted power from this turbine depends of its working conditions, where the elevation, directing and the local wind properties, strongly affect on the power generation [6,7];…”

Section: Wind Turbines Specificationsmentioning

confidence: 99%

Analysis of the Generated Output Energy by Different Types of Wind Turbines

Hassan

Mahmoud

Almohammed

2020

J. Hum. Earth Future

View full text Add to dashboard Cite

This study intends to analyse the generated individual output energy by different types of wind turbines. Focusing on estimating the total energy output generated by a wind farm utilizing three distinct wind turbines, Siemens Gamesa SG 3.4-132, Vesatas HTq V126, and Lagerwey L100, with rated powers of 3.465MW, 3.45 MW, and 2.5 MW respectively. Sixty turbines of each type will be installed at the elevations of 97 m, 87 m, and 99 m consecutively. For the purpose of the study, the Sorochi Gory region was chosen as an eligible location to the farm, due to its physiographic location and desirable forestry. A virtual experiment will be conducted, by testing different possible wind turbines configurations, and calculating their gross energy output, considering the output wind speed is in the ideal case, while the output energy includes the wake effect, using (WindFarmer analyst software). Thereupon, the results will be presented, including the optimal wind turbine configuration for the wind farm, in terms of efficiency, stability, and economy wise. Doi: 10.28991/HEF-2020-01-04-03 Full Text: PDF

show abstract

“…The resulted power from this turbine depends of its working conditions, where the elevation, directing and the local wind properties, strongly affect on the power generation [6,7];…”

Section: Wind Turbines Specificationsmentioning

confidence: 99%

Analysis of the Generated Output Energy by Different Types of Wind Turbines

Hassan

Mahmoud

Almohammed

2020

J. Hum. Earth Future

View full text Add to dashboard Cite

show abstract

“…Fatigue loads on the tower in the presence of wind and wave loads have been previously modeled using standard GPR by Texeira et al [6]; however, they omit heteroscedasticity. GPR has been compared to other data-driven methods like linear regression, and artificial neural networks by Gasparis et al [7] for modeling power and fatigue loads, showing a superior performance by the GPR. Similarly, Dimitrov et al [8] evaluate importance sampling, nearest-neighbor interpolation, polynomial chaos expansion (PCE), GPR, and quadratic response surface (QRS), to conclude a better performance again by the GPR despite a computational penalty.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic surrogate modeling of offshore wind-turbine loads with chained Gaussian processes

Singh

Dwight

Laugesen

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Heteroscedastic Gaussian process regression, based on the concept of chained Gaussian processes, is used to build surrogates to predict site-specific loads on an offshore wind turbine. Stochasticity in the inflow turbulence and irregular waves results in load responses that are best represented as random variables rather than deterministic values. Moreover, the effect of these stochastic sources on the loads depends strongly on the mean environmental conditions - for instance, at low mean wind speeds, inflow turbulence produces much less variability in loads than at high wind speeds. Statistically, this is known as heteroscedasticity. Deterministic and most stochastic surrogates do not account for the heteroscedastic noise, giving an incomplete and potentially misleading picture of the structural response. In this paper, we draw on the recent advancements in statistical inference to train a heteroscedastic surrogate model on a noisy database to predict the conditional pdf of the response. The model is informed via 10-minute load statistics of the IEA-10MW-RWT subject to both aero- and hydrodynamic loads, simulated with OpenFAST. Its performance is assessed against the standard Gaussian process regression. The predicted mean is similar in both models, but the heteroscedastic surrogate approximates the large-scale variance of the responses significantly better.

show abstract

“…The limitation of this paper is the accuracy of influence factors, which may differ in complex layouts. Georgios [14] applied the regression method to map the relationship between the load and de-rating control strategy. This method can estimate the short-term fatigue load.…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning Method for Modeling Wind Farm Fatigue Load

2022

View full text Add to dashboard Cite

Wake steering control can significantly improve the overall power production of wind farms. However, it also increases fatigue damage on downstream wind turbines. Therefore, optimizing fatigue loads in wake steering control has become a hot research topic. Accurately predicting farm fatigue loads has always been challenging. The current interpolation method for farm-level fatigue loads estimation is also known as the look-up table (LUT) method. However, the LUT method is less accurate because it is challenging to map the highly nonlinear characteristics of fatigue load. This paper proposes a machine-learning algorithm based on the Gaussian process (GP) to predict the farmlevel fatigue load under yaw misalignment. Firstly, a series of simulations with yaw misalignment were designed to obtain the original load data, which considered the wake interaction between turbines. Secondly, the rainflow counting and Palmgren miner rules were introduced to transfer the original load to damage equivalent load. Finally, the GP model trained by inputs and outputs predicts the fatigue load. GP has more accurate predictions because it is suitable for mapping the nonlinear between fatigue load and yaw misalignment. The case study shows that compared to LUT, the accuracy of GP improves by 17% (RMSE) and 0.6% (MAE) at the blade root edgewise moment and 51.87% (RMSE) and 1.78% (MAE) at the blade root flapwise moment.

show abstract

Surrogate Models for Wind Turbine Electrical Power and Fatigue Loads in Wind Farm

Cited by 13 publications

References 25 publications

Analysis of the Generated Output Energy by Different Types of Wind Turbines

Analysis of the Generated Output Energy by Different Types of Wind Turbines

Probabilistic surrogate modeling of offshore wind-turbine loads with chained Gaussian processes

A Machine Learning Method for Modeling Wind Farm Fatigue Load

Contact Info

Product

Resources

About