TY - JOUR
T1 - Vortex-model-based Multi-objective Optimization of Winglets for Wind Turbines using Machine Learning
AU - Leenders, Nick
AU - Yu, Wei
AU - Gaunaa, Mac
AU - Caboni, Marco
AU - Ferreira, Carlos Simão
PY - 2022
Y1 - 2022
N2 - Different Design Driving Load constraints (DDLs), are explored in this work to determine under which constraints and conditions a winglet can have an added value to the wind turbine blade design. Multi-objective Bayesian optimization is used to maximize the rotor's power production while minimizing the flapwise DDLs. Surrogate models, created using machine learning techniques such as Gaussian Processes and Bayesian Neural Networks, are used in combination with an acquisition function, to determine what designs should be evaluated by the lifting line model AWSM, with the goal to obtain designs that lie on the Pareto front of two or more objectives. The recent Bayesian Neural Networks as surrogate model were able to find the Pareto-front most effectively in this work. Furthermore, the results show that different DDL constraints led to different winglet designs, with noticeable differences between upwind and downwind winglet designs. Winglet designs were found to be able to increase power without increasing the thrust, root flapwise bending moment and flapwise bending moment at radial locations on the blade. A noticeable increase in power was found when introducing sweep to the winglet design.
AB - Different Design Driving Load constraints (DDLs), are explored in this work to determine under which constraints and conditions a winglet can have an added value to the wind turbine blade design. Multi-objective Bayesian optimization is used to maximize the rotor's power production while minimizing the flapwise DDLs. Surrogate models, created using machine learning techniques such as Gaussian Processes and Bayesian Neural Networks, are used in combination with an acquisition function, to determine what designs should be evaluated by the lifting line model AWSM, with the goal to obtain designs that lie on the Pareto front of two or more objectives. The recent Bayesian Neural Networks as surrogate model were able to find the Pareto-front most effectively in this work. Furthermore, the results show that different DDL constraints led to different winglet designs, with noticeable differences between upwind and downwind winglet designs. Winglet designs were found to be able to increase power without increasing the thrust, root flapwise bending moment and flapwise bending moment at radial locations on the blade. A noticeable increase in power was found when introducing sweep to the winglet design.
UR - http://www.scopus.com/inward/record.url?scp=85131827021&partnerID=8YFLogxK
U2 - 10.1088/1742-6596/2265/3/032056
DO - 10.1088/1742-6596/2265/3/032056
M3 - Conference article
AN - SCOPUS:85131827021
SN - 1742-6588
VL - 2265
JO - Journal of Physics: Conference Series
JF - Journal of Physics: Conference Series
IS - 3
M1 - 032056
T2 - 2022 Science of Making Torque from Wind, TORQUE 2022
Y2 - 1 June 2022 through 3 June 2022
ER -