In order to reduce the levelised cost of energy, the rotors of wind turbines are increasing in size. To increase the energy yield, wind turbine rotors need to have an innovative tip design; such as winglets. Winglets are used widely in aircraft design; however, they remain mostly absent in state-of-the-art wind turbine design. The low-fidelity wind turbine design models used by industry, such as BEM, are insufficient to capture the full 3D flow physics in such an innovative design. Therefore, high-fidelity methods, such as vortex methods, are becoming more and more important in such a design phase in wind energy research. Single-objective optimisation has been applied in earlier works to maximise power production. Winglets have shown the potential of increasing power production while simultaneously increasing the design-driving loads (DDLs), for example, the thrust or flapwise bending moment. This work focuses on optimisation using machine learning of a winglet that increases power production without increasing DDLs. A parameterised design for a winglet on a wind turbine is created. Different design constraints, such as DDLs or a diameter constraint, are explored to determine under which constraints and conditions a winglet can have an added value to the wind turbine blade design. Multi-objective Bayesian optimisation is used to maximise the rotor's power production and minimise 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. This has the goal to obtain designs that lie on the Pareto front of two or more objectives. The recent Bayesian Neural Networks 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 obtained by the optimiser. Both a downwind and upwind winglet were found to be able to increase power without increasing the thrust, root flapwise bending moment and flapwise bending moment at 80% of the rotor radius.

Wind turbine power output has grown massively over the past few decades, and this has been achieved in part by increasing the size of rotors. But the size of rotors is now limited by structural constraints as well as space constraints in wind farms. It is therefore important to use other innovative methods to increase wind turbine capacity without increasing size. One way to achieve this is by the use of winglets. Winglets increase power output by reducing tip effects, thereby producing a more efficient distribution of forces over the blade. The art of designing winglets is to find the best trade-off between the increase in profile drag of the winglet itself and the reduction of induced drag that the winglet provides. To do this, it is very important to fully understand the aerodynamics of winglets on wind turbine blades. High-fidelity methods like CFD are capable of producing accurate and detailed flow fields and are able to offer greater insight into the complex aerodynamics of winglets on rotors. However, this comes at great computational cost which might be infeasible in the design and optimization of winglets. More common and cheaper models like the BEM method are incapable of modelling winglets and other out-of-plane features. The Lifting Line Method is a middle ground that is capable of simulating winglets but is also comparatively inexpensive. The goal of this thesis is to study the performance of the Lifting Line method, in particular, ECN Aeromodule's AWSM Free-Wake Vortex Lifting Line code in simulating the case of winglets mounted on wind turbines. AWSM results are compared with results of normal and tangential forces and circulation distribution from a validated OpenFOAM model. The results show that over the outboard section of the blade and over the span of the winglet, AWSM performs well in predicting the performance of the blade-winglet configuration. This study shows that AWSM is a reliable tool for the design and optimization of winglets on wind turbine blades at a much lower cost than higher fidelity methods like CFD.