This journal paper focuses on developing surrogate models for predicting the damage equivalent load (DEL) on wind turbines without needing extensive aeroelastic simulations. The study emphasizes the development of a sequential machine learning architecture for this purpose. The study also explores implementing simplified wake models and transfer learning to enhance the models' prediction capabilities in various wind conditions.

The selection of a suitable site for the installation of a wind turbine plays an important role in ensuring a safe operating lifetime of the structure. In this study, we show that mixture density networks can accelerate this process by inferring functions from data that can accurately map the environmental conditions to the loads but also propagate the uncertainty from the inflow to the response.

This study investigates the offshore wind turbine support structure’s fatigue life by a rapid numerical model which considers the effects of scour and a tuned mass damper. An optimization technique is proposed to find the damper's optimal parameters, considering time-varying scour. It is found that the damper optimized by the proposed optimization technique performs better than an initially designed damper in terms of fatigue life enhancement.

Oscillating bearings, like rotating bearings, can fail due to rolling contact fatigue. But the publications in the literature on this topic are difficult to understand. In order to help people decide which method to use, we have summarized the available literature. We also point out some errors and things to look out for to help engineers that want to calculate the rolling contact fatigue life of an oscillating bearing.

Wind turbine rotor blades consist of several subcomponents that are glued together. Such connections are subjected to fatigue loads. This paper analyzes the characteristics of those fatigue loads in trailing edge adhesive joints of three different wind turbine rotor blades. It is shown that the fatigue loads have significant degrees of non-proportionality, which helps engineers to choose a valid fatigue analysis framework and to design more reliable and cost-efficient rotor blades in the future.