Abstract
AbstractWind turbine fatigue estimation is based on time‐consuming Monte Carlo simulations for various wind conditions, followed by cycle‐counting procedures and the application of engineering damage models. The outputs of the fatigue simulations are large in volume and of high dimensionality, as they typically consist of estimates on finite‐element computational meshes. The strain and stress tensor time series, which are the primary quantities of interest when considering the problem of fatigue estimation, are dictated by complex vibration characteristics due to the coupled effect of aerodynamics, structural dynamics, geometrically non‐linear mechanics, and control. A Variational Auto‐Encoder (VAE) is trained in order to model the probability distribution of the accumulated fatigue on the root cross‐section of a simulated wind turbine blade. The VAE is conditioned on historical data that correspond to coarse wind‐field measurement statistics, such as mean hub‐height wind speed, standard deviation of hub‐height wind speed and shear exponent. In the absence of direct measurements of structural loads, the proposed technique finds applications in making long‐term probabilistic deterioration predictions from historical Supervisory, Control, and Data Acquisition (SCADA) data, while capturing the inherent aleatoric uncertainty due to the incomplete information on strain time series of the wind turbine structure, when only SCADA data statistics are available.
Highlights
Prediction of remaining life of wind turbines is of great interest to turbine owners and operators
For the purpose of uncertainty propagation for the accumulating damage equivalent loads, it is of interest to model the probability distribution of short term accumulating fatigue loads with respect to the variables that are registered in SCADA data
It is argued that Variational Auto-Encoder (VAE) and generative models in general are a promising tool for diverse overarching tasks related to structural health monitoring and engineering under uncertainty
Summary
Prediction of remaining life of wind turbines is of great interest to turbine owners and operators. It is important to exploit historical records of influencing factors, such as records related to wind conditions, for robust estimates of the accumulated structural fatigue damage. We propose the construction of probabilistic models for the accumulated blade cross-section fatigue, employing large-scale simulations. The analysis and methodology presented in this work naturally extend to any cross-section of the blades or to other mechanical fatigue estimates of different components of the wind turbine, which can be learned jointly employing the proposed methodology. A general-purpose probabilistic modeling technique that can cope with quantities of interest characterized by high dimensionality, such as the short-term accumulated fatigue damage on the whole cross-section considered is proposed.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
