Abstract
A recurrent deep-neural network (DNN) surrogate model capable of modeling the unsteady aerodynamic response and dynamic stall behavior of wind turbine blades has been developed and validated for use in engineering design codes. The model is trained using a subset of the oscillating airfoil experiments conducted at the Ohio State University wind tunnel. The predictions from our DNN model show excellent agreement with the measured data and, in all cases, a marked improvement over the state-of-the-art unsteady aerodynamic models. The DNN-based unsteady aerodynamics model was integrated with OpenFAST to perform full-turbine load computations for the NREL-5MW rotor. The largest differences are observed for the inboard stations, particularly in the pitching moment response, when using the new surrogate model compared to the other models available in OpenFAST.
Highlights
Unsteady aerodynamic response of wind-turbine blades under turbulent inflow conditions is the primary driver of the fatigue loads experienced by wind turbine rotors
The deep-neural network (DNN) model consists of three stacked long short-term memory (LSTM) cells connected a linear layer
A hyperparameter optimization methodology was used to determine the optimal number of long shortterm memory (LSTM) cells, the number of hidden nodes, the batch size, and learning rate during the training phase of the surrogate model
Summary
Unsteady aerodynamic response of wind-turbine blades under turbulent inflow conditions is the primary driver of the fatigue loads experienced by wind turbine rotors. The models used in engineering design and optimization workflows must be capable of properly modeling the aerodynamic lag and hysterisis effects and the dynamic stall phenomena under a wide range of inflow conditions and Reynolds numbers across the blade. The most popular models used in wind-turbine applications are variants of either the Beddoes-Leishman (BL) [4, 5] or the Øye [6] models. These models introduce unsteady aerodynamic effects as a correction to the two-dimensional (2D) steadystate polars based on coefficients that are tuned using a limited set of parameters for specific applications using experimental datasets.
Sign-in/Register to view highlights & summary 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.
