Relative Foil-Fluid Velocity Estimation and Forecasting for Cyclorotor Wave Energy Conversion

Wave energy remains an underutilized renewable resource, requiring further advancements in Wave Energy Converters (WECs) to compete with wind and solar energy. However, the high levelized cost of energy (LCoE) associated with traditional WECs, which rely on buoyancy or diffraction, has hindered their commercial viability. In contrast, recent analytical and experimental studies on lift-based cyclorotor WECs have demonstrated superior power absorption potential, particularly when optimal control strategies are employed. Effective control, however, depends on accurate estimation and prediction of the wave-induced relative foil-fluid velocity. This study introduces a novel approach to estimate and predict the relative foil-fluid velocity for hydrofoils in a cyclorotor WEC by utilizing an Extended Kalman Filter (EKF) and Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN). The obtained results demonstrate reliable estimation and prediction of the relative foil-fluid velocity, paving the way for the implementation of advanced control strategies in cyclorotor WECs.