Analysis, forecasting and system identification of a floating offshore wind turbine using dynamic mode decomposition
Giorgio Palma, Andrea Bardazzi, Alessia Lucarelli, Chiara Pilloton, Andrea Serani, Claudio Lugni, Matteo Diez
TL;DR
The study demonstrates that Dynamic Mode Decomposition and its Hankel extensions can be effectively applied to a hexafloat floating offshore wind turbine to achieve short-term forecasting (nowcasting) and data-driven reduced-order modeling for system identification. By incorporating time-delayed observables (Hankel-DMD) and external forcing (Hankel-DMDc), and by adding Bayesian uncertainty quantification, the authors produce predictive models with practical runtimes suitable for real-time digital twins. Modal analysis reveals coherent structures linking mooring loads, platform motions, wave elevation, and wind input, guiding input selection for identification. The work shows promise for real-time, data-driven supervision of FOWTs, while acknowledging challenges from nonlinear turbine control on predicting power and rotor speed, and outlining avenues for hybridization with machine learning and richer measurement configurations.
Abstract
This article presents the data-driven equation-free modeling of the dynamics of a hexafloat floating offshore wind turbine based on the application of dynamic mode decomposition (DMD). All the analyses are performed on experimental data collected from an operating prototype. The DMD has here used i) to extract knowledge from the dynamic system through its modal analysis, ii) for short-term forecasting from the knowledge of the immediate past of the system state, and iii) for the system identification and reduced order modeling. The forecasting method for the motions, accelerations, and forces acting on the floating system is developed using Hankel-DMD, a methodological extension that includes time-delayed copies of the states in an augmented state vector. The system identification task is performed by applying Hankel-DMD with control (Hankel-DMDc), which models the system including the effect of forcing terms. The influence of the main hyperparameters of the methods, namely the number of delayed copies in the state and input vector and the length of the observation time, is investigated with a full factorial analysis using three error metrics analyzing complementary aspects of the prediction: the normalized root mean square error, the normalized average minimum-maximum absolute error, and the Jensen-Shannon divergence. A Bayesian extension of the Hankel-DMD and Hankel-DMDc is introduced by considering the hyperparameters as stochastic variables varying in suitable ranges defined after the full factorial analysis, enriching the predictions with uncertainty quantification. Results show the capability of the approaches for short-term forecasting and system identification, suggesting their potential for real-time continuously-learning digital twinning and surrogate data-driven reduced order modeling.