This study aims to investigate the power takeoff (PTO) performance of a two-buoy-type wave energy converter (WEC) with a PTO system under real sea conditions. The two-buoy-type WEC is composed of two hemispherical heaving buoys with a hydraulic PTO system. The hydrodynamic analysis considering two-body interaction is carried out based on the wave green function and Cummins equation. In addition, a hydraulic PTO system is described as an approximate Coulomb damping force and applied to the equation of motion for a WEC. First, by comparing the extraction power on various irregular wave conditions, the PTO performance of an isolated-buoy WEC, and the two-buoy-type WEC is estimated. Through this, it is found that the maximum extraction power occurred when the wave peak period is 1.2 times longer than the heave natural period of a WEC. By comparing the external force and wave elevations near the WEC, three incident wave directions are applied for the maximum or minimum extraction power. Based on these results, the two-buoy-type WEC is applied to the Korean coastal area (Uljin). The PTO force is calculated from the polynomial regression analysis to produce maximum extraction power on various irregular wave conditions. Finally, the annual extraction power and capture width of the WEC in Uljin are calculated. The relation between the design wave period and heave natural period of the WEC is investigated. The annual extraction power is maximum when the design wave period is 20% longer than the WEC's heave natural period and the incident wave is 90°.

This paper introduces a comprehensive, data-driven framework for parametrically estimating directional ocean wave spectra from numerically simulated FPSO (Floating Production Storage and Offloading) vessel motions. Leveraging a mid-fidelity digital twin of a spread-moored FPSO vessel in the Guyana Sea, this approach integrates a wide range of statistical values calculated from the time histories of vessel responses—displacements, angular velocities, and translational accelerations. Artificial neural networks (ANNs), trained and optimized through hyperparameter tuning and feature selection, are employed to estimate wave parameters including the significant wave height, peak period, main wave direction, enhancement parameter, and directional-spreading factor. A systematic correlation analysis ensures that informative input features are retained, while extensive sensitivity tests confirm that richer input sets notably improve predictive accuracy. In addition, comparisons against other machine learning (ML) methods—such as Support Vector Machines, Random Forest, Gradient Boosting, and Ridge Regression—demonstrate the present ANN model’s superior ability to capture intricate nonlinear interdependencies between vessel motions and environmental conditions.