Forward prediction of surface wave elevations and motions of offshore floating structures using a data-driven model
Jialun Chen, Ian Milne, Paul H. Taylor, David Gunawan, Wenhua Zhao
Abstract
Accurate predictions of surface waves and subsequent wave-induced vessel motion have the potential to improve safety and efficiency for a wide range of offshore operations, such as active control of wave energy converters and floating wind turbines. In this paper, an Auto-Regressive model is proposed to predict surface waves and vessel motions based on the measured time sequences at a particular location. Based on numerically synthesized wave data, it is shown that band-pass filtering with a single cut-off frequency can improve the accuracy of predictions. These prediction results suggest that the narrower the spectral bandwidth, the more accurate predictions. However, digital filters cannot be implemented in the context of real-time prediction due to non-causality. For practical forecast, prediction of offshore floating structures could be treated in much the same as a physical filter as it only responds significantly over a limited range of frequencies. Analysis of wave basin test data confirms this hypothesis, making the forecasting of floating body motions promising.