ANN-based surrogate model for the structural evaluation of jacket support structures for offshore wind turbines

The expansion of offshore wind farms, driven by better offshore wind conditions and fewer spatial limitations, has promoted the growth of this technology. This study focuses on the design of jacket support structures for Offshore Wind Turbines, which are suitable for deeper waters. However, the structural analysis required for designing these structures is computationally intensive due to multiple load cases and numerous checks. To reduce this computational cost, artificial-neural-network-based surrogate models capable of estimating the feasibility of a jacket structure acting as the support structure for any given wind turbine at a specific site are developed. A synthetic dataset generated through random sampling and evaluated by a structural model is utilized for training and testing the models. Two kind of models are compared: one is trained to estimate global feasibility, while the other estimates compliance with each of the structural partial requirements. Also, several assembly methods are proposed and compared. The best-performing model shows great classification metrics, with a Matthews Correlation Coefficient of 0.674, enabling an initial assessment of the structural feasibility. The low computational cost of artificial neural networks compared to structural models makes this surrogate model useful for accelerating otherwise prohibitive parametric studies or optimization processes.