Abstract
This paper introduces an advanced framework for the multi-objective optimization of mooring systems in offshore renewable energy applications. Employing a machine learning-based surrogate model integrated with the Non-dominated Sorting Genetic Algorithm II (NSGA-II), the approach efficiently navigates the complex design space. The framework, demonstrated through the optimization of a mooring system for a wave energy converter, emphasizes minimizing manufacturing costs and maximizing x-direction offset motion while adhering to specified constraints. Utilizing validated numerical models, the surrogate model is trained on a comprehensive dataset, enabling accurate predictions of tension and platform motion. The integration of a genetic algorithm systematically explores design possibilities, with the surrogate model validating each generation, eliminating the need for time-intensive simulations. The study produces a spectrum of optimal solutions, offering insights into the intricate interplay between design modifications, cost considerations, and platform motion. This nuanced understanding facilitates informed decision-making in the realm of offshore renewable energy projects, providing a valuable contribution to mooring system design optimization.
