1Departamento de Ingenierıa Mecánica, Escuela Politécnica Nacional 2Research Center of Mathematical Modelling (MODEMAT) Quito, Ecuador 17-01-2759

Abstract:

Abstract 6 Safe execution of marine operations (MOs) depends on accurate pbkp_rediction of vessel dynamic 7 responses, which are necessary to help a superintendent make on-board decisions. However, it can 8 be challenging to conduct complex numerical simulations prior to execute a MO, especially at offshore 9 sites characterized by complex wave conditions, ie multimodal directional (2D) wave spectra. In 10 this context, this article introduces a methodology for assessing vessel dynamic responses using 11 characteristics of actual 2D wave spectra and regression models from machine learning. First, a 12 state-of-the-art algorithm is used for 2D spectra partitioning and spectral characterization (climate). 13 This allows identifying wave systems that can occur at a study location, and their integral parameters. 14 For that, a data set for the North Atlantic Ocean, spanning 36 years is used. Then, the main wave 15 parameters of each wave system including significant wave height, peak period and peak direction, 16 are used as features to train and test regression models from machine learning tool kits. Accurate 17 pbkp_redictions of dynamic responses were obtained with a” boosted trees” regression model considering 18 all six long-term wave systems (18 features) detected at the site. These findings are valuable as new 19 tools to help on-board personnel make safe and quick decisions. 20

Año de publicación:

Keywords:

Fuente:

google