NICOP FORWARD (DIT.AD019.134)
Thematic area
Engineering, ICT and technologies for energy and transportation
Project area
Tecnologie Marittime (DIT.AD019)Structure responsible for the research project
Institute of Marine Engineering (INM)
Project manager
MATTEO DIEZ
Phone number: 06502991
Email: matteo.diez@cnr.it
Abstract
The objective of the project is the development and application of hybrid machine learning (ML) and modal-decomposition/reduced-order methods to improve knowledge, prediction, and forecasting of global/local loads, motions, and trajectories for ships operating in waves.
The projects investigates the combination (or hybridization) of ML approaches (such as, for instance, recurrent neural networks, RNN) with modal-decomposition/reduced-order methods (such as, for instance, dynamic mode decomposition, DMD) to (a) predict/forecast global/local loads, motions, and trajectories of ships operating in waves (b) extract statistical predictive models for relevant kinematic and dynamics quantities of interest and (c) facilitate the interpretation and explanation of ML results. The proposed approach combines methods that work well in predicting systems' dynamics (such as RNN) with methods that offer a physical explanation via modal decomposition (such as DMD).Expected results include predicting/forecasting not only motions but also local global/loads on the hull, which can be extended to forecasting loads based on real-time data of ship motions only, fusing real-time data with pre-computed CFD
Goals
The objective of the project is the development and application of hybrid machine learning (ML) and modal-decomposition/reduced-order methods to improve knowledge, prediction, and forecasting of global/local loads, motions, and trajectories for ships operating in waves.
The projects investigates the combination (or hybridization) of ML approaches (such as, for instance, recurrent neural networks, RNN) with modal-decomposition/reduced-order methods (such as, for instance, dynamic mode decomposition, DMD) to (a) predict/forecast global/local loads, motions, and trajectories of ships operating in waves (b) extract statistical predictive models for relevant kinematic and dynamics quantities of interest and (c) facilitate the interpretation and explanation of ML results. The proposed approach combines methods that work well in predicting systems' dynamics (such as RNN) with methods that offer a physical explanation via modal decomposition (such as DMD).Expected results include predicting/forecasting not only motions but also local global/loads on the hull, which can be extended to forecasting loads based on real-time data of ship motions only, fusing real-time data with pre-computed CFD
Start date of activity
02/07/2021
Keywords
Improving Knowledge, Ships in Waves, Hybrid Machine Learning Methods
Last update: 26/04/2024