Improving Ship Response Estimation using Neural Networks

Abstract

The feasibility of a data-adaptive multi-fidelity seakeeping model is assessed for use in early stage design in this study. Data adaptive tuning (or correction) of lower-fidelity model predictions are implemented based on training with higher fidelity ship motion response data. Long Short-Term Memory (LSTM) neural networks are incorporated as part of a multi-fidelity approach for prediction of 6 degree of freedom (6-DOF) ship motion responses in waves. LSTM networks are trained and tested with Large Amplitude Motion Program (LAMP)simulations as a target, and SimpleCode simulations and wave time series as inputs. LSTM networks improve the fidelity of SimpleCode seakeeping predictions relative to LAMP, while retaining the computational efficiency of a lower-fidelity simulation tool.