Implementation of the Critical Wave Groups Method with Computational Fluid Dynamics and Neural Networks

TL;DR

This paper introduces a neural network-enhanced framework to significantly reduce the computational cost of the critical wave groups method combined with CFD for predicting extreme ship responses.

Contribution

It develops LSTM neural networks trained on limited CFD simulations to efficiently approximate the CWG method, saving two orders of magnitude in computational resources.

Findings

Neural network models accurately replicate CFD-based CWG predictions.

The framework achieves two orders of magnitude reduction in computational cost.

Validated on a 2-D ship hull in Sea State 7 and beam seas.

Abstract

Accurate and efficient prediction of extreme ship responses continues to be a challenging problem in ship hydrodynamics. Probabilistic frameworks in conjunction with computationally efficient numerical hydrodynamic tools have been developed that allow researchers and designers to better understand extremes. However, the ability of these hydrodynamic tools to represent the physics quantitatively during extreme events is limited. Previous research successfully implemented the critical wave groups (CWG) probabilistic method with computational fluid dynamics (CFD). Although the CWG method allows for less simulation time than a Monte Carlo approach, the large quantity of simulations required is cost prohibitive. The objective of the present paper is to reduce the computational cost of implementing CWG with CFD, through the construction of long short-term memory (LSTM) neural networks. After training the models with a limited quantity of simulations, the models can provide a larger quantity of predictions to calculate the probability. The new framework is demonstrated with a 2-D midship section of the Office of Naval Research Tumblehome (ONRT) hull in Sea State 7 and beam seas at zero speed. The new framework is able to produce predictions that are representative of a purely CFD-driven CWG framework, with two orders of magnitude of computational cost savings.