Rapid prediction of damaged ship roll motion responses in beam waves based on stacking algorithm

Accurate modeling for highly non-linear coupling of a damaged ship with liquid sloshing in waves is still of considerable interest within the computational fluid dynamics (CFD) and AI framework. This paper describes a data-driven Stacking algorithm for fast prediction of roll motion response amplitudes in beam waves by constructing a hydrodynamics model of a damaged ship based on the dynamic overlapping grid CFD technology. The general idea is to optimize various parameters varying with four types of classical base models like multi-layer perception, support vector regression, random forest, and hist gradient boosting regression. This offers several attractive properties in terms of accuracy and efficiency by choosing the standard DTMB 5415 model with double damaged compartments for validation. It is clearly demonstrated that the predicted response amplitude operator (RAO) in the regular beam waves agrees well with the experimental data available, which verifies the accuracy of the established damaged ship hydrodynamics model. Given high-quality CFD samples, therefore, implementation of the designed Stacking algorithm with its optimal combination can predict the damaged ship roll motion amplitudes effectively and accurately (e.g., the coefficient of determination 0.9926, the average absolute error 0.0955 and CPU 3s), by comparison of four types of typical base models and their various forms. Importantly, the established Stacking algorithm provides one potential that can break through problems involving the time-consuming and low efficiency for large-scale lengthy CFD simulations.