Damage prediction of hull structure under near-field underwater explosion based on machine learning

Underwater explosions generate diverse loads, encompassing shock waves and bubble pulsation, and pose a substantial threat to naval vessels. In this study, finite element simulations were carried out to evaluate the response of the hull to different underwater explosion cases, including varying TNT masses and standoff distances. With the increase of the standoff distance, the deformation of the bottom plate was observed to exhibit a multi-peak phenomenon with a sharp decrease followed by a slight increase and subsequent reduction. Based on a large hull damage dataset obtained from the finite element simulations, a deep neural network (DNN) model was trained using machine learning (ML) algorithms. The deformation values predicted by the model were found to closely match the simulation results. This method provides an approach for the rapid prediction of the deformation of hull structures under near-field underwater explosions.