Predicting the near field underwater explosion response of coated composite cylinders using multiscale simulations, experiments, and machine learning

Prediction of underwater explosion response coated composite cylinders using machine learning (ML) requires a large, consistent, accurate, and representative dataset. However, such reliable large experimental dataset is not readily available. Besides, the ML algorithms need to abide by fundamental laws physics avoid non-physical predictions. To address these challenges, this paper synergistically integrates with high-throughput multiscale finite element (FE) simulations predict subjected nearfield explosion. The simulated responses from approach correlate very well observations. After validation approach, consistent containing more than 3800 combinations developed simulation varying fiber/matrix/coating material properties, coating thickness as variables explosive energy stand-off distance. leveraged feed-forward multilayer perceptron-based neural network (NN) which shows excellent Overall, synergistic powered physics-based presented here can potentially enable materials scientists engineers make intelligent, informed decisions in purview innovative design strategies for mitigation structures.