Hybrid Numerical Modeling of Ballistic Clay under Low-Speed Impact using Artificial Neural Networks

TL;DR

This paper presents a hybrid ANN-FEM model that accurately predicts clay indentation depth under low-speed impact, optimizing material parameters without additional mechanical testing, thus improving ballistic performance modeling.

Contribution

The study introduces a novel hybrid neural network and finite element approach to determine high-strain-rate material parameters for clay, bypassing traditional testing methods.

Findings

Achieved over 98% prediction accuracy.

Successfully optimized material parameters using inverse tracking.

Enhanced modeling of ballistic clay behavior.

Abstract

Roma Plastilina No. 1 clay has been widely used as a conservative boundary condition in bulletproof vests, namely to play the role of a human body. Interestingly, the effect of this boundary condition on the ballistic performance of the vests is indiscernible. Moreover, back face deformation should be characterized by measuring the indentation in the deformed clay, which is important for determining the lethality of gunshots. Therefore, several studies have focused on modeling not only bulletproof vests but also the clay backing material. Despite various attempts to develop a suitable numerical model, determining the appropriate physical parameters that can capture the high-strain-rate behavior of clay is still challenging. In this study, we predicted indentation depth in clay using an artificial neural network (ANN) and determined the optimal material parameters required for a finite element method (FEM)-based model using an inverse tracking method. Our ANN-FEM hybrid model successfully optimized high-strain-rate material parameters without the need for any independent mechanical tests. The proposed novel model achieved a high prediction accuracy of over 98% referring impact cases.