High-velocity impact study of an advanced ceramic using finite element model coupling with a machine learning approach

Abstract

A numerical approach combining finite element modeling and machine learning is used to inform the material performance of an alumina ceramic tile undergoing high-velocity impact. In this study, the alumina ceramic tile is simulated by incorporating a user-defined Johnson–Holmquist–Beissel (JHB) material model within the framework of smoothed particle hydrodynamics (SPH) in LS-DYNA finite element software. The implementation of the JHB model is verified by comparing equivalent stress–pressure responses through a single element simulation test. After implementation, the computational framework is simulated across our chosen range of conditions by matching the results from both plate impact experiments and ballistic testing from the literature. The computational model is then used to generate training data sets for an artificial neural network (ANN) to predict the residual velocity and projectile erosion for an alumina ceramic tile undergoing high-velocity impact in the SPH framework. The ANN is then used to perform a sensitivity analysis involving exploring the effect of mechanical properties (e.g., strength and shear modulus) and impact simulation geometries (e.g., thickness of ceramic tile) on material performance (i.e., residual projectile velocity and erosion). Overall, this study shows the capability of the FEM-ANN approach in studying the high-velocity impact on ceramic tiles and is applicable to guide the structural-scale design of ceramic-based protection systems.