A neural network--based methodology for the recreation of high-speed impacts on metal armours

摘要

The prediction of the consequences of a ballistic impact is highly relevant in the advanced material engineering. Traditionally, the solution of this kind of problems was made by means of experimental tests, analytical models or numerical simulations. In this domain, the particularities of the phenomenon at high speed increase the difficulty of the mathematical resolution of the equations associated, and the complexity of the mechanical behaviour of the materials at high strain rates complicates the numerical simulation of the problem. Therefore, this paper describes a neural network--based methodology applied to recreate the ballistic impact phenomenon. The objective of this study is threefold. Firstly, to obtain the most precise prediction possible, minimizing the amount of data used. Secondly, to discover and analyse the influence of each of the variables on the entire neuronal model. Finally, to compare the precision and performance of this methodology with other alternatives of learning machine. The empirical results have shown that the proposed methodology is an interesting approach to reliably solving ballistic impact problems.