Modelling and prediction of process parameters in explosive welding of plates using GMDH-type neural network and singular value decomposition

Abstract

GMDH-type neural networks are used for the modelling of explosive welding process of plates. The aim of such modelling is to show how the geometric characteristics of the bonding interface such as amplitude and wave length change with the variation of important parameters involved in the explosive welding of plates, namely, standoff distance, mass of the explosive per unit weight of flyer plate, flyer plate thickness, and parent plate thickness. It is also demonstrated that Singular Value Decomposition (SVD) can be effectively used to find the vector of coefficients of quadratic sub-expressions embodied in such GMDH-type networks. Such application of SVD will highly improve the performance of GMDH-type networks to model the very complex process of explosive welding of plates.