Plastic Deformation of Reinforced Aluminum Plates with Polyurea Coating under Impulsive Loading: Experimental Investigation and Modelling using Neural Networks

A single-stage gas detonation apparatus was used for the free forming of metallic-polymeric structures. In the experimental section, to improve the performance of aluminum plates under gas mixture detonation loading, a layer of polyurea material was sprayed onto the back surface of the metallic plate. In order to investigate the effect of the thickness of the metallic and polymeric layers on the dynamic response of the structure, aluminum plates with different thicknesses of 1, 1.5, 2 and 2.5 mm, as well as polyurea coatings with different thicknesses of 3, 4, 5 and 6 mm, were used. Experimental results showed that spraying the polyurea coating onto the back surface of aluminum plates can significantly reduce the maximum permanent deflection of the structure and also prevent the rupture of the aluminum specimens. In the numerical modeling section, the Group Method of Data Handling (GMDH) neural network was used to present a mathematical model based on dimensionless numbers to predict the maximum permanent deflection of metallic-polymeric structures under impulsive loading. In order to increase the prediction capability of the proposed neural network for this process, the experimental data were divided into two training and prediction sets. The results showed that good agreement between the proposed model and the corresponding experimental results is obtained and all data points are within the ±10% error range.