a b s t r a c tA new methodology based on artificial neural networks has been developed to study the high velocity oblique impact of spheres into CFRP laminates. One multilayer perceptron (MLP) is employed to predict the occurrence of perforation of the laminate and a second MLP predicts the residual velocity, the obliq uity of trajectory of the sphere after perforation and the damage extension in the laminate. In order to train and test the networks, multiple impact cases have been generated by finite element numerical sim ulation covering different impact angles and impact velocities of the sphere for a given system sphere/ laminate.

This article puts forward the results obtained when using a neural network as an alternative to classical methods (simulation and experimental testing) in the prediction of the behaviour of steel armours against high-speed impacts. In a first phase, a number of impact cases are randomly generated, varying the values of the parameters which define the impact problem (radius, length and velocity of the projectile; thickness of the protection). After simulation of each case using a finite element code, the above-mentioned parameters and the results of the simulation (residual velocity and residual mass of the projectile) are used as input and output data to train and validate a neural network. In addition, the number of training cases needed to arrive at a given predictive error is studied. The results are satisfactory, this alternative providing a highly recommended option for armour design tasks, due to its simplicity of handling, low computational cost and efficiency.

a b s t r a c tA new tool based on artificial neural networks (ANNs) has been developed for the design of lightweight ceramic-metal armours against high-velocity impact of solids. The tool developed predicts, in real-time, the response of the armour: impacting body arrest or target perforation are determined and, in the latter case, the residual mass and velocity of the impacting body are determined. A large set of impact cases has been generated, by FEM numerical simulation, in order to train and test the ANN. The impact cases consider different impacting body and target geometries, materials and impact velocities, all these parameters varying in a wide range that covers most common impact situations. The behaviour of the ceramic material under impact was simulated using a modified version of the model developed by Cortés et al. The ANN developed has a remarkable prediction ability and therefore it constitutes a complementary methodology to the conventional design techniques.

a b s t r a c tA constitutive model to simulate the behavior of ceramic materials under impact loading is proposed in order to achieve a better representation of the damage process due to the material fragmentation. To integrate the proposed constitutive equations, a semi implicit algorithm (implicit for the stresses and explicit for the damage variable) has been developed, leading to the generalized expressions of the clas sical return mapping algorithm. The model was implemented in a commercial finite element code and its performance was demonstrated by comparing its predictions with experimental results obtained by other authors.