Study on a Zerilli-Armstrong and an artificial neural network model for 4Cr5MoSiV1 Quenched Steel at High Strain Rate

The flow stress in compression of 4Cr5MoSiV1 quenched Steel was investigated by means of a split Hopkinson pressure bar (SHPB) experiment apparatus under different temperature. According to the stress-strain curves, the Zerilli-Armstrong constitutive model was chosen and its relationship parameters were determined by Genetic Algorithm (GA) with adaptive population size. At the same time, the Back Propagation artificial neural network (BP ANN) was used for establishing constitutive model of 4Cr5MoSiV1 quenched Steel. Compared with the experimental data, two constitutive equations can predict the flow stress very well, and the prediction method using the BP artificial neural network had higher accuracy. The research provides a necessary material characteristic parameters for finite element numerical simulation of 4Cr5MoSiV1 quenched Steel, and the two prediction method can be widely used to establish other nonlinear relations of manufacturing procedure.