Constitutive model of additively manufactured FeCoCrNi high-entropy alloy

High-entropy alloys (HEAs) have attracted extensive attention due to their excellent properties, and additively manufactured FeCoCrNi HEAs show great potential in various applications. Uniaxial compression experiments at room temperature were conducted on additively manufactured FeCoCrNi HEAs using a self-developed high-throughput compression testing machine under different strain rates (1.5 × 10⁻³/s, 1.5 × 10⁻²/s, 1.5 × 10⁻¹/s, 1.5/s). The true stress–strain relationships of the material were obtained. Results indicated that the flow stress increased with the strain rate. Three constitutive models were established: phenomenological models based on Johnson–Cook and Khan–Huang–Liang, and a backpropagation (BP) neural network model. These models predicted the relationship between the flow stress and strain rate of the HEA. Parameters of the constitutive models were optimized using regression analysis and a genetic algorithm. The accuracy of the models was evaluated by calculating their correlation coefficients (R) and average absolute relative errors, showing that the BP neural network model was the most accurate in describing the flow stress.