To optimize material performance and ensure the safety of engineering structures, it is essential to investigate the mechanical properties of cement hydration models with complex structures. This study aims to investigate the influence of the water-to-cement ratio and phase volume fractions on the equivalent mechanical properties of cement paste, particularly focusing on how these parameters influence the behavior of the material. A data-driven model is proposed to predict the mechanical performance of hydrated cement structures. Three-dimensional structural slices of Portland hydrated cement paste were created by utilizing the HYMOSTRUC 3D software. Subsequently, an automated batch-processing script coded in Python was applied to transform these slices into ABAQUS models. Tensile simulations were performed to determine the equivalent elastic modulus and equivalent strength of the structures. Based on the simulation results, a backpropagation prediction model was developed using a data-driven approach. Hyperparameter optimization of the model was performed using K-fold cross-validation to improve its generalization capability. Consequently, the trained neural network model demonstrates high accuracy in predicting the mechanical properties of hydrated cement structures. This approach not only ensures reliable predictions but also significantly reduces the complexity associated with traditional microscale material analysis methods. Overall, this study offers an efficient and robust solution for performance prediction of cement-based materials.

The application of carbon fiber reinforced polymer (CFRP) composite in protective equipment is restricted by its complex penetration behavior and unclear failure mechanism under fragment impact. To overcome the difficulty and high cost of monitoring the penetration process information through experiments, a finite element analysis (FEA) model of CFRP composite under fragment impact is constructed in this study. In this model, a strain-based three-dimensional Hashin failure criterion is adopted, and the rate-dependent relationship of strength is introduced. The effectiveness of the FEA model is verified by comparison with experimental results. The simulation results show significant difference in both initial velocities and impact inclination angles under different TNT equivalents and distances from the explosion point. The inclination angles of fragments with the target plate on y-z and x-z planes are defined as α and β. When β=0°, CFRP composites exhibit pronounced impact velocity sensitivity in the velocity range of 195−392 m/s. The energy absorption capability and impact velocity sensitivity of specimens with different inclination angles β are significantly different. However, the energy absorption capability and impact velocity sensitivity of specimens with different inclination angles α do not show significant differences. When α=0°, the impact velocity sensitivity of CFRP composites in the impact velocity range of 195−392 m/s gradually declines with the increase of inclination angle β. Visualization of the penetration process and failure area indicates that the contact area and time and deformation degree are the crucial reasons for the differences in energy absorption capability and impact velocity sensitivity observed in CFRP composites.