To achieve high-throughput optimization design of gradient materials, it is essential to establish accurate and rapid predictive capabilities for the loading performance of such materials. The rapid advancement of artificial intelligence technology combined with hardware development has gradually become a revolutionary research tool across various scientific fields. In materials science, machine learning methods play a significant role in high-throughput material design and performance prediction. This study introduces machine learning methods into the optimization design of functionally graded materials with controllable loading. By integrating computational results from physics-based models, a relatively accurate rapid prediction model was established, significantly enhancing optimization throughput. The multi-material fluid-elastoplastic computational program MLEP has undergone multiple rounds of validation in the experimental design and data interpretation of gradient materials, demonstrating high predictive accuracy for experimental results. Numerical experimental samples based on this program can be used to construct high-precision surrogate models. To extend MLEP’s applicability to a broader range of density-gradient material design and experimental prediction, the p-α model has been incorporated into the existing simulation framework. This model describes the mechanical behavior of low-density polymers under shock/quasi-isentropic loading, enabling the expansion of flyer plate density from approximately 0.5 g/cm³ to 15.0 g/cm³.