Artificial intelligence/machine learning methods can discover hidden physical patterns in data. By constructing an end-to-end surrogate model between state parameters and dynamic results, many complex engineering problems such as strong coupling, nonlinearity, and multiphysics can be efficiently solved. In the field of highly nonlinear explosion and shock dynamics, a classic detonation driving problem was chosen as the research object. Using numerical simulation results as training data for machine learning surrogate models, and combining forward simulation and reverse design organically. Based on deep neural network technology, an end-to-end surrogate model was constructed between feature position velocity profiles, material dynamic deformation, and engineering factors. And the calculation accuracy of the surrogate model was provided, verifying the ability to invert engineering factors from velocity profiles. The research results indicate that the end-to-end surrogate model has high predictive ability, with relative errors of less than 1% in both velocity profile prediction and engineering factor estimation. It can be applied to the rapid design, high-precision prediction, and agile iteration of highly nonlinear explosion and impact dynamics problems.

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.