Analysis of the Competing Mechanisms Between Inertial and Structural Effects in Data-Driven Hybrid Lattice Structures

Through spatial arrangement of different microstructures, well-designed hybrid lattice structures exhibit enhanced mechanical properties compared with uniform lattice structures composed of a single unit cell, thereby serving as a promising strategy for lightweight lattice structure design. However, current microstructure design approaches for hybrid lattices primarily focus on improving quasi-static compressive mechanical performance. In reality, engineering protection often involves complex dynamic impact environments rather than simple quasi-static loads. However, research on the microstructural design of hybrid lattices under high strain rate impact loading remains limited. This is due to the significant influence of inertial effects on dynamic structural mechanical response, which complicates multi-objective optimization. In this study, a fourth-order hybrid orthogonal isotropic lattice structure is constructed using two types of rhombic dodecahedron unit cells with different relative densities. A Bidirectional Long Short-Term Memory (Bi-LSTM) network is employed to develop a predictive model that expands the dataset of stress-strain curves obtained from finite element simulations. The reliability of the model’s predictions is validated through multi-dimensional evaluation metrics. Specific energy absorption is adopted as an indicator for evaluating energy absorption capacity based on the accurately predicted stress-strain curves. The structural effects on the energy absorption behavior of the hybrid lattice are analyzed under quasi-static planar compression. By increasing the compression speed to 100 m/s to simulate high strain rate conditions, the role of inertial effects on the dynamic mechanical response is investigated through comparative analysis. Furthermore, the competition and synergy between inertial effects and structural effects are systematically analyzed by categorizing the hybrid lattices according to the degree of unit cell mixing. By using machine learning to efficiently expand the data scale of finite element simulations, this study demonstrates the internal relationships among inertial effects, unit cell proportion, and spatial arrangement under high strain rate conditions. The findings provide valuable insights for the application of hybrid lattice structures in impact protection and related engineering fields.