Al-Li alloys are widely used in aerospace applications due to their high strength, high fracture toughness, and strong resistance to stress corrosion. However, the lack of interatomic potentials has hindered systematic investigations of the relationship between structures and properties. To address this issue, we apply a neural network-based neuroevolutionary machine learning potential (NEP) and use evolutionary strategies to train it for large-scale molecular dynamics (MD) simulations. The results obtained from this potential function are compared with those from Density Functional Theory (DFT) calculations, with training errors of 2.1 meV/atom for energy, 47.4 meV/Å for force, and 14.8 meV/atom for virial, demonstrating high training accuracy. Using this potential, we simulate cluster formation and the high-temperature stability of the T1 phase, with results consistent with previous experimental findings, confirming the accurate predictive capability of this potential. This approach provides a simple and efficient method for predicting atomic motion, offering a promising tool for the thermal treatment of Al-Li alloys.

Due to their excellent specific strength and lightweight characteristics, Al-Cu-Li alloys are widely used in aerospace applications. The newly developed three-stage creep aging (CA) process ensures both the formability and high performance of the Al alloy. However, research at the atomic scale investigating the relationship between the microstructure and performance of ternary alloys under intricate heat treatment conditions remains scarce. This study investigates the microstructural evolution of Al-Cu-Li alloys during multi-stage low-high-low temperature CA experiments, combined with molecular dynamics (MD) simulations based on the neuroevolutionary machine learning potential (NEP) function. The simulation results indicate that the segregation state of lithium atoms at low temperatures is unstable and cannot persist at elevated temperatures. As the aging temperature in the second stage increases, the segregation of lithium atoms gradually diminishes. However, the low-temperature aging in the third stage facilitates continued atomic segregation, although the recovery is somewhat limited. Additionally, it was observed that high-temperature aging in the second stage reduces the material’s performance, while the low-temperature aging in the third stage contributes to the recovery of its properties. The experimental results indicate that the degree of precipitation phase enrichment decreases with the increase in temperature during the second stage but slightly increases with the low-temperature aging in the third stage. The excellent agreement between the experimental and simulation results validates the reliability of the MD simulations, providing a valuable reference for the performance enhancement and microstructural optimization of Al-Cu-Li alloys.