Simulation Study on Tensile Mechanical Properties of Graphene Based on Long and Short-Term Memory Neural Network

Abstract

The current simulation methods of graphene tensile mechanical properties have not processed the data used in the simulation process, resulting in large errors between the simulation results and the experimental results. For this reason, a graphene tensile mechanics based on long and short-term memory neural networks is proposed. The graphene nanoribbons model was established using Materials Studio software to determine the simulation process of graphene tensile mechanical properties. Use the long and short-term memory neural network to process and store the simulation research data to get the simulation results. Analysis of the simulation results shows that the tensile properties of graphene are affected by the structure of graphene itself, the constituent element atoms, and the distance between atoms, and there will be certain differences in tensile forces in different directions. Three sets of comparative experiments are designed. The experimental results show that the simulation results obtained by the simulation method of graphene tensile mechanical properties in this study are very close to the experimental results, and there is basically no experimental error.