A machine learning-based model for the estimation of the temperature-dependent moduli of graphene oxide reinforced nanocomposites and its application in a thermally affected buckling analysis

In this paper, analytical functions for the estimation of the temperature-dependent behaviors of poorly and highly dispersed graphene oxide reinforced nanocomposite (GORNC) materials are studied in the framework of a machine learning-based approach. The validity of the presented models is shown comparing the results achieved from this modeling with those reported in the open literature. Also, the application of the obtained functions in solving the thermal buckling problem of beams constructed from such nanocomposites is demonstrated based on an energy-based method incorporated with a shear deformable beam hypothesis. The verification of the results indicates that the presented mechanical model can approximate the buckling behaviors of nanocomposite beams with remarkable precision. It can be realized from the results that the temperature plays an indispensable role in the determination of the buckling load which can be endured by the nanocomposite structure.

Automated summary

This paper investigates the analytical functions for estimating the temperature-dependent behaviors of poorly and highly dispersed graphene oxide reinforced nanocomposite materials using a machine learning-based approach. The validity of the models is demonstrated by comparing the results with those in the open literature. It is shown that temperature plays a crucial role in determining the buckling load that can be endured by the nanocomposite structure.