mechanical property estimation of functionalized graphene nanocomposite using machine learning and its use-case in buckling response

In this paper, a machine learning model is developed to approximate the functionalized graphene (fg) nanocomposite’s young’s moduli in various temperatures. the machine learning model which is based on regression will find the appropriate function to estimate the temperature-dependent moduli of the fg nanocomposite and neat epoxy. afterward, the governed mathematical expressions are used to solve the buckling problem of an fg nanocomposite beam. to achieve this goal, an energy-based technique including the shear deformable beam hypothesis is utilized. also, the navier’s method is used to derive the governing equations needed to find the critical buckling response when the beam is exposed to a temperature gradient. comparisons between the results of our work with the ones reported in the literature indicate impressive precision of the presented machine learning model, as well as, the buckling response of the structure under study. finally, the impact of some parameters including the temperature gradient, and slenderness ratio on the buckling of the proposed beam structure are presented in a framework of numerical case studies. the results of this study show that temperature plays a vital role in both young’s modulus of functionalized graphene, and the buckling load that beams fabricated from nanocomposites reinforced with functionalized graphene can tolerate.