Axisymmetric thermal post-buckling of the eccentric annular sector plate made of Gori-metamaterials: introducing DNN-RF algorithm for solving the post-buckling problems

Composite eccentric annular sector plates are frequently utilized in engineering. This structure is crucial in the manufacturing, aircraft, nuclear, and construction industries due to its asymmetrical geometry. So, in this work for the first time, thermal-post buckling analysis of the composite eccentric annular sector plate made of graphene origami enriched auxetic metamaterial (GOEAM) is presented. To improve the stability of this kind of structure, the GOEAM composite eccentric annular sector plate is surrounded by an auxetic concrete foundation. To estimate the nonlinear thermal buckling information of the presented structure using a hybrid machine learning algorithm, a dataset is needed. Due to the lack of thermal post-buckling datasets for the presented composite eccentric annular sector plate, a mathematical simulation is presented. In the mathematical simulation (MS) section, quasi-3D refined theory (Q3D-RT), Von-Karman nonlinearity, minimum total potential energy principle, and Haber-Schaim formulations are used to generate the governing and boundary equations of the GOEAM annular sector plates surrounded by auxetic concrete foundation. After extracting the governing equations, they are solved via the transformed differential quadrature method (TDQM) with the aid of differential quadrature (DQ) weighting coefficients. After obtaining the datasets using MS, in the artificial intelligence domain, the results for future research of thermal post-buckling of the GOEAM composite eccentric annular sector plate surrounded by the auxetic concrete foundation are tested, trained, and validated. So, with the presented datasets of thermal post-buckling of the GOEAM composite eccentric annular sector plate surrounded by auxetic concrete foundation, this kind of structure using a machine learning algorithm can be simulated in other complex situations.