This work introduces a quasi-3D refined theory for assessing the transient dynamic reactions of a sandwich annular sector plate subjected to mechanical shock loading. The sandwich structure has two facesheets composed of graphene origami (GOri)-enabled auxetic metal metamaterials (GOEAMs) and a core composed of carbon fiber reinforced polymer. The auxetic quality of the annular plates is mainly determined by the quantity of graphene and the level of folding in the GOri material. The elements are assessed layer by layer across the thickness of the plates. Micromechanical models supported by genetic programming may be used to predict the position-dependent Poisson’s ratio and other material parameters. The concept of Hamiltonian is used to deduce the governing equations of the structure. The equations of motion, which vary with time, are solved using the numerical solution process and the Laplace transform. A comprehensive parametric study is carried out to examine the influence of various geometric and physical parameters on the time-dependent behavior of annular sector plates. The current mathematical modeling results are being compared to the findings of previous works, as well as a machine learning technique. By using this machine learning methodology, it is feasible to computationally solve differential equations at a reduced expense, while simultaneously surmounting the challenge of formulation. To use machine learning techniques, a dependable dataset acquired from either experimental or numerical analysis is necessary. The dataset was created using the quantitative findings of the investigation. Furthermore, the machine learning technique demonstrates its capacity to provide very precise outcomes when predicting the transient behavior of the existing structure under novel loading and boundary circumstances.