Application of machine learning algorithm to measure nonlinear transient frequencies of the centrifugal systems under moving loads with velocity acceleration

Submarines, civil engineering, and aeronautical engineering all use a series of interconnected cone-cone shells in a progressive manner. It is well acknowledged that when shells experience fast loading, a substantial localized bending moment is generated around the junction. These heavy loads have the potential to generate vibrations that may lead to fatigue issues. So, in order to establish the essential requirements for safe design, it is imperative to comprehend the vibration characteristics of bonded shells. The nonlinear oscillations of conical-conical graphene nanoplatelets reinforced composite (GPLRC) shells under moving loads with velocity acceleration are therefore shown for the first time in this work. Mathematical simulations that make use of the von Karman nonlinearity and account for the continuity of the displacement components as well as the forces and moments that occur at the intersection of the shell system are used to describe a cone-cone shell structure. The generalized differential quadrature technique (GDQM), the Newmark method, and the Newton-Raphson iterative approach are used to solve the nonlinear partial differential equations (NPDEs) of the system. It may be shown that the results have been verified by contrasting the findings of the present study with those of earlier studies. Moreover, for additional assurance, the extreme gradient boosting (XGBoost) algorithm as an effective machine learning model is presented for more verification and prediction of the engineering problem. Finally, some innovative and applicable outcomes for future handbooks of mechanical engineering are provided in detail.