Nonlinear vibration analysis of graphene platelets reinforced nanocomposite doubly curved concrete panels subjected to thermal shock: Development of an artificial intelligence technique

Abstract

When the temperature gradient across a component quickly changes, a phenomenon known as thermal shock occurs that exposes the component to fast variable thermal stresses and large-scale strains. One of the goals of this abrupt loading is to increase the capacity of different systems to withstand thermal shock. The nonlinear thermally induced vibration of doubly curved graphene nanoplatelet reinforced nanocomposite panels subjected to abrupt thermal shock is being studied right now. The bottom portion of the curved panel system is held at a reference temperature while the top portion is thermally shocked. The Crank-Nicholson technique and generalized differential quadrature (GDQ) are used to build up and solve the one-dimensional transient heat equation. The double-curved panel’s thermomechanical characteristics are temperature dependent; hence this equation is nonlinear. Based on the law of decoupled thermoelasticity, Kant’s theory, and von Karman’s assumption of some kind of geometric nonlinearity, the overall function of the doubly curved panel is established. After modeling the current system mathematically and comparing the current approach’s findings to those of earlier research, we revalidated the findings in a Python environment by comparing them to those of the Extreme Gradient Boosting (XGBoost) machine learning algorithm. This approach is founded on the “boosting” idea, which combines additive training techniques with the identification of weak learners to produce strong learners. The findings demonstrate that certain structural geometrical and physical factors are significant contributors to the double-curved GPLRC panel’s nonlinear frequency under thermal shock.