Prediction of nth-order derivatives for vibration responses of a sandwich shell composed of a magnetorheological core and composite face layers

Abstract

Since their mechanical qualities may be adjusted by an applied magnetic field, designers have shown considerable interest in Magneto-Rheological (MR) materials, a recently discovered class of smart materials. For the first time, this research details the vibration stability related to a sandwich shell composed of an MR core and graphene nanoplatelets (GPLs) reinforced composite (GPLRC) face layers. Residual stresses under in-plane loading contribute to the geometric stiffness considered here. This paper uses a mixed and improved Halpin-Tsai hypothesis to characterize the effective material features of GPLRC face layers. Based on the linear viscoelastic scheme and Hamilton's principle, the governing equations related to the present assembly are established. As an added bonus, compatibility equations are included to aid in providing an accurate model of the sandwich. The linked structure's governing equations under a variety of boundary conditions are solved using the wave propagation technique (WPA). Here, the authors focus on validating a Deep Neural Network (DNN) strategy for different kinds of Mean Squared Error (MSE). In conclusion, the outputs illustrate that the GPL weight fraction, viscoelastic foundation, and form of the structure are crucial in establishing the vibration stability and loss parameter factor related to the sandwich shells.