An intelligent computer method for vibration responses of the spinning multi-layer symmetric nanosystem using multi-physics modeling

This article is the first attempt to employ deep learning to estimate the frequency performance of the rotating multi-layer nanodisks. The optimum values of the parameters involved in the mechanism of the fully connected neural network are determined through the momentum-based optimizer. The strength of the method applied in this survey comes from the high accuracy besides lower epochs needed to train the multi-layered network. It should be mentioned that the current nanostructure is modeled as a nanodisk on the viscoelastic substrate. Due to rotation, the centrifugal and Coriolis effects are considered. Hamilton's principle and generalized differential quadrature method (GDQM) are presented for obtaining and solving the governing equations of the high-speed rotating nanodisk on a viscoelastic substrate. The outcomes show that the number of layers viscoelastic foundation, angular velocity speed, angle of ply, nonlocal, and length-scale parameters have a considerable impact on the amplitude and vibration behavior of a laminated rotating cantilevered nanodisk. As an applicable result in related industries, in the initial value of radius ratio, damping of the foundation does not have any effect on the dynamics of the system, but when the outer radius is bigger enough, the effect of damping parameter on the frequency of the laminated nanostructure will be bold sharply.

Automated summary

This article explores the frequency performance of rotating multi-layer nanodisks using deep learning. The optimized neural network parameters contribute to the method's high accuracy and efficiency in training the multi-layered network. The study reveals the significant impact of various parameters on the vibration behavior of laminated rotating cantilevered nanodisks.