Forced vibration analysis of the axially reinforced thick concrete plate using general expression of the polynomial series theory: Development and validation of a deep neural network

In this work, the forced vibration characteristics of an axially reinforced concrete plate with graphene nanoplatelets (GPLs) subjected to various external loadings is investigated. The shear stress in the thickness direction and the strain effect across the thickness are both taken into account in the quasi-3D plate model used to develop the governing equations for plate motion. The Halpin-Tsai model and rule of the mixture are used to determine the properties of composite materials. Differential circumstances are translated to the Laplace space to determine the system's time-dependent response. At that point, the temporal realization of the system's response is inferred from the Laplace space using the modified announcement of Abate and Dubner's approach. Open-source results from the literature and deep neural networks (DNN) are compared to the present results to confirm the findings. To forecast the vibrational behavior of the existing system, a supervised neural network based on physical knowledge is introduced for DNN. To address the issue of identifying natural frequencies, data-driven discoveries, and data-driven solutions are offered in this context. The fundamental equations created may be applied to any plate moving under a load with constant magnitude and velocity along any route. The findings demonstrate the significance of GPLs features in the transient and forced oscillations of composite systems. The outcomes of our present study may be used as benchmarks and as valuable guidance for more advanced structural design procedures in the future.