Three-dimensional free vibration analysis of functionally graded piezoelectric annular plates via SSDQM and comparative modeling by ANN

This work deals with the study of the free vibration analysis of functionally graded piezoelectric (FGP) annular plates with different boundary conditions. In order to carry out the analysis, a state-space based differential quadrature method (SSDQM) and comparative behavior modeling by an artificial neural network (ANN) are used. The material properties are assumed to have an exponent-law variation through the thickness. A semi-analytical approach (SSDQM) which makes use of the state-space method in the thickness direction and the one-dimensional differential quadrature method in the radial direction is used to obtain the vibrational frequencies. The governing equations are based on 3D piezoelectricity. Numerical results are given to demonstrate the convergence and accuracy of the present method. Also an optimal ANN is selected, trained and tested by the obtained numerical results. In addition to the quantitative input parameters, types of the boundary conditions are also considered as a qualitative input in NN modeling. Eventually the results of SSDQM and ANN are compared and the influence of thickness of the annular plate, the material property graded index and the circumferential wave number on the non-dimensional natural frequency of annular FGP plates with different boundary conditions are investigated. The new results can be used as benchmark solutions for future studies.