Large amplitude vibration prediction of rectangular plates by anoptimal artificial neural network (ANN)

In this paper, nonlinear equations of motion for laminated compositerectangular plates based on the first order shear deformation theory werederived. Using a perturbation method, the nonlinear equation of motion wassolved and analytical relations were obtained for natural and nonlinearfrequencies. After proving the validity of the obtained analytical relations, as analternative and simple modeling technique, ANN was also employed to modelthe laminated rectangular plates and predict effects of different parameters onthe natural and nonlinear frequencies of the plates. In this respect, an optimalANN was selected and trained by training data sets obtained from analyticalmethod and also tested by testing data sets. The obtained results were in goodagreement with the analytical and published results