Determination of Material Properties of Functionally Graded Hollow Cylinders Using Artificial Neural Network

Abstract

Using guided circumferential wave dispersion characteristics, an inverse method based on artificial neural network (ANN) is presented to determine the material properties of functionally graded materials (FGM) pipes. The group velocities of several lowest modes at several lower frequencies are used as the inputs of the ANN model; the outputs of the ANN are the distribution function of the volume fraction of the FGM pipe. The Legendre polynomials method is used to calculate the dispersion curves for the FGM pipe. The internally recurrent neural network is used to improve the convergence speed.