Development of an artificial neural network model for estimating the radius ratio of a one-layered cylindrical shell

The results obtained from previous studies on the acoustic scattering of a plane wave by an elastic cylindrical shell, show that the acoustic resonances of the shell are related to its physical and geometrical properties. In order to estimate the radius ratio of an air-field immersed cylindrical shell, an approach based on artificial neural networks was proposed, which uses the reduced cutoff frequencies of circumferential waves that propagate around the cylindrical shell. The reduced cutoff frequencies of circumferential waves are extracted using modal isolation plan representation. The proposed approach allows us to estimate accurately the values of the radius ratio of the copper cylindrical shell, as well as it can help us to resolve other problems related to acoustic scattering. Furthermore, it can be used to estimate other parameters of the cylindrical shell starting from the characteristics of which it is disposed. The approach proposed in this study does not present any approximation as in the case of the proper mode theory