ABSTRACT
A new approach is used to predict the acoustic form function (FF) for an infinite length cylindrical shell excited perpendicularly to its axis using the artificial neural network (ANN) techniques. The Wigner-Ville distribution is used like a comparison tool between the FF calculated by the analytical method and that predicted by the ANN techniques for a stainless steel tube. During the development of the network, several configurations are evaluated for various radius ratios ba (a: outer radius: b: inner radius of the tube). The optimal model is a network with one hidden layer. It is able to predict the FF with a mean relative error about 1.61% for the cases studied in this paper.
Subject(s)
Acoustics , Computer Simulation , Models, Theoretical , Neural Networks, Computer , Sound , Stainless Steel , Water , Acoustics/instrumentation , Equipment Design , Reproducibility of Results , Sound Spectrography , Time Factors , VibrationABSTRACT
This work concerns monitoring the polymerization of an epoxy resin and its hardener. An ultrasonic pulse echo technique was used to monitor the attenuation, the phase velocity, and the acoustic impedance of the resin as a function of time. The first two parameters give information about the average state of the hardening of the resin itself. The third parameter, acoustic impedance, indicates the state of the hardening of the resin at the interface with the vessel. These parameters are determined from spectral properties of echoes extracted from the experimental echo waveforms. Experiments were made for different proportions of hardener and allowed a determination of the best mixture (10% of hardener) that corresponds to the manufacturer's recommended value. Analysis of the results shows a progressive hardening from the center of the resin toward the walls of the vessel.
