Title: Development of an artificial neural network model for estimating the radius ratio of a one-layered cylindrical shell
Authors: Khandouch, Younes
Aassif, El Houcein
Agounad, Said
Maze, Gérard
Citation: Applied and Computational Mechanics. 2020, vol. 14, no. 2, p. 163-178.
Issue Date: 2020
Publisher: University of West Bohemia
Document type: article
článek
URI: http://hdl.handle.net/11025/42435
ISSN: 1802-680X (Print)
2336-1182 (Online)
Keywords: válcová skořepina;poměr poloměru;obvodové vlny;snížené mezní frekvence;modální izolační plán;umělé neuronové sítě
Keywords in different language: cylindrical shell;radius ratio;circumferential waves;reduced cutoff frequencies;modal isolation plan;artificial neural networks
Abstract in different language: 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.
Rights: © University of West Bohemia
Appears in Collections:Volume 14, Number 2 (2020)
Volume 14, Number 2 (2020)

Files in This Item:
File Description SizeFormat 
533-3875-1-PB.pdfPlný text1,78 MBAdobe PDFView/Open


Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/42435

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.