Please use this identifier to cite or link to this item: https://er.chdtu.edu.ua/handle/ChSTU/4874
Title: Surrogate methods for determining profiles of material properties of planar test objects with accumulation of apriori information about them
Authors: Halchenko, Volodymyr
Trembovetska, Ruslana
Tychkov, Volodymyr
Tychkova, Natalіia
Гальченко, Володимир Якович
Трембовецька, Руслана Володимирівна
Тичков, Володимир Володимирович
Тичкова, Наталія Борисівна
Keywords: accumulation of apriori information;electrical conductivity and magnetic permeability profiles;neural network metamodel;structuroscopy;surface eddy-current probe;surrogate optimization
Issue Date: 2024
Publisher: Archives of Electrical Engineering
Abstract: New methods for identifying the material properties of planar objects as a result of measurements by the eddy current method are proposed. The methods are based on the latest surrogate strategies and advanced optimization techniques that improve efficiency and reduce resource consumption of problem solutions, and balance computational complexity with the accuracy of the results. High-performance metamodels for global surrogate optimization are based on deep truly meaningful fully connected neural networks, serving as an additional function of accumulating apriori information about objects. High accuracy of the approximation of the multidimensional response surface, which is determined by the “exact” electrodynamic model of the testing process, is ensured by performing calculations according to the computer design of a homogeneous experiment with a low weighted symmetric centered discrepancy. The results of numerical experiments performed for full and reduced dimensional search spaces, which can be obtained by linear transformations using the principal component method, are presented. The verification of the methods proved their sufficiently high accuracy and computational performance.
URI: https://er.chdtu.edu.ua/handle/ChSTU/4874
ISSN: 1427-4221 (print)
2300-2506 (online)
DOI: 10.24425/aee.2024.148864
Volume: 73
Issue: 1
First Page: 183
End Page: 200
Appears in Collections:Наукові публікації викладачів (ФЕТР)

Files in This Item:
File Description SizeFormat 
12_int.pdf3.04 MBAdobe PDFThumbnail
View/Open


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