Phase boundary estimation in electrical resistance tomography with weighted multilayer neural networks

Author

Kim, Jae Hyoung ; Kang, Byoung Chae ; Choi, Bong Yeol ; Kim, Min Chan ; Kim, Sin ; Kim, Kyung Youn

Author_Institution

Dept. of Electron. Eng., Kyungpook Nat. Univ., Daegu

Volume

42

Issue

4

fYear

2006

fDate

4/1/2006 12:00:00 AM

Firstpage

1191

Lastpage

1194

Abstract

This work presents a boundary estimation approach in electrical resistance imaging for binary mixture fields based on weighted multilayer neural network. The interfacial boundaries are expressed with the truncated Fourier series and the unknown Fourier coefficients are estimated with the weighted multilayer neural network. In doing so, normalized boundary voltages are used for training the neural network and the results from real experiments show that the proposed approach has strong possibility for real-time monitoring of binary mixtures

Keywords

Fourier series; electric impedance imaging; estimation theory; magnetic multilayers; neural nets; tomography; binary mixture fields; electrical resistance imaging; electrical resistance tomography; interfacial boundaries; normalized boundary voltages; phase boundary estimation; truncated Fourier series; unknown Fourier coefficients; weighted multilayer neural networks; Electric resistance; Fourier series; Intelligent networks; Multi-layer neural network; Neural networks; Phase estimation; Pollution measurement; Power engineering and energy; Tomography; Voltage; Binary mixtures; boundary estimation; electrical resistance tomography; multilayer neural network;

fLanguage

English

Journal_Title

Magnetics, IEEE Transactions on

Publisher

ieee

ISSN

0018-9464

Type

jour

DOI

10.1109/TMAG.2006.871671

Filename

1608425