Image reconstruction algorithm based on algebraic neural network for electrical resistance tomography

Zhang Yanjun*, Wang Lili, Zhou Jing, Chen Deyun

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)

Abstract

Two-phase fluid has complex flow characteristic and the accurate identification of flow regime is the basis of the accurate measurement of two-phase flow's parameter. There are still many defects such as low reconstruction quality and low reconstruction speed in image reconstruction algorithm because of soft field characteristic, strong nonlinear and ill-posedness of electrical resistance tomography. This paper put forward a new image reconstruction algorithm for ERT based on algebraic neural network. This algorithm transformed image reconstruction into a problem of solving strictly diagonal-dominant linear equations. Through the simulation experiment analysis, this method has characteristics such as fast convergence, low cost and small error.

Original languageEnglish
Title of host publicationProceedings - 2009 IITA International Conference on Control, Automation and Systems Engineering, CASE 2009
Pages242-245
Number of pages4
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event2009 IITA International Conference on Control, Automation and Systems Engineering, CASE 2009 - Zhangjiajie, China
Duration: 11 Jul 200912 Jul 2009

Publication series

NameProceedings - 2009 IITA International Conference on Control, Automation and Systems Engineering, CASE 2009

Conference

Conference2009 IITA International Conference on Control, Automation and Systems Engineering, CASE 2009
Country/TerritoryChina
CityZhangjiajie
Period11/07/0912/07/09

Keywords

  • Algebraic neural network
  • Electrical resistance tomography
  • Image reconstruction algorithm
  • Two phase flow

Fingerprint

Dive into the research topics of 'Image reconstruction algorithm based on algebraic neural network for electrical resistance tomography'. Together they form a unique fingerprint.

Cite this