Evaluation of methods for on-line image analysis of electrical impedance tomography images

被引：4

作者：

Gutierrez Gnecchi, Jose Antonio ^{[1
]}

Marroquin Pineda, Edith ^{[1
]}

机构：

[1] Inst Technol Morelia, Dept Ingn Elect, Morelia, Michoacan, Mexico

来源：

CERMA 2007: ELECTRONICS, ROBOTICS AND AUTOMOTIVE MECHANICS CONFERENCE, PROCEEDINGS | 2007年

关键词：

D O I：

10.1109/CERMA.2007.4367700

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper describes the manner in which EIT (Electrical Impedance Tomography) was used to online estimate separation efficiency in solid/liquid separators. Although off-line image analysis can be used to determine the characteristics of the internal flow, it is necessary to develop a technique for on-line control of the separation process. Three different methods were evaluated to determine a suitable strategy for on-line image analysis of electrical impedance tomography data: (i) Use of back-propagation artificial neural networks (ANN), (ii) air core scaling and (iii) use of radial basis functions and detection of abrupt changes. One case study is presented: A 44 mm internal-body diameter hydrocyclone pilot-scale plant.

引用

页码：283 / 288

页数：6