Title :
Image reconstruction algorithm for electrical capacitance tomography based on radial basis function neural network
Author :
Zhang, Li-Feng ; Wang, Hua-Xiang ; Ma, Min ; Jin, Xiu-zhang
Author_Institution :
Sch. of Control Sci. & Eng., North China Electr. Power Univ., Baoding, China
Abstract :
Electrical capacitance tomography (ECT) technique is a new technique for two-phase flow measurement. This paper describes the basic principles of ECT. Forward and inverse problem of ECT are analyzed in detail. The conventional image reconstruction algorithm, i.e., linear back projection algorithm has been given. Then, the new image reconstruction algorithm for ECT based on radial basis function (RBF) neural network has been presented. Using the measurement data obtained from the ECT simulation software developed by the author, the reconstructed images were obtained. Results indicate that RBF neural network is suitable for solving the nonlinear problem of ECT image reconstruction. Comparing with linear back projection algorithm, this algorithm has advantages of higher accuracy.
Keywords :
capacitance measurement; capacitive sensors; flow visualisation; image reconstruction; radial basis function networks; tomography; two-phase flow; electrical capacitance tomography; forward problem; image reconstruction; inverse problem; linear back projection algorithm; nonlinear problem; radial basis function neural network; two-phase flow measurement; Capacitance measurement; Electric variables measurement; Electrical capacitance tomography; Fluid flow measurement; Image reconstruction; Inverse problems; Neural networks; Projection algorithms; Radial basis function networks; Software measurement; Electrical capacitance tomography; RBF neural network; image reconstruction; two-phase flow;
Conference_Titel :
Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on
Conference_Location :
Guangzhou, China
Print_ISBN :
0-7803-9091-1
DOI :
10.1109/ICMLC.2005.1527664
