Neural network based multi-criteria optimization image reconstruction technique for imaging two- and three-phase flow systems using electrical capacitance tomography

A new image reconstruction technique for imaging two- and three-phase flows using electrical capacitance tomography (ECT) has been developed based on multi-criteria optimization using an analog neural network, hereafter referred to as Neural Network Multi-criteria Optimization Image Reconstruction (NN-MOIRT)). The reconstruction technique is a combination between multi-criteria optimization image reconstruction technique for linear tomography, and the so-called linear back projection (LBP) technique commonly used for capacitance tomography. The multi-criteria optimization image reconstruction problem is solved using Hopfield model dynamic neural-network computing. For three-component imaging, the single-step sigmoid function in the Hopfield networks is replaced by a double-step sigmoid function, allowing the neural computation to converge to three-distinct stable regions in the output space corresponding to the three components, enabling the differentiation among the single phases.

[1]  G. A. Johansen,et al.  The use of entropic thresholding methods in reconstruction of capacitance tomography data , 1997 .

[2]  Jan-Erik Nordtvedt,et al.  A new reconstruction algorithm for process tomography , 1993 .

[3]  Shigeo Uchida,et al.  A model for simultaneous measurement of gas and solid holdups in a bubble column using ultrasonic method , 1995 .

[4]  Yi Sun,et al.  Improvement on performance of modified Hopfield neural network for image restoration , 1995, IEEE Trans. Image Process..

[5]  Liang-Shih Fan,et al.  Some aspects of high-pressure phenomena of bubbles in liquids and liquid–solid suspensions , 1999 .

[6]  Steven L. Ceccio,et al.  Quantitative tomographic measurements of opaque multiphase flows , 2000 .

[7]  Tomasz Dyakowski,et al.  Application of capacitance tomography to gas-solid flows , 1997 .

[8]  Brian S. Hoyle,et al.  Electrical capacitance tomography for flow imaging: system model for development of image reconstruction algorithms and design of primary sensors , 1992 .

[9]  Marimuthu Palaniswami,et al.  Neural versus traditional approaches to the location of interacting hub facilities , 1996 .

[10]  Aggelos K. Katsaggelos,et al.  Image restoration using a modified Hopfield network , 1992, IEEE Trans. Image Process..

[11]  Dieter Mewes,et al.  Investigation of the two-phase flow in trickle-bed reactors using capacitance tomography , 1997 .

[12]  B. K. Jenkins,et al.  Image restoration using a neural network , 1988, IEEE Trans. Acoust. Speech Signal Process..

[13]  Richard A Williams,et al.  Simulation of the performance of electrical capacitance tomography for measurement of dense phase pneumatic conveying , 1997 .

[14]  A. Y. Nooralahiyan,et al.  Three-component tomographic flow imaging using artificial neural network reconstruction , 1997 .

[15]  Wuqiang Yang,et al.  Optimization of an iterative image reconstruction algorithm for electrical capacitance tomography , 1999 .

[16]  Yuanmei Wang.  Neural network approach to image reconstruction from projections , 1998 .

[17]  Leon Kaufman,et al.  A general algorithm for oblique image reconstruction , 1990, IEEE Computer Graphics and Applications.

[18]  Wuqiang Yang,et al.  Development of capacitance tomographic imaging systems for oil pipeline measurements , 1995 .

[19]  B. T. Hjertaker,et al.  A dual sensor flow imaging tomographic system , 1996 .

[20]  M. S. Beck.  Chapter 3 – Selection of sensing techniques , 1995 .

[21]  Maurice Beck,et al.  Tomographic imaging of two-component flow using capacitance sensors , 1989 .

[22]  J. S. Halow,et al.  Observations of fluidized bed coalescence using capacitance imaging , 1992 .

[23]  G. Herman,et al.  Algebraic reconstruction techniques (ART) for three-dimensional electron microscopy and x-ray photography. , 1970, Journal of theoretical biology.

[24]  Yao Liang,et al.  Combinatorial Optimization by Hopfield Networks Using Adjusting Neurons , 1996, Inf. Sci..

[25]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[26]  Shigeo Uchida,et al.  Flow structure and phase distributions in a slurry bubble column , 1997 .

[27]  Dieter Mewes,et al.  Recent developments and industrial/research applications of capacitance tomography , 1996 .

[28]  Supachai Bangliang,et al.  The use of simultaneous iterative reconstruction technique for electrical capacitance tomography , 2000 .

[29]  Tomasz Dyakowski,et al.  On-line monitoring of dense phase flow using real time dielectric imaging 1 The authors are members , 1999 .

[30]  Gabor T. Herman,et al.  Image Reconstruction From Projections , 1975, Real Time Imaging.

[31]  Tomasz Dyakowski,et al.  Real time capacitance imaging of bubble formation at the distributor of a fluidized bed , 1995 .

[32]  Wuqiang Yang,et al.  Development of capacitance tomographic imaging systems for oil pipeline measurements , 1995 .

[33]  Ø. Isaksen,et al.  A review of reconstruction techniques for capacitance tomography , 1996 .

[34]  Liang-Shih Fan,et al.  Gas-Liquid-Solid Fluidization Engineering , 1989 .

[35]  Wuqiang Yang,et al.  An image-reconstruction algorithm based on Landweber's iteration method for electrical-capacitance tomography , 1999 .

[36]  Richard A Williams,et al.  Process tomography: a European innovation and its applications , 1996 .

[37]  Shigeo Uchida,et al.  Cross-sectional distributions of gas and solid holdups in slurry bubble column investigated by ultrasonic computed tomography , 1999 .

[38]  Yuanmei Wang,et al.  Multicriteria neural network approach to turbulent image reconstruction , 1997 .

[39]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.