Neural network approach to ECT inverse problem solving for estimation of gravitational solids flow

Author

Garbaa, Hela ; Jackowska-Strumillo, Lidia ; Grudzien, Krzysztof ; Romanowski, Andrzej

Author_Institution

Inst. of Appl. Comput. Sci., Lodz Univ. of Technol., Lodz, Poland

fYear

2014

fDate

7-10 Sept. 2014

Firstpage

19

Lastpage

26

Abstract

A new method to solve the inverse problem of electrical capacitance tomography is proposed. Our method is based on artificial neural network to estimate the radius of an object present inside a pipeline. This information is useful to predict the distribution of material inside the pipe. The capacitance data used to train and test the neural network is simulated on Matlab using the electrical capacitance tomography toolkit ECTsim. The provided accuracy is promising and shows efficiency to solve the inverse problem in a simple manner and on reduced computational time about 120 times when compared to the existing Landweber iterative algorithm for tomographic image reconstruction that can be encouraging for dynamic industrial applications.

Keywords

image reconstruction; inverse problems; learning (artificial intelligence); mathematics computing; neural nets; production engineering computing; tomography; ECT inverse problem solving; ECTsim; Landweber iterative algorithm; Matlab; artificial neural network; dynamic industrial applications; electrical capacitance tomography toolkit; gravitational solids flow estimation; neural network approach; object radius estimation; pipeline; tomographic image reconstruction; Capacitance; Capacitance measurement; Image reconstruction; Inverse problems; Neurons; Permittivity; Sensors; Artificial Neural Networks; Electrical Capacitance Tomography; Gravitational Flow of Solids; Inverse Problem;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science and Information Systems (FedCSIS), 2014 Federated Conference on

Conference_Location

Warsaw

Type

conf

DOI

10.15439/2014F368

Filename

6932992