Study On Image Reconstruction Algorithm For Electrical Capacitance Tomography System

Electrical capacitance tomography (ECT) is a kind of process tomographytechnology. It grows rapidly as an important field of the process tomography inrecent years.The visual information in the pipeline can be obtained by using ECTtechnology through the working principle of the capacitance measurement.Because of its advantages such as security, non intrusive, low cost, electricalcapacitance tomography has a wide application.Currently, there are still manytechnical difficulties to break through, so it has important significance andapplication value to carry out the relevant theory and technology research. In thisthesis, the research object is the ECT system of12-electrode and the imagereconstruction algorithm.By deeply studying different image reconstructionalgorithms, image fusion can be used to improve the quality of the imagereconstruction.In order to remedy the deficiency of the existing algorithm, thethesis proposes image reconstruction algorithm based on deep learning.The mainresearch contents in this thesis are as follows:Firstly, based on the research background, the significance of the researchtopic is discussed, and the research status of electrical capacitance tomographyand deep learning are also studied in this thesis.Secondly, this thesis analyses the composition of electrical capacitancetomography system, establish the mathematical model of ECT system andderivation ECT image reconstruction.ECT simulation system is established byusing Matlab, research on ECT image reconstruction algorithm in common use,through the simulation system for ECT image reconstruction of differentalgorithms, comparative analysis of advantages and disadvantages of differentalgorithms.Thirdly, combining the characteristics of ECT image reconstruction, by using wavelet technique, fusion the high and low frequency with different fusionrules of different reconstruction of image fusion,then experimental andsimulation, comparative analysis.Finally, use deep learning network combined with solving the inverseproblem of ECT process, put forward the ECT image reconstruction algorithmbased on the deep learning network, through experiments to demonstrate theeffectiveness of the algorithm, by compared with the traditional algorithm, theimaging quality by reconstructed by deep learning network is higher.