Electrical Capacitance Tomography Using Incomplete Measurement Set

In the electrical capacitance tomography (ECT) systems, the electrodes, and cables may fail to function properly, which will cause several measurements missing. In these cases, image reconstruction can only use the remaining effective measurements. In order to make the reconstructed images close to the image results of the complete measurement set, it is necessary to use the incomplete measurements reasonably. The measurement/data recovery method and image reconstruction can be conducted to obtain the results, which meet the imaging needs under these circumstances. The measurement/data recovery method by using the sensitivity matrix and the regression model of least square support vector machine (LS-SVM) are proposed. The image recovery result is reconstructed by the method of total variation (TV) minimization. The simulations and experiments of gas–solids two-phase measurement are conducted to validate the method.

[1]  P. Roth.  MISSING DATA: A CONCEPTUAL REVIEW FOR APPLIED PSYCHOLOGISTS , 1994 .

[2]  Jan Porzuczek,et al.  APPLICATIONS OF ELECTRICAL CAPACITANCE TOMOGRAPHY FOR RESEARCH ON PHENOMENA OCCURRING IN THE FLUIDISED BED REACTORS , 2014 .

[3]  Haifeng Wang,et al.  Comparison of SVM and LS-SVM for Regression , 2005, 2005 International Conference on Neural Networks and Brain.

[4]  Masahiro Takei,et al.  Application of Process Tomography to Multiphase Flow Measurement in Industrial and Biomedical Fields: A Review , 2017, IEEE Sensors Journal.

[5]  Arun S. Mujumdar,et al.  Measurement Techniques to Monitor and Control Fluidization Quality in Fluidized Bed Dryers: A Review , 2014 .

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

[7]  Y. Ju,et al.  Direct Measurements of Permittivity of Plasma-Assisted Combustion Using Electrical Capacitance Tomography , 2016, IEEE Transactions on Plasma Science.

[8]  Amparo Alonso-Betanzos,et al.  Recovering Missing Data with Functional and Bayesian Networks , 2003, IWANN.

[9]  Jungah Son,et al.  Gap compensation during PET image reconstruction by constrained, total variation minimization. , 2012, Medical physics.

[10]  V. Mosorov.  Flow Pattern Tracing for Mass Flow Rate Measurement in Pneumatic Conveying Using Twin Plane Electrical Capacitance Tomography , 2008 .

[11]  Liang-Shih Fan,et al.  Bed nonhomogeneity in turbulent gas‐solid fluidization , 2003 .

[12]  Jing Liu,et al.  Flame Detection on Swirl Burner Using ECT With Dynamic Reconstruction Algorithm Based on the Split Bregman Iteration , 2017, IEEE Sensors Journal.

[13]  Huaxiang Wang,et al.  A review on image reconstruction algorithms for electrical capacitance/resistance tomography , 2016 .

[14]  Wuqiang Yang,et al.  Online monitoring and flow regime identification of fluidised bed drying and granulation processes , 2009, 2009 IEEE International Workshop on Imaging Systems and Techniques.

[15]  Madhavan Swaminathan,et al.  Machine Learning and Uncertainty Quantification for Surrogate Models of Integrated Devices With a Large Number of Parameters , 2019, IEEE Access.

[16]  A. Raheja,et al.  Multiresolution expectation maximization reconstruction algorithm for positron emission tomography using wavelet processing , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[17]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[18]  Haim Kalman,et al.  Flow regime diagram for vertical pneumatic conveying and fluidized bed systems , 2011 .