Abstract：In order to solve the nonlinear ill-posed inverse problem of electrical capacitance tomography (ECT), a multi-scale adaptation network (MSANet) model is proposed, which achieves the fusion of multi-scale features in a more fine-grained dimension and has a relatively small number of model parameters.By constructing a tree structure within a single residual block to form a multi-scale feature fusion module, MSANet achieves more robustness and lower computational parameters. Furthermore,by adding an adaptive spatial threshold module, the reconstruction accuracy of the images is further improved. Compared with linear back projection (LBP) algorithm, Landweber iterative algorithm,and commonly used deep learning methods, this method has the smallest average relative error and the largest average correlation coefficient,with 0.181 and 0.967, respectively.
XU Y, PEI Y and DONG F. An adaptive Tikhonov regularization parameter choice method for electrical resistance tomography［J］. Flow Meas Instrum , 2016 , 50: 1-12.
［4］
GAMIO J C, ORTIZ-ALEMAN C, MARTIN R. Electrical capacitance tomography two-phase oil-gas pipe flow imaging by the linear back-projection algorithm ［J］. Geofísica Internacional, 2010, 44(3): 165-273.
［11］
YANG X, ZHAO C, LI Y, et al. Big data driven U-Net based electrical capacitance image reconstruction algorithm ［C］//2019 IEEE International Conference on Imaging Systems and Techniques(IST). Abu Dhabi, UAE, 2019.
YAN C M, MU Z, ZHANG D L, et al. ECT image reconstruction based on improved Landweber algorithm ［J］. Chinese Journal of Sensors and Actuators, 2019, 32(10): 1522-1526.
［9］
ZHENG J and PENG L H. A deep learning compensated back projection for image reconstruction of electrical capacitance tomography［J］. IEEE Sensors Journal, 2020, 20(9): 4879-4890.
［15］
YANG W Q. Hardware design of electrical capacitance tomography systems ［J］. Meas Sci Technol, 1996, 7(3): 225-232.
MA M, GUO X. Research on ECT image reconstruction based on improved SR3 model algorithm ［J］. Acta Metrologica Sinica, 2023, 44(1): 95-102.
ZHANG L F, ZHANG M. An optimized algorithm for image reconstruction of electrical capacitance tomography ［J］. Acta Metrologica Sinica,2021, 42(9): 1155-1159.
MA M, SUN Y, FAN G Y. ECT image reconstruction algorithm based on depth belief network ［J］. Acta Metrologica Sinica, 2021, 42(4): 476-482.
［13］
ZHU H, SUN J, LONG J, et al. Deep image refinement method by hybrid training with images of varied quality in electrical capacitance tomography ［J］. IEEE Sensors Journal, 2021, 21(5): 6342-6355.
［1］
ZHU L, JIANG Y, Li Y, et al. Conductivity prediction and image reconstruction of complex-valued multi-frequency electrical capacitance tomography based on deep neural network ［J］. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-10.
ZHANG L F, DAI L. Image reconstruction of electrical capacitance tomography based on robust regularization limit learning machine ［J］. Acta Metrologica Sinica, 2022, 43(8): 1044-1049.
［8］
WAMG Z, ZHANG L F, ZHANG B X, et al. Image reconstruction based on multilevel densely connected network with threshold for electrical capacitance tomography［J］. IEEE Sensors Journal, 2022, 22(22): 21996-22007.
［12］
LI F, TAN C, DONG F, et al. V-Net deep imaging method for electrical resistance tomography［J］.IEEE Sensors Journal,2020, 20(12): 6460-6469.
［14］
FU R, WANG Z, ZHANG X, et al. A regularization-guided deep imaging method for electrical impedance tomography［J］. IEEE Sensors Journal, 2022, 22(9): 8760-8771.
［16］
ZHU H, SUN J, XU L, et al. Permittivity reconstruction in electrical capacitance tomography based on visual representation of deep neural network ［J］. IEEE Sensors Journal, 2020, 20(9): 4803-4815.
［17］
WANG S, XU C, LI J, et al. An instrumentation system for multi-parameter measurements of gas-solid two-phase flow based on capacitance-electrostatic sensor［J］. Measurement, 2016, 94: 812-827.
2024, Vol. 45 
