Image Reconstruction Based on Multilevel Densely Connected Network with Threshold for Electrical Capacitance Tomography

Electrical capacitance tomography (ECT) is a real-time monitoring technology for the visualization of industrial dynamic processes. Due to the inherent nonlinearity and ill-posed nature of the ECT inverse problem, achieving fast and accurate image reconstruction remains a great challenge. A novel mu...

Full description

Saved in:
Bibliographic Details
Published in:IEEE sensors journal 2022-11, Vol.22 (22), p.1-1
Main Authors: Wang, Zhi, Zhang, Lifeng, Zhang, Boxiong, Zhao, Jianhai, Wu, Sicheng
Format: Article
Language:English
Subjects:
Algorithms
Capacitance
channel-wise threshold
Data models
Deep learning
dense connection
electrical capacitance tomography
Electrodes
Image reconstruction
Imaging
Information transfer
Inverse problems
Iterative algorithms
Iterative methods
Machine learning
Nonlinearity
Permittivity
Sensors
Thresholds
Tomography
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Electrical capacitance tomography (ECT) is a real-time monitoring technology for the visualization of industrial dynamic processes. Due to the inherent nonlinearity and ill-posed nature of the ECT inverse problem, achieving fast and accurate image reconstruction remains a great challenge. A novel multilevel densely connected network with channel-wise thresholds (MDCN-CW) is proposed, which adopts a deep learning framework to implement a reconstruction process similar to iterative algorithms. MDCN-CW is a highly condensed framework that achieves efficient information transfer through dense connections between and within sub-networks, and soft thresholding is inserted into the sub-network as a nonlinear transformation layer to eliminate unimportant features. Matching the purpose and structure of MDCN-CW, a phased strategy is used to train it. Each sub-network is first trained with a stepwise individual strategy, and network parameters are fine-tuned after all sub-networks are integrated to improve the overall fit of the model. Simulation and experimental results show that, compared with existing deep learning-based reconstruction methods and traditional algorithms, the proposed ECT image reconstruction network with soft thresholds has the advantages of simple structure, high imaging accuracy, and good generalization ability.
ISSN:1530-437X
1558-1748
DOI:10.1109/JSEN.2022.3211708