.png){kind=icon}
.png){kind=icon}
Return
An ECT image reconstruction method for the tiny tube based on encoder–decoder network
.png){kind=icon}
PRE
AI
DOI：10.1088/1361-6501/ae5d58.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Gas–liquid two-phase flow detection in tiny tubes holds significant importance for chemical engineering and aerospace applications. Electrical capacitance tomography (ECT) has emerged as a prominent technique for multiphase flow measurement due to its non-invasive nature, cost-effectiveness, and structural simplicity. However, due to the size of the tiny tube, fewer electrodes can be used for measurement, conventional ECT imaging algorithms often suffer from limited accuracy. To overcome these challenges, this study develops a 6-electrode ECT simulation model specifically designed for the tiny tube and introduces a novel reconstruction network based on DeepLabv3 for gas–liquid two-phase flow imaging. To achieve high-speed, high-accuracy ECT imaging, this work utilizes compression strategies for the conv4_x blocks of the ResNet101. Imaging speed, relative error and correlation coefficient are evaluated for different backbone layers. By conducting, the proposed algorithm achieves high-speed reconstruction at 20 frames per second (fps) with a relative error of 13.71% on the test dataset. To validate the method’s effectiveness, a dedicated gas–liquid two-phase flow experimental platform was constructed, incorporating an ECT measurement system. Comprehensive experiments were conducted under various operational conditions. Dynamic experimental results demonstrate the method’s feasibility in characterizing gas–liquid two-phase flow parameters in tiny tubes, offering a robust solution for industrial applications.
Keywords:
ECT imaging
gas–liquid two-phase flow
tiny tube
DeepLabv3
image reconstruction
Journal
IF:
3.4
Papers:
2.6K
Citations:
2.3W