Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method for imaging incomplete measurement data for electrical capacitance tomography

A technology of electrical capacitance tomography and measurement data, which is applied in the direction of material capacitance, etc., can solve the problems of imaging results, lack of effective measurement values, affecting the industrial promotion and application of ECT systems, etc., and achieve the effect of enhancing stability

Inactive Publication Date: 2021-06-25
TIANJIN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Missing valid measurements can have a serious impact on imaging results
However, the current ECT system design does not consider the failure of some faulty electrodes, wiring and measurement circuits, which will affect the reliability and robustness of the ECT system, and affect the industrial promotion and application of the ECT system

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for imaging incomplete measurement data for electrical capacitance tomography
  • A method for imaging incomplete measurement data for electrical capacitance tomography
  • A method for imaging incomplete measurement data for electrical capacitance tomography

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023]

[0024] Table 1 variable definition

[0025] The measured values ​​are all measured values ​​obtained by normalizing the measured values ​​of the space-time field and the full field after calibration:

[0026] C=(C x -C l ). / (C h -C l )

[0027] where C x is the actual measured absolute capacitance measurement value, C l Absolute capacitance measurement when calibrated for empty field, C h Absolute capacitance measurements when calibrated for full field.

[0028] figure 1 Shown is a schematic flow chart of the method for imaging incomplete measurement values ​​of the present invention. Using incomplete measurement values, the method steps to realize image reconstruction include: (1) solving the approximate value of the complete measurement data through the ECT sensitivity matrix, (2) solving the approximate value of the complete measurement data through the least square support vector machine (Least Square Support Vector Machine, LS-SVM) regression model (...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

PropertyMeasurementUnit
diameteraaaaaaaaaa
thicknessaaaaaaaaaa
lengthaaaaaaaaaa
Login to View More

Abstract

The invention relates to an electrical capacitance tomography method using incomplete measurement data, comprising the following steps: under normal conditions, the measurement channel of the ECT system acquires measurement data for training a regression model; In the measurement data of the training regression model, the measurement value corresponding to the faulty channel is set to 0; the measurement data used to train the regression model after being set to 0 is used to solve the inverse problem and the direct problem through the sensitivity matrix, and the approximate recovery value of the complete measurement data is obtained. Training samples; clustering of training samples to obtain labeled training samples; use LS-SVM of radial basis kernel function to establish regression model; obtain test samples of regression model; step 7: use RF algorithm to classify test samples; Component minimization algorithm for imaging.

Description

technical field [0001] The invention relates to a process imaging device, in particular to an imaging method for incomplete measurement data of an electrical capacitance tomography imaging system. Background technique [0002] The Electrical Capacitance Tomography (ECT) system relies on the array electrodes arranged on the boundary of the measured field to obtain a series of capacitance measurements, and uses the relationship between the capacitance measurements and the distribution of the medium in the measured field to perform image analysis. Reconstruct to obtain the medium distribution image in the measured field. Sensors are the source of information for the ECT system. Usually, the number of electrodes of ECT sensor is 8, 12 or 16 electrode sections, and can form a multi-section sensor. An ECT sensor composed of n electrodes can obtain m=n·(n-1) independent measurement values ​​through measurement. [0003] In terms of hardware structure, the ECT front-end circuit i...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G01N27/22
CPCG01N27/22
Inventor 崔自强夏子涵
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com