ECT image reconstruction method based on deconvolution network

A deconvolution network and image reconstruction technology, applied in image generation, image data processing, neural learning methods, etc., can solve the problems of incomplete sensitive field experience information, difficult to deal with complex sensitive field changes, etc., and achieve high-precision images. Reconstruction and increase the effect of spatial feature extraction

Pending Publication Date: 2020-07-28
XIAN UNIV OF SCI & TECH
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The empirical information of the sensitive field detected by the traditional ECT image reconst

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
  • ECT image reconstruction method based on deconvolution network
  • ECT image reconstruction method based on deconvolution network
  • ECT image reconstruction method based on deconvolution network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0038] Example one

[0039] Such as figure 1 Said, an ECT image reconstruction method based on a deconvolution network, is characterized in that it comprises the following steps:

[0040] S1, the mathematical model of ECT image reconstruction is established through the deconvolution network solving formula;

[0041] S2. Randomly generate geometric parameters to build a geometric model, make label data and training data;

[0042] S3. Build a deconvolution network model;

[0043] S4. Use the built deconvolution network model for training.

[0044] S5. Use a deconvolution network to realize ECT image reconstruction.

[0045] For the ECT problem, the shallow fully connected network has insufficient feature extraction capabilities and weak nonlinear fitting capabilities; the deep fully connected network has too many parameters, and the training period is time-consuming and inefficient. Therefore, the present invention proposes a deconvolution network solution formula. Unlike the fully connect...

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
The inside diameter ofaaaaaaaaaa
Outer diameteraaaaaaaaaa
Login to view more

Abstract

The invention relates to the field of motion rules of two-phase flow, in particular to an ECT image reconstruction method based on a deconvolution network. The method comprises the following steps: S1, establishing a mathematical model for ECT image reconstruction through a deconvolution network solution formula; S2, randomly generating geometric parameters to build a geometric model, and manufacturing label data and training data; S3, building a deconvolution network model; S4, training by using the built deconvolution network model; and S5, realizing ECT image reconstruction by using a deconvolution network. According to the invention, the deconvolution network is used to extract the truly distributed spatial features, the feature extraction capability is enhanced, and for a local application scene, high-precision image reconstruction can be realized without sensitive field priori. The quality of the image is better than that of the prior art, the 2D image of the pipeline section canbe dynamically presented, and monitoring personnel can conveniently analyze the motion law of the two-phase fluid.

Description

technical field [0001] The invention relates to the field of motion laws of two-phase flow, in particular to an ECT image reconstruction method based on a deconvolution network. Background technique [0002] In the two-phase flow pipeline transportation process, the detection of fluid motion parameters is of great significance for improving production efficiency and ensuring production safety. However, due to the complex force between the phases and the large changes in the physical properties of the phase surface, it is difficult to detect the motion mechanism and state of the two-phase flow through traditional means. In addition, pipe plugging and scaling on the pipe wall are unavoidable during the transportation process, which will increase the energy consumption of the pipeline and affect the safe operation of the pipeline. The pipeline is often a closed environment, so the visual observation technology for closed pipelines also needs to be solved urgently. [0003] In ...

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
IPC IPC(8): G06T11/00G06N3/04G06N3/08
CPCG06T11/006G06N3/084G06T2211/424G06N3/045
Inventor 秦学斌纪晨晨王卓李明桥申昱瞳刘浪王湃张波王美赵玉娇
Owner XIAN UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap