Intelligent identification and measurement method for defects of anti-corrosion layer

A technology of intelligent recognition and measurement method, applied in character and pattern recognition, optical testing flaws/defects, image data processing, etc. The effect of reliable defect identification and measurement, improved accuracy and improved work efficiency

Pending Publication Date: 2022-04-08
SUZHOU NUCLEAR POWER RES INST +2
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, in order to overcome the defects of the prior art, the purpose of the present invention is to provide a method based on modern computer image recognition technology for intelligent identification and measurement of anti-corrosion coating defects on the surface of pipeline equipment, which is used to solve the problems in the prior art. Due to human factors, the identification errors of anti-corrosion layer defects, large manual measurement errors and low work efficiency, as well as the poor image quality obtained by existing traditional cameras, and the poor image processing ability lead to the problem that the defects with small differences cannot be effectively distinguished

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
  • Intelligent identification and measurement method for defects of anti-corrosion layer
  • Intelligent identification and measurement method for defects of anti-corrosion layer
  • Intelligent identification and measurement method for defects of anti-corrosion layer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Embodiment 1 Coating Bubble Defect

[0045] Such as Figure 4 to Figure 6 As shown, this embodiment provides a method for intelligent identification and measurement of the anti-corrosion layer of the coating bubbling defect.

[0046] Firstly, the image acquisition of the defects of coating bubbles is carried out, and the following results are obtained: Figure 4 and Figure 6 The first original image in , and then grayscale processing is performed on the image to grayscale the coating image, so that the outline of the typical defect bubbles of the coating can be displayed. Then, according to the actual scale marked by the laser radar rangefinder, the number, size and density of the bubbles are automatically measured, and corresponding data reports are generated. According to the generated data report and grayscale image, compare it with the rating of coating defects in "GBT 30789.2-2014 Part 2: Evaluation of Blistering Grade", according to the standard evaluation pri...

Embodiment 2

[0048] Example 2 Coating Rusting Defects

[0049] Such as Figure 7 and Figure 8 As shown, this embodiment provides a method for intelligent identification and measurement of the anti-corrosion layer of coating rust defects.

[0050] Firstly, the image acquisition of the coating rust defect is obtained as follows: Figure 7 The first original image in the image, and then grayscale processing is performed on the image to remove the excess impurities other than rust on the surface of the coating rust defect image, and the rust on the coating surface is displayed in a more obvious dark color Then display the area of ​​rusty features by means of color scale contrast enhancement, and extract rusty features; and generate basic parameters such as the number, density and area of ​​rusty spots; generate corresponding data reports; according to the generated The data report and grayscale image are compared with the rating of coating defects in "GBT 30789.3-2014 Part 3: Evaluation of...

Embodiment 3

[0051] Example 3 Coating Cracking Defects

[0052] Such as Figure 9 and Figure 10 As shown, this embodiment provides a method for intelligent identification and measurement of anti-corrosion coating cracking defects.

[0053] Firstly, the image acquisition of the coating crack defect is obtained as follows: Figure 9 The first original image in the image, and then grayscale processing is performed on the image to clean up the dirty spots on the surface of the coating crack defect image, so that the image color is only the cracked crack color and the surface color of the coating, and then through The method of enhancing the contrast of the color scale makes the crack features more vividly displayed and extracts the crack features. And generate the corresponding data report; according to the generated data report and grayscale image, compare it with the coating defect rating in "GBT 30789.4-2014 Part 4: Evaluation of Cracking Grade", and automatically give the rating accord...

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

No PUM Login to view more

Abstract

The invention discloses an intelligent identification and measurement method for defects of an anti-corrosion layer. The method comprises the following steps: step 1, carrying out image acquisition on a defect area generated by the anti-corrosion layer; 2, sequentially performing contrast enhancement, filtering processing, threshold segmentation, morphological processing, feature extraction and classification and defect information collection on the acquired image; and step 3, generating a feature code from the processed image, comparing the feature code with the anticorrosive coating defect database, evaluating the defect level and generating a defect evaluation report. According to the anti-corrosion layer defect intelligent identification and measurement method, the image of the anti-corrosion layer defect is subjected to feature extraction and conversion through a computer image identification technology, and the position and the category attribute of the defect are identified. A traditional manual visual recognition and measurement mode is replaced, the conditions of corrosion-resistant layer defect recognition errors and large manual measurement errors caused by human factors are effectively avoided, and the accuracy of corrosion inspection of the corrosion-resistant layer defects is improved.

Description

technical field [0001] The invention belongs to the technical field of anti-corrosion layer defect evaluation of metal equipment and pipelines in nuclear power plants, and in particular relates to an intelligent identification and measurement method for anti-corrosion layer defects. Background technique [0002] At present, in the field of nuclear power, the method of evaluating the defects of the anti-corrosion coating of metal equipment and pipelines still adopts the traditional manual visual inspection and evaluation method. There are various types and complex presentation forms, so it is difficult for corrosion inspectors to identify specific defect types. Not only that, the naked eye observation will also cause subtle defects to be difficult to find due to visual errors, such as pitting micropores, micro-dotted bubbling and filamentary cracks. In defect measurement, traditional measuring tools are used, and it is difficult to guarantee the measurement accuracy required...

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 Applications(China)
IPC IPC(8): G06T7/00G06T7/11G06T7/136G06T7/155G06T7/187G06T5/00G06T5/10G06T5/40G06F3/0481G06V10/764G06K9/62G01N21/88
Inventor 刘洪群张彦召刘忠张舟永潘姚凡
Owner SUZHOU NUCLEAR POWER RES INST
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