Method and system for scanning and warehousing of pipeline weld film and weld defect identification
A technology of defect recognition and film, applied in character and pattern recognition, optical test flaws/defects, image enhancement, etc., can solve problems such as finding weld defects with big data pattern recognition technology
Active Publication Date: 2019-06-07
GUANGDONG DAPENG LNG COMPANY
View PDF12 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The inventive idea of the present invention is to provide a large data-based method for scanning and warehousing of pipeline weld film negatives and defect identification, aiming at the inability to find weld defects and identify specific defects through big data pattern recognition technology in the prior art. The method includes the steps of:
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0049] attached figure 1 For the engineering background work flow diagram implemented according to the embodiment of the present invention, according to the availability of weld radiographs, this project is divided into two parts and carried out respectively: (1) the part where the pipeline weld radiographs can be found; (2) without Portion of a radiograph of a weld seam. According to attached figure 1 The main workflow includes: 1) Digitization of weld film: Use the special digital system for industrial radiography inspection industrial film: MII-900plus or high-intensity film viewer to digitize the radiograph and convert it into a single file of 330mm. Required color depth: 8bit / 16bit grayscale (256 grayscales / 65536 grayscales); optical resolution: preset 300 dots per inch (300dpi), the maximum should be 2400dpi; the blackness of weld scanning should be above 2.5, the maximum blackness The degree can reach 4.7. 2) Establish the weld film database and put it into the wareho...
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
| Property | Measurement | Unit |
|---|---|---|
| diameter | aaaaa | aaaaa |
| length | aaaaa | aaaaa |
| width | aaaaa | aaaaa |
Login to View More
Abstract
The present invention provides a large data-based scanning and warehousing of pipeline weld film and a method for identifying weld defects, comprising the steps of: (1) scanning the target pipeline weld film, and scanning and warehousing the weld film; (2) Establish a weld map database; (3) Establish a pattern recognition model for large data images of welds, analyze and determine the risks of weld slag inclusions, incomplete fusion, and incomplete penetration in the negative film information images, and find out the risks that may exist in the radiographic film (4) Carry out big data image recognition and analysis of welds, and issue a report; (5) Screen the report, and put forward hidden dangers and risk points. It also provides the corresponding big data-based pipeline weld scanning storage and defect identification algorithm. The method and system complete the scanning, identification and storage of all relevant negatives, the review of monitoring signals in the pipeline, the verification and repair of defect excavation, the synchronous comparison and verification of internal detection abnormalities and weld film defects, and find out possible hidden risks.
Description
technical field [0001] The invention relates to the technical field of weld seam detection, in particular to the technology of scanning and warehousing of pipeline weld film negatives and weld defect identification based on big data. Background technique [0002] Pipeline welds are one of the important characteristics of pipelines, and their quality directly affects the safety of pipelines. Since 2005, there have been many accidents caused by welding quality. According to statistics, more than 20 accidents occurred during the construction and operation periods, such as Seninglan The air leakage accident of the oblique weld of the double line and the oil leakage accident of the full cracking of the weld of the Moda Line in 2011 were all caused by the weld. Although the influence of external force cannot be ruled out, the welding conditions, temperature and weld quality all reflect abnormal behavior. Accidents caused by welds are manifested as: pipelines collided with dead jo...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/136G06T7/11G06K9/62G06T5/40G01N21/88G01N23/04G06F16/51
CPCG06T5/40G06T7/0004G06T7/11G06T7/136G01N21/8851G01N23/04G06T2207/20032G06T2207/30152G06F18/2411
Inventor 李强梁强刘新凌于航杨贺朱明元安鹏飞梁菁嬿
Owner GUANGDONG DAPENG LNG COMPANY