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

Extraction method of typical features of natural gas pipeline corrosion defects

A natural gas pipeline and feature extraction technology, which is applied in pipeline systems, gas/liquid distribution and storage, instruments, etc., can solve the initial cluster center interference of cluster analysis, and the detection data processing method cannot efficiently and reasonably extract pipeline corrosion defects Typical characteristics and other problems, to achieve the effect of high data processing efficiency and simple extraction process

Active Publication Date: 2020-10-30
SOUTHWEST PETROLEUM UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention aims to solve the problems that the clustering analysis is easily disturbed by outliers and initial cluster centers, and the existing detection data processing methods cannot efficiently and reasonably extract the typical characteristics of pipeline corrosion defects. Brand and natural gas composition information, based on the statistical outlier detection method and the improved clustering algorithm based on the roulette algorithm, the method of extracting typical characteristics of corrosion defects from a large number of detection data

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
  • Extraction method of typical features of natural gas pipeline corrosion defects
  • Extraction method of typical features of natural gas pipeline corrosion defects
  • Extraction method of typical features of natural gas pipeline corrosion defects

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0061] Four natural gas pipelines in a certain area have been inspected for defects. Among them, the grades of P1~P2 pipelines are X52, the pipe diameters are 630×8.0mm, 630×9.0mm, and the design pressure is 4MPa. The pipeline transportation medium is dry natural gas, which does not contain h 2 S and CO 2 ; Among them, the P3 pipeline grade is 16Mn, the pipe diameter specification is 559×8.0mm, the design pressure is 6.6MPa, and the pipeline transportation medium is containing H 2 S dry natural gas; the grade of P4 pipeline is 20#, the diameter specification is 325×8.0mm, the design pressure is 6.4MPa, and the pipeline transportation medium is H 2 Wet natural gas of S. Now according to the method of the present invention, the typical size and circumferential distribution orientation characteristics of corrosion defects inside the pipeline are extracted from the detection data of the above-mentioned pipelines, and the size and the circumferential distribution orientation char...

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 a method for extracting typical features of corrosion defects of natural gas pipelines, belonging to the technical field of oil and gas pipelines. It includes the following steps: collecting design parameters and conveying medium information of pipelines with defects; detecting pipeline defects by using a magnetic flux leakage detector; pre-classifying the corrosive defect data; Curve fitting to obtain the optimal distribution type and probability density function that the defect size variable obeys; a clustering algorithm based on statistical outlier detection method and roulette algorithm idea improvement is used to cluster and analyze the defect data, and obtain Defect typical size, circumferential distribution orientation characteristic value. The invention improves the selection method of the initial cluster center, reduces the adverse influence of outliers on the cluster analysis, and provides a set of scientific and comprehensive methods for extracting corrosion defect distribution law, typical size and circumferential distribution orientation characteristics from a large number of detection data. systematic approach.

Description

technical field [0001] The invention belongs to the technical field of oil and gas pipelines, in particular to a method for extracting typical features of corrosion defects in natural gas pipelines. Background technique [0002] In the oil and gas pipeline industry, corrosion is one of the main factors that threaten the safety of natural gas pipelines. It can lead to the formation of a large number of corrosion defects such as thinning and cracks on the surface of the pipeline, burying hidden dangers for the safe operation of oil and gas pipelines. Regularly inspecting and evaluating the metal surface of oil and gas pipelines, and formulating reasonable repair measures, has become an important technical means for the oil and gas pipeline industry to deal with the threat of pipeline corrosion and reduce the risk of corrosion failure. [0003] Defect detection of metal pipelines usually produces a large amount of detection data, including information such as types and sizes of...

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): F17D5/02G06K9/62G01N27/83
CPCF17D5/02G01N27/83G06F18/23213G06F18/2433
Inventor 贾文龙杨帆吴瑕李长俊张员瑞张皓李经廷
Owner SOUTHWEST PETROLEUM 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