A pipeline leak diagnosis method based on a combination algorithm of big data

A combined algorithm and diagnosis method technology, which is applied in the pipeline leakage diagnosis of combined algorithm and pipeline leakage algorithm field, can solve the problem that the acoustic wave method is easily affected by the external environment, the positioning accuracy of the acoustic wave method is not good, and the detection sensitivity and false alarm positioning accuracy are low. and other problems to achieve the effect of improving sensitivity

Active Publication Date: 2021-08-10
CHINA PETROLEUM & CHEM CORP +2
View PDF14 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The research on pipeline leakage detection technology started relatively late in my country, but it has developed rapidly. According to different detection principles, there are mainly various detection algorithms such as negative pressure wave method, acoustic wave method, and mass balance method. The positioning accuracy of negative pressure wave method is Compared with the sonic method, the effect is not good. The sonic method is easily affected by the external environment, and the mass balance method is beneficial to the detection of small leaks. The above methods are difficult to solve the contradiction between the on-site detection sensitivity and false alarms and the positioning. The problem of low precision

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 pipeline leak diagnosis method based on a combination algorithm of big data
  • A pipeline leak diagnosis method based on a combination algorithm of big data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0036] The summary logic of the system is that the leak location is mainly based on the results of the negative pressure wave method, whether there is a leak is mainly based on the results of the infrasonic method, and the results of the mass balance method are mainly used for verification and correction.

[0037] For the negative pressure wave method, the instantaneous alarm output will generate a B-level alarm in the system. If the alarm result is verified by the infrasonic wave method or the mass balance method, the B-level alarm will be upgraded to an A-level alarm, and the leak location will be taken as negative. The position interval determined by the pressure wave method.

[0038] For the infrasonic wave method, the instantaneous alarm output will generate an A-level alarm in the system. If the negative pressure wave also outputs an alarm, the leak position will be corrected by the result of the negative pressure wave. If the negative pressure wave does not output an al...

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

A method for diagnosing pipeline leakage based on a combined algorithm of big data, which obtains pipeline pressure data, acoustic wave data, and flow data in real time through pressure transmitters, acoustic wave sensors, and flow meters; by connecting the PPS interface of the GPS system with the communication interface, the Synchronously store pressure data, acoustic wave data and flow data; use negative pressure wave method, acoustic wave method, and mass balance method to obtain measurement data, and use neural network algorithm after merging pressure data, acoustic wave data, and flow data at multiple scales Leakage diagnosis, and multiple algorithm diagnosis results are obtained at the same time; the diagnosis results of the above algorithms are combined, and the final diagnosis result is obtained by pattern discrimination with structural risk minimization; the positioning distance of each road is integrated, and the combined algorithm positioning result is obtained through statistical analysis; The technical means of combining multiple inspection methods combines the advantages of multiple algorithms and complements each other, improving the sensitivity of leak detection and the positioning accuracy of leak locations.

Description

technical field [0001] The invention relates to a pipeline leakage algorithm, in particular to a pipeline leakage diagnosis method based on a combination algorithm of big data, and belongs to the technical field of pipeline detection. Background technique [0002] Oil pipeline leakage is a potential threat to daily production and life, and it will bring great losses to people. Therefore, only by timely discovering oil pipeline leakage and the location of the leakage point can the pipeline safety be effectively and timely guaranteed Production. [0003] The research on pipeline leakage detection technology started relatively late in my country, but it has developed rapidly. According to different detection principles, there are mainly various detection algorithms such as negative pressure wave method, acoustic wave method, and mass balance method. The positioning accuracy of negative pressure wave method is Compared with the sonic method, the effect is not good. The sonic met...

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): F17D5/06G06K9/62G06N3/02
CPCF17D5/06G06N3/02G06F18/2411
Inventor 张惠民李亚平彭云超曹旦夫舒莉莉陈鹏汤养浩刘亭孟繁兴张瑜孙天择袁社梅王爱菊陈昱含刘鹏黄刚庄君史瑶华周靖林田新韬
Owner CHINA PETROLEUM & CHEM CORP
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