Reading identification method for single-pointer instrument based on shale gas field production

A technology for instrument reading and recognition methods, applied in character and pattern recognition, instruments, computer parts, etc., can solve problems such as low instrument image, inability to accurately identify clarity, and low clarity

Pending Publication Date: 2020-12-04
四川长宁天然气开发有限责任公司 +1
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The object of the present invention is to provide a recognition method based on the reading of a single-pointer instrument in shale gas field production. For the image of a mechanical instrument with low definition obtained by a monitoring camera on the production site, this method is used for image processing. The computer vision analysis of the mechanical instrument dial can accurately identify t

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
  • Reading identification method for single-pointer instrument based on shale gas field production
  • Reading identification method for single-pointer instrument based on shale gas field production
  • Reading identification method for single-pointer instrument based on shale gas field production

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] An identification method based on single-pointer instrument readings in shale gas field production, such as figure 1 , mainly including the following steps in sequence:

[0068] Step 1, capture the image: use the mechanical instrument model trained by deep learning to detect and locate the position of the mechanical instrument in the captured image, intercept the sub-image of the instrument, and perform computer vision analysis of the mechanical instrument;

[0069] Step 2, image preprocessing: perform image preprocessing on the intercepted sub-image of the mechanical instrument, and perform image resampling;

[0070] Step 3, image filtering: transfer the resampled image from RGB space to HSV space, loop through the V channel data of the image space, detect and find the boundary of the speckle under each V value;

[0071] Step 4, constructing the central rectangle: constructing the central rectangle of the sub-image of the mechanical meter, and filtering the border of ...

Embodiment 2

[0082] On the basis of the above-mentioned embodiment 1, the step 3 mainly includes the following steps carried out in sequence:

[0083] Step 3-1: Convert the resampled image from RGB space to HSV space;

[0084] Step 3-2: Loop through the V value of the HSV image space from 80 to 230, perform 150 boundary judgments and search for each image, and find the boundary of the map spot.

[0085] It should be noted that in different application scenarios, the value range of HSV is different, such as figure 2 , the present invention utilizes the cvSplit function in openCV to select the image type, the value range of H is 0-180, the value range of S is 0-255, the value range of V is 0-255, and when the V value is too large or too small The error range of the patch boundary is too large, so we choose a middle range of V value range to loop through, here we choose the V value range from 80 to 230.

[0086] Working principle: By analyzing the instrument images under different rotation...

Embodiment 3

[0088] On the basis of the above-mentioned embodiment 1 or 2, when loop traversing the V channel data of the image space in the step 3, the influencing factors of the loop termination mainly include the aspect ratio of the minimum circumscribed rectangle of the boundary line, the minimum side of the minimum circumscribed rectangle At least one of the length ratio of the side length ratio of the center rectangle of the construction instrument, the area of ​​the boundary line to the area ratio of the center rectangle of the construction instrument, and the values ​​of the impact factors are all within the predefined threshold, the loop terminates, otherwise continue to loop through the search Blob border.

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 reading identification method for a single-pointer instrument based on shale gas field production relates to the field of instrument intelligent identification, and aims to convert a blurred mechanical instrument dial image shot by a camera on a production site from an RGB space to an HSV space, and then perform cyclic traversal on V channel data of an image space to obtain a mechanical instrument dial image. A pattern spot boundary is detected and searched under each V value; A central rectangle of a mechanical instrument sub-image is crated and a formed pattern spotboundary is filtered. then, the filtered pattern spot boundary is subjected to length-width ratio constraint, the pattern spot boundary comprises central rectangular central point constraint, and then mechanical instrument pointer boundary positioning is carried out; and finally, the found pointer boundary is subjected to straight line fitting, deflection angle calculation and instrument readingcalculation, so that data reading of the mechanical instrument dial plate is realized by directly using a monitoring camera in a production field, and compared with an existing intelligent identification method, the accuracy of identifying a fuzzy picture is higher.

Description

technical field [0001] The invention relates to the field of instrument intelligent identification, in particular to an identification method based on the reading of a single-pointer instrument in shale gas field production. Background technique [0002] As shale gas production capacity continues to increase, more and more unmanned inspection shale gas production platforms will be put into production sites. At present, there are many single-pointer mechanical instruments in the key platform wells of shale gas production sites. These mechanical instruments are not connected to intelligent electronic devices, and the readings cannot be directly transmitted back to the back-end online platform. The existing production sites generally use manual inspections. After the reading, the data is sent back to the back-end online platform through the terminal online platform, the labor cost is high, and the data cannot be read in real time at any time. [0003] Cameras are installed at ...

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): G06K9/20G06K9/46
CPCG06V10/22G06V10/56G06V2201/02
Inventor 文士豪蔡从德谭婷朱君伍星张中杰周聪郑永明王承宇
Owner 四川长宁天然气开发有限责任公司
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