Oil level detection method and system

An oil level detection and oil level technology, applied in image data processing, instruments, calculations, etc., can solve problems such as increased compressor power consumption, severe friction of compressor bearings, high heat, etc., to increase safety and reduce consumption. , the effect of better safety

Pending Publication Date: 2020-09-08
SUZHOU ZUOZHU HOT & COLD CONTROL TECH CO LTD +1
View PDF1 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The oil level reflects the oil quantity information inside the compressor. When the oil quantity of the compressor is too low, it will cause severe friction of the compressor bearings, generate excessive heat, and increase the power consumption of the compressor. Therefore, there is an urgent need for an oil level detection technology with high detection efficiency and high detection accuracy

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
  • Oil level detection method and system
  • Oil level detection method and system
  • Oil level detection method and system

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0053] The first embodiment, such as figure 1 As shown, a computer vision-based oil level detection method includes the following steps:

[0054] S1, collecting the image of the oil level observation port;

[0055] S2, image preprocessing, select the area of ​​interest to mark the oil level transparent area, reduce the noise edge of the image, and obtain the edge contour of the observation port and the oil level surface;

[0056] S3, regular image detection, setting the radius range of the oil level observation port, after filtering out invalid data, obtaining the radius and center coordinates of the circle where the oil level observation port is located;

[0057] Draw the oil level line, calculate the slope of the line where the oil level line is located, and calculate the intersection of the line and the circle;

[0058] S4, calculating and converting the distance from the center of the circle to the straight line into a percentage of oil volume.

no. 2 example

[0059] In the second embodiment, the present invention provides a computer vision-based oil level detection method, comprising the following steps:

[0060] S1, reference figure 2 As shown, the image of the oil level observation port is collected;

[0061] Optionally, images can be captured by industrial cameras;

[0062] S2, ref. image 3 As shown in the image preprocessing, the region of interest is selected to mark the oil level transparent region. The region of interest is the region in the image with the same shape as the oil level observation port. First, bilateral filtering is used to remove image noise edges, and then adaptive image The binarized image processing obtains the edge contour of the observation port and the oil level surface.

[0063] S3, ref. Figure 4 As shown, regular image detection, according to the Hough circle fitting core algorithm, find out the circle and the center of the oil level observation port in the preprocessed image. At the same time,...

no. 3 example

[0078] For the third embodiment, refer to Image 6 As shown, a computer vision-based oil level detection system includes:

[0079] a light source, which is annular, and which is used to illuminate the oil level sight glass;

[0080] Optionally, the light source is provided with a light source controller;

[0081] a camera unit, which is used to acquire the image of the oil level observation port;

[0082] A server, which is used to obtain the percentage of oil quantity according to the image of the oil level sight glass and the oil level calculation rules;

[0083] The server can adopt a computer with image processing function;

[0084] Among them, the oil level calculation rules include:

[0085] Select the area of ​​interest to mark the oil level transparent area, reduce the noise edge of the image, and obtain the edge contour of the observation port and the oil level surface;

[0086] Set the radius range of the oil level observation port, filter invalid data, obtain t...

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 oil level detection method, which is based on computer vision and comprises the following steps of: acquiring an oil level observation port image; preprocessing the image, selecting a region of interest to mark an oil level transparent region, reducing image noise edges, and obtaining an observation port edge contour and an oil level surface; performing regular image detection: setting a radius range of an oil level observation port, and filtering invalid data to obtain a radius and a circle center coordinate of a circle where the oil level observation port is located; drawing an oil level line, calculating the slope of a straight line where the oil level line is located, and calculating the intersection of the straight line and a circle; and calculating to obtain a percentage of converting the distance from the circle center to the straight line into oil. The invention further discloses an oil level detection system. The oil level monitoring system can be used for monitoring the oil level in real time, can automatically monitor the oil level information of the compressor, can reflect and record the oil level information more accurately and timely, can reduce the consumption of human resources, and improves the safety of oil level detection.

Description

technical field [0001] The invention relates to an oil level detection method applied in industry, in particular to a method for detecting the oil level through the image of an oil level observation port based on computer vision. The invention also relates to a system for detecting the oil level through the image of the oil level observation port based on computer vision. Background technique [0002] With the rapid development of computer vision technology and image processing technology, people can already apply computer vision technology to industry, and use cameras instead of manpower to monitor all aspects of production. This method is often stable, safe, contact-free, and real-time feedback High reliability, and reduce the consumption of human resources. [0003] At present, some factories mainly detect the oil level through manual detection. This method often has problems of low efficiency, poor real-time performance, poor safety, and low accuracy. Some other factor...

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): G06T7/60G06T7/13G06T5/00
CPCG06T7/60G06T7/13G06T5/002G06T2207/20028
Inventor 王文斌张倩
Owner SUZHOU ZUOZHU HOT & COLD CONTROL TECH CO LTD
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