Real-time accurate detection method for state of split knife switch

A detection method and a split-type technology, applied in the field of image recognition, can solve the problems of low real-time detection accuracy of knife gate status and so on

Pending Publication Date: 2020-01-21
南京鑫和汇通电子科技有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of low real-time detection accuracy of the knife switch state in the prior

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
  • Real-time accurate detection method for state of split knife switch
  • Real-time accurate detection method for state of split knife switch
  • Real-time accurate detection method for state of split knife switch

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] Embodiment 1: A real-time and accurate detection method of the split knife switch state, including: collecting the real-time monitoring video of the split knife switch, acquiring any frame image of the video and establishing the boundary line of the knife switch arm of this type according to it The model is saved as a model file, and the left midpoint, right midpoint, midpoint, and centerline of the knife arm are calculated according to the model file; the sample image of the split knife gate is obtained through various methods, and the sample image is processed by deep learning Training Obtain the training model, use the training model to detect the first frame image of the video, obtain all the switch area, switch status and insulator area in the first frame image, and then combine the model file to detect the switch in the first frame image The arm and the insulator are positioned, and the reliability of the knife switch is calculated according to the positioning resu...

Embodiment 2

[0075] Embodiment 2: First assign weights to the edge line set of the left knife gate arm and the edge line set of the right knife gate arm, such as Figure 3 to Figure 5 As shown, the method of assigning weights to the edge line set of the left knife arm is as follows: traverse all the edge lines in the edge line set of the left knife arm, calculate the angle of each left edge line and classify the left edge according to it, given the height Angle threshold and low angle threshold, set the left edge line corresponding to the left edge line angle greater than the high angle threshold as vertical edge line 3, and set the left edge line corresponding to the left edge line angle smaller than the low angle threshold as horizontal edge line 4 , set the left edge line corresponding to the left edge line angle between the low angle threshold and the high angle threshold as the inclined edge line 5;

[0076] For all vertical edge lines 3 of the left knife arm, set the x coordinate val...

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 provides a real-time accurate detection method for the state of a split knife switch, and the method comprises the steps: collecting a real-time monitoring video, and building a model file; acquiring sample images, training the sample images by using deep learning to acquire a training model, detecting each frame of image to acquire a knife switch area, a knife switch state and an insulator area in the image, positioning a knife switch arm and an insulator in the image in combination with a model file, and calculating the credibility of a knife switch according to a positioning result; detecting the image meeting the credibility condition according to the positioning result, and calculating an initial included angle between the left disconnecting link arm and the right disconnecting link arm; estimating a system error, determining a correction included angle between the left knife switch arm and the right knife switch arm in each frame of image, judging a real-time stateof the knife switch in each frame of image until the knife switch is detected to stop moving, and verifying a final state of knife switch movement in the video; according to the invention, the problemof low real-time detection precision of the state of the split knife switch is solved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a real-time and accurate detection method for the state of a split knife switch. Background technique [0002] Knife switch is an electrical appliance that is used very frequently in high-voltage switching appliances, and it plays an isolation role in the circuit. In practical applications, due to the long-term operation of the knife switch, there will be situations where the knife switch is not closed or opened properly, and this situation will cause an arc to be generated between the left and right knife switch arms of the knife switch. Arc is a gas discharge phenomenon. The instantaneous spark generated by the current passing through some insulating media may cause fire or threaten personal safety; in addition, the arc temperature is extremely high, and it is easy to burn the insulating material, causing leakage events or causing damage to the knife switch equipment....

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): G06K9/00G06K9/62G06T7/13G06T7/136
CPCG06T7/13G06T7/136G06T2207/10016G06V20/41G06V20/52G06F18/214
Inventor 任大明汪辉
Owner 南京鑫和汇通电子科技有限公司
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