Method and device for detecting abnormality of power grid equipment

A power grid equipment and anomaly technology, applied in the direction of neural learning methods, character and pattern recognition, biological neural network models, etc., can solve the problems of being unable to directly output image abnormal areas, unable to locate abnormal areas, etc., to improve the accuracy of abnormal detection, The effect of improving detection accuracy and improving feature extraction ability

Active Publication Date: 2020-08-21
BEIJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Among the existing abnormality detection methods for power grid equipment, a method based on image comparison is to use the traditional image registration algorithm to segment the two images respectively, compare the degree of difference with the set threshold, and judge whether the currently captured image is Anomaly image; however, the method cannot locate anomalous regions in the image
[0005] Another existing method is an equipment abnormality recognition method based on deep learning, which uses image classification technology to train a classifier model on the data, and finally uses the trained model to directly classify; but this method cannot directly output the data in the image. Abnormal area

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
  • Method and device for detecting abnormality of power grid equipment
  • Method and device for detecting abnormality of power grid equipment
  • Method and device for detecting abnormality of power grid equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Embodiment 1 of the present invention provides a method for detecting abnormality of power grid equipment, the process of which is as follows figure 1 shown, including the following steps:

[0058] Step S101: Use the feature extraction network to perform feature extraction on the grid equipment image to be detected.

[0059] In this step, the grid equipment image to be detected is input into such as figure 2 Feature extraction is performed in the feature extraction network in the abnormal region detection model shown. Among them, the abnormal area detection model may include a feature extraction network and an object detector.

[0060] The feature extraction network can be a pre-trained convolutional neural network. The residual structure network in the convolutional neural network can output the high-level semantic feature image of the abnormal image of the grid equipment according to the input abnormal image of the grid equipment. Such as figure 2 As shown, the...

Embodiment 2

[0104] As a more optimal implementation mode, the second embodiment of the present invention provides a method for detecting abnormality of power grid equipment, the process of which is as follows Figure 5 shown, including the following steps:

[0105] Step S501: Use the feature extraction network to perform feature extraction on the grid equipment image to be detected.

[0106] In this step, the method of using the feature extraction network to extract the features of the grid equipment image to be detected is the same as the method in step S101 in the first embodiment above, and the structure of the feature extraction network in the second embodiment of the present invention is also the same as that in the first embodiment above The structure of the feature extraction network is the same and will not be repeated here.

[0107] Step S502: Use the object detector to detect abnormal areas of the grid equipment in the grid equipment image.

[0108] In this step, the method of...

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 and device for abnormal detection of power grid equipment. The method includes: using a feature extraction network to perform feature extraction on an image of power grid equipment to be detected, and inputting several feature images of different sizes output by the feature extraction network respectively. to each anchor point generation layer in the object detector; each anchor point generation layer in the object detector performs image interception on the input feature image according to the preset width and height dimensions, and is detected by the detection in the object detector The head calculates the probability value of the equipment abnormal area for each intercepted image; the detection head sorts the calculated probability values ​​from high to low, and uses the images with the top N in the probability value sorting as the detected abnormal area of ​​the power grid equipment. image. The application of the invention can directly locate the abnormal area in the grid equipment image.

Description

technical field [0001] The invention relates to the technical field of grid equipment abnormality detection, in particular to a detection method and device for grid equipment abnormality. Background technique [0002] With the development of image processing technology, in order to meet the requirements of power operation site safety monitoring and reduce personal accidents, it is more and more feasible to use image intelligent processing methods to detect abnormalities in power grid equipment such as substation equipment. With the continuous popularization and development of intelligent inspection equipment, under the widespread use of various power units, the abnormal image data of the equipment is increasing. The massive inspection data relies on manual retrieval analysis or traditional image processing to set thresholds, etc., which is inefficient and intelligent. It is impossible to automatically monitor power equipment in real time and accurately identify and locate fa...

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): G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/462G06N3/045G06F18/217G06F18/214
Inventor 傅慧源马华东于广华
Owner BEIJING UNIV OF POSTS & TELECOMM
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