Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Insulator identification method in distribution line based on statistical characteristics and machine learning

A technology for insulator identification and statistical features, which is applied in the fields of power technology and computer vision, and can solve problems such as complexity, many background changes, and no universality.

Active Publication Date: 2018-08-31
TIANJIN UNIV
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the variety and complexity of the background, the above methods are not universal and cannot be well applied to the actual system

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
  • Insulator identification method in distribution line based on statistical characteristics and machine learning
  • Insulator identification method in distribution line based on statistical characteristics and machine learning
  • Insulator identification method in distribution line based on statistical characteristics and machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] specific implementation plan

[0025] In order to make the technical solution of the present invention clearer, the specific implementation of the present invention will be further described below in conjunction with the accompanying drawings. The specific implementation plan flow chart is as follows figure 1 shown.

[0026] 1 Obtain the training set pictures and train the classifier model.

[0027] 1) Divide the aerial pictures obtained when patrolling the power distribution lines into two groups according to the appropriate ratio, and use them as training set pictures and test set pictures respectively. Among them, the training set contains 56 pictures, and the test set contains 14 pictures. Positive and negative The sample is divided into half and half. original image figure 2 shown.

[0028] 2) Perform YCbCr transformation on the training set picture obtained in step 1, that is, transform from RGB color space to YCbCr color space. The YCbCr color space consis...

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 relates to an insulator identification method in a distribution line based on statistical characteristics and machine learning. The method comprises the following steps of dividing aerial pictures acquired during distribution line patrolling into two groups according to an appropriate proportion and taking as a training set picture and a test set picture; carrying out YCbCr transformation; extracting the statistical characteristics on a Y channel, a Cb channel, and a Cr channel respectively, wherein the selected statistical characteristics are from a first moment to a six momentof an image and a standard deviation; carrying out normalization processing and arranging original data into [0,1]; making a label file according with a support vector machine SVM and taking as the training sample of a SVM classifier; training the SVM classifier, carrying out optimal characteristic selection, and selecting a data set having an identification advantage from 7 statistical characteristics; and inputting into the test set picture, and using a trained classifier to output a classification result.

Description

technical field [0001] The invention belongs to the fields of electric power technology and computer vision, and relates to a method for identifying insulators in drone inspection aerial images based on image processing technology and machine learning technology. Background technique [0002] The power distribution network refers to the network in which the low-voltage side of the secondary step-down transformer in the power system supplies power to the user directly or after step-down. The distribution line refers to the power from the step-down substation to the distribution transformer or the power to the distribution substation The line sent to the power unit. Insulators are an important part of overhead distribution lines. They are used to support and fix busbars and live conductors, and to provide sufficient distance and insulation between live conductors or between conductors and the earth. They also bear the vertical load and horizontal load of the conductors. Accor...

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): G06K9/00G06K9/62G06K9/46
CPCG06V20/13G06V10/56G06F18/2411
Inventor 侯春萍李晨杨阳章衡光
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com