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

Method and system for intelligently identifying power grid stockbridge damper based on transfer learning algorithm

A technology of transfer learning and anti-vibration hammer, applied in the field of Al recognition, can solve the problem of low fault recognition rate of Al model, and achieve the effect of accurate recognition results

Pending Publication Date: 2019-07-12
SICHUAN POWER EHV OVERHAUL
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of the problems of the above research, the purpose of the present invention is to provide a method and system for intelligent identification of power grid anti-vibration hammers based on migration learning algorithms, to solve the problem in the prior art that the images collected by UAV inspection power grid lines are processed through the Al model. Fault identification, when the sample size obtained is not enough, it will cause the problem of low recognition rate of Al model for faults

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 system for intelligently identifying power grid stockbridge damper based on transfer learning algorithm
  • Method and system for intelligently identifying power grid stockbridge damper based on transfer learning algorithm
  • Method and system for intelligently identifying power grid stockbridge damper based on transfer learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0079] Obtain 30,000 JPG pictures containing the anti-vibration hammer of the power grid (that is, the picture of the anti-vibration hammer of the communication tower) as source data; clean and label the 30,000 pieces of source data in turn to obtain 30,000 pieces of marked source data; Tens of thousands of annotated pictures in the source data are input to the Resnet 101-layer deep residual network, and the output features are 2048-dimensional vectors, that is, a total of 2048 numbers; put the features into faster-rcnn for suggestion box selection, and get multiple A suggestion box, each suggestion box that obtains is similar to the data structure of json format, comprises prob, name, the situation of box (box comprises the coordinates of four points, in fact the algorithm output among the present invention is box four points In the later stage, you need to multiply the entire length and width by the relative position information. That is: ymin=s_boxes[i][0]*height, xmin=s_box...

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 system for intelligently identifying power grid stockbridge damper based on transfer learning algorithm, belongs to the technical field of AI identification, and solves the problem of low fault identification rate of an AI model under the condition that the acquired sample size is insufficient when fault identification is performed on an image acquired by an unmanned aerial vehicle inspection power grid line through the AI model in the prior art. According to the method, AI modeling is carried out based on acquired source data and a fasterrcnn algorithm network, an original data model is generated, and the source data is composed of a JPG picture containing a power grid stockbridge damper; on the basis of the obtained target data, the original data model is migrated through a migration learning algorithm to generate a target data model, the target data is composed of anti-vibration hammer characteristics of the power grid; and the to-be-detected power grid stockbridge damper picture is automatically identified based on the target data model to obtain a final identification result. The method is used for intelligent identification of the power grid stockbridge damper.

Description

technical field [0001] A method and system for intelligent identification of power grid anti-vibration hammers based on transfer learning algorithms, which are used for intelligent identification of power grid anti-vibration hammers, and belong to the technical field of Al identification. Background technique [0002] With the rapid development of my country's economy and society, the demand for electricity is also increasing day by day. The power grid is an important support for the national economy. The stability and reliability of power lines are closely related to people's life and production activities. The society brings economic losses that cannot be underestimated. For this reason, power grid inspection work is very important, and its strategic position and rigid demand are very prominent. With the development of power grid inspection for many years, power inspection has changed from traditional manual inspection to drone inspection. With the new wave of technology b...

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): G06T7/00G06T7/62G06T7/73
CPCG06T7/0004G06T7/62G06T7/73G06T2207/10004G06T2207/20081G06T2207/20084G06T2207/30108
Inventor 鲁力杨蔚于佰龙蒋泽峰熊一帆饶韦马志方冯伦罗宇辰高冲
Owner SICHUAN POWER EHV OVERHAUL
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