Deep-learning-based method for identifying defect of power transmission equipment automatically

A technology of power transmission equipment and deep learning, which is applied in image data processing, instruments, biological neural network models, etc., can solve the problems of hidden dangers in power transmission lines, low work efficiency, and high labor intensity, so as to reduce manual labor intensity, Processing speed Real-time, fast processing effect

Inactive Publication Date: 2018-07-06
TIANJIN WOMOW TECH CO LTD
View PDF5 Cites 66 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On the one hand, most of the existing inspection image processing methods are based on manual interpretation to complete the calibration of target components and the classification of defects. Manual interpretation is labor-intensive and low-efficiency
On the other hand, the manual interpretation method does not have a unified evaluation standard as a basis, is easily affected by personal subjective facto

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
  • Deep-learning-based method for identifying defect of power transmission equipment automatically
  • Deep-learning-based method for identifying defect of power transmission equipment automatically
  • Deep-learning-based method for identifying defect of power transmission equipment automatically

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] It should be noted that, in the case of no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other.

[0042] The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0043] The method that the present invention proposes is:

[0044] First, use the multi-target recognition algorithm to identify the target device from the drone inspection photos or videos, and then use the deep learning classifier to judge whether the target device is defective and the type of defect.

[0045] Specifically, if figure 2 As shown, the photos of transmission line equipment obtained by each UAV inspection are first sent to the Faster-Rcnn model to extract the area containing transmission equipment, and the type of transmission equipment contained in each area is judged, and then according to its type Send it to the defect classification model (defect classifier) ​​of th...

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

According to the invention, a body photo, obtained by routing inspection by an unmanned aerial vehicle, of a transmission tower is analyzed automatically by using a deep learning technology. On the basis of a Faster-Rcnn algorithm, power transmission equipment needing detection is identified from the photo obtained by routing inspection by the unmanned aerial vehicle; the power transmission equipment is sent to a defect classifier for the equipment to determine whether the equipment has a defect and which type the defect is; if the equipment has a defect, the location of the defect equipment as well as the defect type is marked in the photo automatically; and then a defect report is generated finally and maintenance information is provided for the maintenance staff. According to the invention, the analysis process has advantages of high accuracy, fast processing speed and high reliability; and the automatic analysis of the inspection photo of the transmission line is realized without manual participation.

Description

technical field [0001] The invention belongs to the field of electric power detection, and in particular relates to a deep learning-based automatic defect recognition method for power transmission equipment. Background technique [0002] The power system is different from other industries. Maintenance cannot interrupt production at will. It is necessary to make sufficient predictions before the accident occurs—to solve the fault before the accident occurs, and the focus is on the preventive inspection of the transmission line. Transmission lines are burdened with high voltage and high current for a long time. In recent years, with global warming, severe weather and weather have occurred frequently, which poses an increasing danger to the safe operation of the power grid. [0003] With the continuous improvement of the intelligence level of the power grid, drone inspections are increasingly used. After each inspection task is completed, a large number of inspection pictures ...

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): G06T7/00G06N3/04
CPCG06T7/0004G06N3/045
Inventor 韩双立佘换林赵筱磊段梦凡
Owner TIANJIN WOMOW 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