Electric power infrastructure construction site violation identification method and system

A construction site and identification method technology, applied in the field of electric power engineering, can solve the problems of lack of precise evaluation, deduction and display tools for placement and height constraints, habitual violations, and insufficient enforcement and supervision, so as to promote intelligent operation. The effect of inspection mode change, efficiency improvement and professional depth, efficiency improvement and accuracy rate improvement

Pending Publication Date: 2021-04-06
国网山东省电力公司建设公司 +1
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In terms of process control for the entry of large-scale tools and tools, there is a lack of precise assessment measures and deduction and display tools for placement and height restrictions, which may easily cause safety hazards
At the same time, with the start of the power grid construction and renovation project, the work site is multi-faceted and the construction team is large, and the pressure on safety risk management and control is increasing day by day
[0005] From a subjective point of view, it is easy to cause habitual violations due to personal professional quality, safety awareness, and the pursuit of convenience; As a result, the implementation and supervision during the operation process are not in place, which easily aggravates the safety risk; there are many types of settings, equipment parameters, and equipment status involved in substation inspections. Relying on a completely manual inspection method will bring huge workload. At the same time, it is inevitable that there will be various flaws, which will bring greater security risks.

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
  • Electric power infrastructure construction site violation identification method and system
  • Electric power infrastructure construction site violation identification method and system
  • Electric power infrastructure construction site violation identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] Embodiment 1 of the present disclosure provides a method for identifying violations at the construction site of electric power infrastructure, which analyzes and processes sample feature information on the obtained original video material, adds artificial prior knowledge and image recognition results, and performs feature extraction, classifier model training and verification. , to realize the intelligent judgment of illegal operation behavior.

[0073] Specifically, include the following:

[0074] S1: Sample data classification processing and sample labeling

[0075] Collect image and video data samples at the power infrastructure construction site, compare the sample library, and use the computer to automatically label the samples according to the established sample labeling rules. Compared with the traditional manual labeling method, the work efficiency is significantly improved; Various types of workers, electrical equipment, safety helmets, insulating gloves, etc....

Embodiment 2

[0106] Embodiment 2 of the present disclosure provides a system for identifying violations at a power infrastructure construction site, including:

[0107] The data acquisition module is configured to: acquire the video frame image data of the power infrastructure construction site;

[0108] The feature extraction module is configured to: use the first neural network model to extract device features from video frame images to obtain device feature maps;

[0109] The candidate area acquisition module is configured to: use a preset candidate area generation network to obtain feature candidate areas of various scales and aspect ratios according to the obtained device feature map;

[0110] The violation identification module is configured to: use the preset classification regression network to obtain equipment identification results according to the obtained equipment feature map and feature candidate areas, and judge on-site violations according to the equipment identification re...

Embodiment 3

[0113] Embodiment 3 of the present disclosure provides an auxiliary system for control and control of violations at the construction site of electric power infrastructure, such as Figure 10 As shown, the overall architecture of the system is divided into three levels: intelligent video surveillance acquisition terminal, intelligent mobile monitoring platform and remote monitoring center.

[0114] The intelligent video surveillance acquisition terminal is deployed on the infrastructure site, adopts a portable design, does not require additional new video surveillance equipment, and integrates a video data intelligent analysis unit and a video violation storage unit, wherein the video data intelligent analysis unit is used for The video image is subjected to comparative analysis of video data, identification of violation features, and confirmation of violations; the video violation storage unit is used for alarming the violation results and storing violation logs, and the video ...

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 an electric power infrastructure construction site violation identification method and system. The method comprises the following steps: obtaining electric power infrastructure construction site video frame image data; performing equipment feature extraction on the video frame image by using a first neural network model to obtain an equipment feature map; according to the obtained equipment feature map, a preset candidate region generation network is utilized to obtain feature candidate regions of various scales and aspect ratios; and utilizing a preset classification regression network to obtain an equipment identification result according to the obtained equipment feature map and the feature candidate region, and performing field violation judgment according to the equipment identification result. According to the invention, an artificial intelligence deep learning algorithm is adopted to realize rapid identification of various violations of the power infrastructure construction site, and the intelligent identification efficiency and accuracy of violation operation are improved.

Description

technical field [0001] The present disclosure relates to the technical field of electric power engineering, in particular to a method and system for identifying violations at a construction site of electric power infrastructure. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] With the rapid development of social economy and technological development, the construction of electric power infrastructure continues, the traditional inspection mode is still based on a large amount of manpower input, the information acquisition method is traditional, and the source is single, and more rely on manual methods such as telephone and on-site surveys to obtain equipment-related information , the degree of leanness of a single manual operation has fallen into a bottleneck, which cannot fully meet the requirements of lean management in the future. [0...

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): G06K9/00G06K9/32G06K9/46G06K9/62G06N3/04G06N3/08G06Q10/06
CPCG06N3/08G06Q10/063114G06V20/41G06V20/46G06V10/25G06V10/44G06V2201/07G06N3/047G06N3/045G06F18/241
Inventor 张映晖王晓燕柴沛张利民韩鹏凯张廷尹东李睿杨博聂文昭翟乐刘锋张成于青涛许志健王佳科李乐蒙付振虎郭玉新高兴强
Owner 国网山东省电力公司建设公司
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