Power grid image recognition system and method

An image recognition and power grid technology, applied in the field of electric power, can solve problems such as uneven understanding and application of image recognition algorithms, hindering the development speed of image recognition technology, failing to meet fast identification and terminal compatibility, etc., to achieve easy maintenance and management, avoid Manual cumbersome operation, the effect of improving scalability

Inactive Publication Date: 2018-05-18
SHENZHEN POWER SUPPLY BUREAU +1
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, many achievements have been made in the power industry by using image recognition technology at home and abroad. However, due to separate research and construction, each product has uneven understanding and application of image recognition algorithms and power models, which seriously hinders the use of image recognition technology in the domestic power industry. The development speed of the industry, coupled with the fact that image recognition applications are generally applied to mobile terminals, independent applications often cannot meet the requirements of fast identification and terminal compatibility

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
  • Power grid image recognition system and method
  • Power grid image recognition system and method
  • Power grid image recognition system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] refer to figure 1 , A power grid image recognition system provided in Embodiment 1 includes: a service integration layer, a service implementation layer, and a third-party service layer, specifically:

[0031] Service integration layer, including service gateway and service registry.

[0032] Among them, the service registration center is used to register different types of services, and the services here specifically include third-party services and business services. Registering the service to the system enables the system to plug and unplug the service and realize a unified software platform that can be flexibly expanded.

[0033] It can be understood that by registering the business service in the service registry, the business service can be added to the service implementation layer; and by deleting the business service from the service registry, the business service can be deleted from the service implementation layer. Of course, adding to or deleting from the s...

Embodiment 2

[0044] Based on the same inventive concept, the present invention also discloses a grid image recognition method based on the above system, the method includes:

[0045] The service gateway receives external requests, and after finding the corresponding service in the service registry, forwards the request to the corresponding type of service;

[0046] The business service receives the request forwarded by the service gateway, and processes the request by invoking the basic service. Among them, the processing of the request by calling the basic service includes: calling the image recognition basic training service based on the TensorFlow deep learning framework encapsulated in the Docker container to realize the training of the image model, and calling the OpenCV cross-platform based on the OpenCV package encapsulated in the Docker container The image recognition basic algorithm service of the computer vision library realizes image recognition.

[0047] It can be understood t...

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 power grid image recognition system and a power grid image recognition method. The system comprises a service integration layer and a service implementation layer, wherein the service integration layer comprises a service gateway and a service registration center, the service registration center is used for registering different types of services, and the service gatewaycan receive a request from the outside, and forward the request to the corresponding type of services after finding the corresponding services; and the service implementation layer comprises a business service and a basic service, the basic server provides an image recognition basic algorithm function and an image recognition basic training function, and the business service receives the request forwarded by the service gateway, and implements treatment on the request through calling the basic service. According to the system and the method provided by the invention, the flexile access capacity is provided for the subsequent new image algorithm service, and the convenience is provided for subsequent upgrade and expansion of a pattern recognition engine, so that the pattern recognition technology can well serve the power industry; pattern recognition can be achieved by using a mobile terminal for collecting equipment information and initiating the request for the service gateway of thesystem when equipment is inspected, and the working efficiency is enhanced.

Description

technical field [0001] The invention relates to the field of electric power, in particular to a power grid image recognition system and method. Background technique [0002] With the construction and development of information systems, the means of data collection are becoming more and more abundant, and the way of data collection using image recognition has gradually become common. At present, when electric power enterprises collect data in mobile field operations, they mostly collect data mechanically, that is, on-site personnel manually identify and enter relevant information into the system for processing and archiving. And some simple mechanical work (such as nameplate data recognition) can use image recognition for data collection to improve the efficiency of on-site operations. [0003] At present, many achievements have been made in the power industry by using image recognition technology at home and abroad. However, due to separate research and construction, each p...

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): H04L12/24H04L29/08G06K9/00
CPCH04L41/5054H04L67/34G06V20/10
Inventor 宁柏锋黄安子吕志宁庞宁余里程冯薇玺孙蓉蓉周子强林煜辉
Owner SHENZHEN POWER SUPPLY BUREAU
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