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

Terminal strip wiring identification and structured export method

A terminal block and structured technology, applied in the field of image recognition, can solve the problem of low efficiency of manual recognition, and achieve the effects of rapid identification and structuring, rapid and accurate identification, good generality and practicability

Pending Publication Date: 2022-04-05
宁夏宁电电力设计有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The problem to be solved by the present invention is to solve the problem that the identification of substation terminal block wiring mainly depends on the low efficiency of manual identification, and the purpose is to quickly and accurately automatically identify the substation terminal block wiring

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
  • Terminal strip wiring identification and structured export method
  • Terminal strip wiring identification and structured export method
  • Terminal strip wiring identification and structured export method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention proposes a method for terminal strip wiring identification and structural derivation, such as figure 1 shown, including the following steps:

[0029] 1) OCR recognizes the image text content.

[0030] 1.1) Perform image preprocessing on the input content image, including: geometric transformation (perspective, distortion, rotation, etc.), distortion correction, blur removal, and image enhancement.

[0031] 1.2) Text detection is performed on the input content image, and the fine-grained text is detected and connected into coarse-grained text regions through a bottom-up method.

[0032] Get the coordinate frame of each character to get fine-grained text. Manually labeled data sets, using the classic convolutional neural network VGG16 for model training, using Gaussian heat map CAM visualization network to guide whether the high response area of ​​the classification falls on the core part of the target. Use the trained model to predict the coordin...

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 terminal strip wiring identification and structured export method, which comprises the following steps of: acquiring a content image of a terminal strip of a transformer substation, performing character identification by adopting an OCR (Optical Character Recognition) technology, performing number type identification on characters identified by the OCR according to a position coordinate of an identified textbox and an image feature, and exporting the terminal strip wiring identification and structured export. And finally, according to the position of the textbox, identifying the corresponding relationship among the terminal group, the terminal port and the connecting wire, and exporting a structured result. According to the invention, the problem of low efficiency due to the fact that the current transformer substation terminal strip wiring identification mainly depends on manual identification is solved, and the rapid and accurate identification of the transformer substation terminal strip wiring is realized.

Description

technical field [0001] The invention belongs to the technical field of image recognition, relates to the recognition of printed characters on equipment, is used for intelligent recognition of substation secondary circuit wiring, and is a method for identifying and structurally deriving terminal strip wiring. [0002] technical background [0003] In the construction of substations, with the development of computer technology, the identification technology based on IoT perception can intelligently identify the on-site wiring of the secondary circuit of the substation. By intelligently comparing with the CAD design drawings, it can be quickly found that the substation site is inconsistent with the as-built drawings. potential risks. [0004] Optical Character Recognition (OCR), referred to as OCR, is a technology that recognizes and extracts the required target text in a complex picture background, thereby converting the text in the picture into editable text information. Unde...

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): G06V30/10G06V30/413G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
Inventor 王新新武玉萍白英郭科邵雪瑾李佳怡施浩楠宋江宁彭海涛胡广燕王金有王茜
Owner 宁夏宁电电力设计有限公司
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