Electric power screen cabinet hard pressing board state identification method based on machine vision

A state recognition and machine vision technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of time-consuming and labor-intensive checking, color shift, and invisible light color, etc., to achieve easy maintenance and installation, and simple operation Effect

Inactive Publication Date: 2018-06-05
WUHAN ZHONGYUAN HUADIAN SOFTWARE
View PDF4 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the large number of hard pressing plates in the station, the checking work is time-consuming and laborious, and manual checking is prone to omissions and errors. Once the hard pressing plates are in the wrong position, there will be risks in equipment operation, which will pose a great threat to power supply security.
[0004] Some methods using image processi

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 screen cabinet hard pressing board state identification method based on machine vision
  • Electric power screen cabinet hard pressing board state identification method based on machine vision
  • Electric power screen cabinet hard pressing board state identification method based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but the protection scope of the present invention is not limited thereto.

[0072] like figure 1 Shown, method step of the present invention is as follows:

[0073] The first step is to collect and calibrate the sample image of the hard press plate, and build the sample library of the hard press plate:

[0074] (1-1) collect images of hard plate samples in different states;

[0075] (1-2) Calibrate the current state for each hard plate sample image.

[0076] The second step is to read all the hard platen images and their labels in the hard platen sample library, train and learn to obtain the target positioning classifier and state recognition classifier:

[0077] (2-1) Calculate the histogram feature of gradients (HOG) of the hard press plate image in the hard press plate sample library; specifically:

[0078] (2-1-1) Calculate the gradient i...

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 an electric power screen cabinet hard pressing board state identification method based on machine vision. An electric power screen cabinet image is acquired through image acquisition equipment. The state of each hard pressing board in the electric power screen cabinet image is identified. Through comparing the identified state with an original preset state of the hard pressing board, the position of the hard pressing board in changed state and the current state are acquired. According to the electric power screen cabinet hard pressing board state identification method,target positioning, result sequencing and state identification are performed on the hard pressing board on the electric screen cabinet, and finally the current state of each hard pressing board is obtained. The single identification result is compared with the original preset state in a one-to-one manner. If the single identification result is same with the original preset state, no treatment is performed; and otherwise, alarming is generated for reminding personnel of a sequence number of the problem and performing in-time treatment. The electric power screen cabinet hard pressing board stateidentification method has advantages of low cost, no specific requirement for appearance and color of the hard pressing board, relatively high adaptability for an outer environment, no requirement for excessive intervention by the personnel in the whole treatment process, visual operation and quick response. The position of the hard pressing board with the problem and the current state of the hard pressing board can be directly obtained.

Description

technical field [0001] The invention relates to the fields of image processing, machine vision and electric power intelligent inspection, and applies image processing and machine learning technology to electric power intelligent inspection, specifically a machine vision-based method for identifying the state of hard pressure plates of power screen cabinets. Background technique [0002] The switching (connection) and withdrawal (disconnection) operation of the hard pressing plate of the power screen cabinet is the main item of the secondary equipment operation in the switching operation of the substation. The hard pressing plate is the bridge and link for the protection device to connect with the external wiring, which is related to the protection function. and whether the action export can function normally. [0003] At present, the checking of the hard pressing plate of the power screen cabinet is basically done manually. The electric power workers hold the paper hard pres...

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): G06K9/62G06K9/00
CPCG06V20/00G06V10/507G06V10/467G06V2201/06G06F18/24G06F18/214
Inventor 马路罗峥冯维纲熊少华周萍曹昊饶小寒
Owner WUHAN ZHONGYUAN HUADIAN SOFTWARE
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