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

Adaptive learning overhead contact system rigid conductor identification method and device

A technology of self-adaptive learning and identification method, applied in the field of catenary rigid conductor identification method and device for self-adaptive learning, can solve problems such as inability to expand application well, complex subway line environment, and inability to adapt to the difference of catenary at the same time.

Active Publication Date: 2018-11-02
CHENGDU TANGYUAN ELECTRICAL APPLIANCE
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When this image processing and analysis method is applied to the measurement of subway lines and other lines, due to the large difference in camera imaging caused by the environmental differences of each line, it needs to be greatly modified for different lines, and cannot be well extended.
[0005] Defects of the traditional geometric parameter testing method based on image processing in the subway line catenary environment: the subway line environment is complex, the stability and accuracy of the measurement results are poor; Longer-term development of new detection and measurement algorithms

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
  • Adaptive learning overhead contact system rigid conductor identification method and device
  • Adaptive learning overhead contact system rigid conductor identification method and device
  • Adaptive learning overhead contact system rigid conductor identification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] Embodiment one: the realization process of the present invention comprises:

[0070] 1) During the acquisition process of the wire gray projection curve, two line array cameras are used to collect images of the same measured point including bus bars and catenary rigid wires, with a total of n images; the n images include bus bars and catenary rigid wires. The image of the conductor is processed by the catenary rigid conductor positioning and identification method to obtain the outline information of the left bus bar or the right bus bar of the catenary rigid conductor, and then based on the gray projection algorithm, the left bus bar or the right bus bar of the catenary rigid conductor is The outline information of the side busbar is processed to obtain the gray scale projection curve of the catenary rigid conductor positioning; (in this process, the catenary rigid conductor positioning identification method is as follows image 3 The method is to determine the position...

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 relates to the field of overhead contact system image processing and provides an adaptive learning overhead contact system rigid conductor identification method and device for the defectexisting in the prior art. The method or the device can be widely applied to metro line overhead contact system rigid conductor identification in different environments and different lines. Geometrical parameter measurement is finished stably and efficiently. According to the method and the device, an overhead contact system rigid conductor positioning identification method is carried out on images which are collected by linear array cameras and comprise an overhead contact system, thereby obtaining overhead contact system rigid conductor curve information; the overhead contact system rigid conductor curve information is processed based on a gray projection statistical method, thereby obtaining a conductor gray projection curve; conductor gray projection curve information is input into aconductor space distribution model, and the optimum conductor model is obtained according to the Euclidean distance optimum solution; identification is carried out according to the optimum conductor model, thereby obtaining the optimum conductor contour location information; and calculation is carried out based on a binocular vision fundamental principle, thereby obtaining overhead contact systemrigid conductor geometrical parameters.

Description

technical field [0001] The invention relates to the field of catenary image processing, in particular to a self-adaptive learning catenary rigid wire identification method and device. Background technique [0002] The catenary is mainly composed of contact suspension, support device, positioning device, pillar and related infrastructure, etc. It is a special transmission line erected along the railway line. Its function is to provide electric energy for the electric locomotive through the contact between the catenary wire and the pantograph. Therefore, in order to ensure the safety of locomotive driving, to ensure good contact between the pantograph and the catenary line, and to ensure stable current flow, in addition to strict requirements on the design, construction and operation of the contact suspension, it is also necessary to perform status inspections on various facilities and equipment of the catenary. . [0003] There are two state parameters to evaluate catenary ...

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): G06T7/13G06T7/41G06N99/00
Inventor 彭博李想
Owner CHENGDU TANGYUAN ELECTRICAL APPLIANCE
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