A method and system for identifying foreign object faults on railway train jumper wires

A technology of fault identification and jumper wires, which is applied in neural learning methods, character and pattern recognition, biological neural network models, etc., can solve problems such as low detection efficiency and poor accuracy, reduce workload, improve detection efficiency, and improve artificial intelligence. The effect of working status

Active Publication Date: 2021-10-01
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the existing problem of low detection efficiency and poor accuracy of manual detection of foreign objects on jumper wires

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
  • A method and system for identifying foreign object faults on railway train jumper wires
  • A method and system for identifying foreign object faults on railway train jumper wires

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0053] Specific implementation mode one: combine figure 1 Describe this embodiment, a method for identifying a foreign object fault on a railway train jumper wire in this embodiment, the method includes the following:

[0054] Step 1. Obtain images containing jumpers on the train;

[0055] Step 2, intercepting the foreign object contour image and the jumper contour image from the image containing the jumper;

[0056] Step 3. Use the styleGAN generator to generate a generated image similar to the foreign object contour image, and use the jumper contour image as the pasting area;

[0057] Step 4. Determine the position to be pasted from the paste area, paste the generated image to the position to be pasted, and use the pasted image as a fault map containing foreign objects;

[0058] Step 5, train the Faster-RCNN network with the fault map containing foreign objects to obtain the training model of Faster-RCNN;

[0059] Step 6. Input the image containing the jumper to be detected...

specific Embodiment approach 2

[0064] Specific embodiment two: present embodiment is to a kind of railway train jumper wire foreign matter fault identification method of specific embodiment one, in step 4, determine the position to be pasted from pasting area, concrete process is:

[0065] Step 41. Acquiring a fault image containing a real foreign object and obtaining a contour line of the outer ring of the foreign object from the image;

[0066] Step 42. Taking each pixel in the paste area as the center, construct the foreign object outer circle contour line obtained in step 41. If the foreign matter outer circle contour line exceeds the pasting area, discard the entire foreign matter outer circle contour line. If the foreign matter outer circle contour line If the contour line does not exceed the pasting area, then keep the entire foreign object outer ring contour line that does not exceed the pasting area;

[0067] Step 43. Select the foreign object outer ring contour line that meets the requirements fro...

specific Embodiment approach 3

[0073] Specific embodiment three: this embodiment is a method for identifying a foreign object fault on a railway train jumper line of the specific embodiment two. In step 41, a fault image containing a real foreign object is obtained and the contour line of the outer ring of the foreign object is obtained from the image, specifically The process is:

[0074] Step 411, acquiring a fault image containing real foreign matter and obtaining a real foreign matter outline from the image;

[0075] Step 412 , making a difference between the expanded real foreign object contour and the unexpanded real foreign object contour, to obtain the foreign object outer circle contour line.

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

A method and system for identifying a foreign object fault on a railway train jumper wire, belonging to the field of fault identification and detection. The purpose of the present invention is to solve the problems of low detection efficiency and poor accuracy in the existing manual detection of foreign objects on jumper wires. Obtain the image containing the jumper on the train; intercept the foreign object contour image and the jumper contour image from the image containing the jumper; use the styleGAN generator to generate a generated image similar to the foreign object contour image, and use the jumper contour image as the pasting area; Determine the position to be pasted from the paste area, paste the generated image to the position to be pasted, and use the pasted image as a fault map containing foreign objects; use the fault map containing foreign objects to train the Faster-RCNN network to obtain the Faster-RCNN Training model; input the image containing the jumper to be detected into the training model of Faster-RCNN, and output the detection result of whether there is a foreign object on the jumper. It is used to detect the presence of foreign objects on jumper wires.

Description

technical field [0001] The invention relates to a method and a system for identifying foreign matter existing on jumper wires, and belongs to the field of fault identification and detection. Background technique [0002] Railway trains are a common means of transportation, and there are a large number of trains running on the line every day. Under the influence of various external environments, failures of various components cannot be avoided. [0003] The foreign object fault of the jumper wire is a fault that endangers driving safety. If the fault is not found in time, it may have serious consequences. At present, it is mainly to use human eyes to search for faults on the whole vehicle. The search range is large, there are many parts, there are many vehicles, and there are many fault forms. Therefore, this work is a mechanical operation with strong repetition, high intensity and fatigue. When workers are tired, it is easy to cause missed inspections and wrong inspections...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/46G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06V20/20G06V10/44
Inventor 蒋弘瑞
Owner HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
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