Catenary dropper defect detection model training method and defect detection method

A defect detection and model training technology, applied in character and pattern recognition, image data processing, instruments, etc., can solve the problems of low detection efficiency of catenary hanging string defects, easy to miss detection, etc. Sticky and efficient effect

Active Publication Date: 2019-10-08
HENAN SPLENDOR SCI & TECH
View PDF2 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a catenary suspension string defect detection model training method and a defect detection method to solve the problems of low detection efficiency and easy missed detection of catenary suspension string defects

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
  • Catenary dropper defect detection model training method and defect detection method
  • Catenary dropper defect detection model training method and defect detection method
  • Catenary dropper defect detection model training method and defect detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Example of training method for catenary suspension string defect detection model

[0044] Such as figure 1 , figure 2 Shown is the training flowchart of the YOLO-v3 convolutional neural network model and the defect classification convolutional neural network model in this embodiment, and the specific steps are as follows.

[0045] Step 1: sort out the catenary hanging string images collected by the previous equipment inspection trains, prepare corresponding samples to build a sample set according to the main components of the catenary hanging string, expand the sample diversity through data augmentation, and calibrate the samples.

[0046] Among them, the sample size is expanded by means of data augmentation, so that the sample size of each type of sample set is not less than 40,000; the image labeling tool labelImg is used to label the hanging string stay wire, bearing cable clip and contact wire clip.

[0047]Step 2: Determine the convolutional neural network struc...

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 a catenary dropper defect detection model training method and a defect detection method, and belongs to the technical field of catenary fault detection. According to the invention, a contact network dropper defect detection model based on two layers of convolutional neural networks is constructed to extract the image features of a catenary dropper, and the defects of the dropper are classified, by utilizing the advantages of a convolution algorithm, the method is not interfered by the objective conditions, such as the geometrical shapes, the shielding of the dropper, etc., in the image, and compared with a traditional detection mode using manual image watching, the robustness and the efficiency are higher. Meanwhile, on the basis of the characteristics of the dropper, the initial anchor is set by using a clustering algorithm, so that the image detection efficiency and accuracy are improved; in addition, during the defect detection, a corresponding threshold value is set for the output of each layer of model, so that the accuracy of the final dropper defect detection is improved.

Description

technical field [0001] The invention relates to a catenary suspension string defect detection model training method and a defect detection method, which belong to the technical field of catenary fault detection. Background technique [0002] The suspension string is an important part of the catenary system. The status of the catenary is related to the safe operation of the high-speed railway, and regular inspection and maintenance of the catenary system is required. Therefore, troubleshooting and defects have become an indispensable task in the safe operation of the railway. process. At present, the inspection status of the hanging strings by the relevant railway departments mostly adopts the inspection car to take pictures at night to collect images, and confirm the defects manually offline or by simple image analysis. In the face of massive hanging string image data, this defect confirmation method The efficiency is low, the rate of false detection and missed detection is...

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): G06T7/00G06K9/62
CPCG06T7/0004G06T2207/20081G06T2207/20084G06T2207/30164G06F18/241
Inventor 陈召阳申博何秋奇徐伟高程传斌刘大庆
Owner HENAN SPLENDOR SCI & TECH
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap