Lug piece breakage detection method for high-speed rail overhead line system supporting device based on HOG features and two-dimensional Gabor wavelet transformation

A wavelet transform and ear piece fracture technology, which is applied in instruments, calculations, character and pattern recognition, etc., can solve problems such as low degree of automation and inability to detect component faults, and achieves reduced workload, objective and high detection results. Smart level effects

Inactive Publication Date: 2015-01-14
SOUTHWEST JIAOTONG UNIV
View PDF1 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the degree of automation of existing non-contact detection devices is generally not high, and the fault detection of many parts cannot be realized

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
  • Lug piece breakage detection method for high-speed rail overhead line system supporting device based on HOG features and two-dimensional Gabor wavelet transformation
  • Lug piece breakage detection method for high-speed rail overhead line system supporting device based on HOG features and two-dimensional Gabor wavelet transformation
  • Lug piece breakage detection method for high-speed rail overhead line system supporting device based on HOG features and two-dimensional Gabor wavelet transformation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0051] Training samples are manually intercepted from the catenary support and suspension device images collected earlier. Among them, the positive sample contains the rotated ears, and the rotated ears occupy the main body position in the middle of the image, figure 1 (a) shown. Negative samples randomly contain other catenary components unrelated to the rotating binaural, figure 1 (b) shown. In order to reduce the difference in HOG features caused by "alignment problems", the aspect ratio of positive and negative samples is fixed at 2:1 when intercepting, and the size is normalized to 128×64 pixels (the size of the detection window).

[0052] Extract HOG features for positive and negative samples: first divide the image into several square cells of the same size. Then merge every four adjacent cells into a square block, and the blocks can overlap each other. Use (1)-(4) to calculate the gradient magnitude (m(x,y)) and direction (θ(x,y)) of each pixel, and calculate the g...

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 lug piece breakage detection method for a high-speed rail overhead line system supporting device based on HOG features and two-dimensional Gabor wavelet transformation. According to the method, a rotating double-lug lug piece breakage failure is detected. The method comprises the following steps that a positive and negative sample library of a rotating double-lug body is built firstly; the HOG features of a positive and negative sample are extracted, and a feature descriptor of the sample is generated; on the basis of an AdaBoost algorithm, a Cascade classifier is trained, the trained classifier is utilized for carrying out classification and identification on an area where the rotating double-lug body in an image is located and an area where a non-rotating double-lug body in the image is located, and positioning of the rotating double-lug body in the image is completed; finally, the two-dimensional Gabor wavelet transformation is utilized for screening edge information of the rotating double-lug image, and therefore identification on fault cracks caused by the lug piece breakage failure is carried out. According to the method, a lug piece where the breakage failure happens can be accurately identified in a complex overhead line system hanging device image, and compared with a method of manual screening, the detection efficiency can be greatly improved.

Description

technical field [0001] The invention relates to the technical fields of HOG feature extraction, Cascade cascade classifier training, two-dimensional Gabor wavelet transformation, edge information screening, and ear piece fracture fault identification. Background technique [0002] The rotating lugs are located at the connection of the locator, which is an important load-bearing component in the support structure of the high-speed railway catenary, and plays a vital role in the safe operation of the train. In the actual operation of the railway, the lugs are often broken due to the vibration of the train, resulting in a reduction in the structural strength of the catenary support device, and even the risk of the positioner falling off in severe cases. Therefore, it is necessary to detect the rotating binaural parts, find and replace faulty parts in time. [0003] For a long time, the detection of bad working conditions of catenary components has mainly relied on the method o...

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): G06K9/00G06K9/62
CPCG06F18/2451
Inventor 刘志刚韩烨钟俊平刘文强张桂南
Owner SOUTHWEST JIAOTONG UNIV
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