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

A catenary balance line fault detection method based on dhog and discrete cosine transform

A discrete cosine transform and fault detection technology, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as increased vibration frequency of the pantograph-catenary system, and achieve good resistance to scale invariance, good accuracy, and Overcoming the low efficiency of manual inspection

Inactive Publication Date: 2018-03-16
SOUTHWEST JIAOTONG UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the opening of a large number of new railway lines in China, China's railways are entering the operation and maintenance period from the large-scale construction period; in addition, due to the high-density operation of EMUs, the vibration frequency of the pantograph-catenary system has increased significantly, which poses a threat to the operation and maintenance of the catenary. brought a severe test

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 catenary balance line fault detection method based on dhog and discrete cosine transform
  • A catenary balance line fault detection method based on dhog and discrete cosine transform
  • A catenary balance line fault detection method based on dhog and discrete cosine transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The embodiment of the present invention will be described in further detail below in conjunction with the actual pictures taken in the experiment.

[0062] combine figure 1 Shown: the detection flowchart of the method proposed in this paper of the present invention.

[0063] The main steps are as follows: firstly, the DHOG feature needs to be extracted from the image of the sample library, on this basis, the AdaBoost classifier is trained and the precise positioning of the balance line and its support is given; secondly, the discrete cosine transform is used to analyze the target feature information of the balance line and its support Enhancement; then based on the arc segment fitting, the circle in the image is detected and counted, and the fault criterion is given according to the statistical number, and finally the fault judgment of the missing balance line of the high-speed rail catenary is realized.

[0064] figure 2 It is a partial image of the high-speed railw...

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 catenary balance line fault detection method based on DHOG and discrete cosine transform. The method includes two processes of identification and positioning of the balance line and its support and fault detection of the absence of the balance line: 1) The identification and positioning of the balance line and its support first needs to extract the DHOG features of the positive and negative samples, and then use the AdaBoost classifier to perform Training; then use the trained classifier to accurately judge whether the sliding detection window contains the target area. 2) The fault detection of the lack of balance line first uses discrete cosine transform to enhance the target feature information of the balance line and its support, and then uses the two-step method of circle detection based on arc segment fitting to count the circles in the image, according to The number of circles finally gives the fault judgment that the catenary balance line is missing. The method of the invention has a high detection accuracy rate, and still has good robustness in the case of rotation and scale changes of the target image, and provides a certain technical reference for the intelligent patrol inspection of the high-speed railway catenary.

Description

technical field [0001] The invention relates to the field of electrified railway detection, in particular to a catenary balance line fault detection method based on DHOG and discrete cosine transform. Background technique [0002] With the opening of a large number of new railway lines in China, China's railways are entering the operation and maintenance period from the large-scale construction period; in addition, due to the high-density operation of EMUs, the vibration frequency of the pantograph-catenary system has increased significantly, which poses a threat to the operation and maintenance of the catenary. brought a severe test. In order to ensure the safety of catenary equipment, it is necessary to carry out effective detection and status monitoring of catenary. In July 2012, the former Ministry of Railways promulgated the "Overall Technical Specifications for High-speed Railway Power Supply Safety Inspection and Monitoring System (6C System)". The power supply equi...

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): G06K9/62
CPCG06F18/24G06F18/214
Inventor 高仕斌刘志刚张桂南
Owner SOUTHWEST JIAOTONG UNIV
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