A detection method for the bad state of the pins of the rotating double-ear part of the high-speed railway catenary
A technology of rotating binaural, bad state, applied in image data processing, instruments, computing and other directions, can solve the problems of difficulty, hysteresis of fault judgment, large fault detection, etc., to achieve simplification difficulty, high correct detection rate, and simple state detection. Effect
Inactive Publication Date: 2017-05-17
SOUTHWEST JIAOTONG UNIV
View PDF5 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
But there are also the following problems: heavy workload, low efficiency, and large lag in fault judgment
Because the images of catenary support and suspension devices collected on site are generally complex, it is difficult to use image processing technology to detect faults in small components such as rotating double-ear pins, and there are no relevant reports on this aspect of research.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0053] Embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings.
[0054] figure 1 It is a process block diagram of the method of the present invention. figure 2 Shows the position of the pin in the field-collected image, highlighting the difficulty of detecting such a small part.
[0055] A. Positioning and extraction of rotating binaurals
[0056] a. Select a clear and complete rotating binaural template image. The SIFT feature operator is not only invariant to image scaling, rotation and brightness changes, but also can adapt to a certain degree of affine transformation, viewing angle changes and noise. Use it to extract the feature points of the binaural template image and the catenary image collected on site, and use the 128-dimensional feature vector A i and B i Describe, and then calculate the Euclidean distance U of each feature vector in the two images to measure their similarity. When the follo...
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
Login to View More Abstract
The invention discloses a method for detecting the bad state of a pin of a rotating double-ear part of a high-speed rail catenary. It includes the following steps: first select a relatively clear and complete rotated binaural template image, use the SIFT algorithm to extract the feature points of the binaural template image and the image collected on the spot and make a match, and then use the improved RANSAC algorithm to eliminate the mismatch to obtain an affine transformation matrix , position and rotate the binaural; secondly, use Hough transform to extract the inclination angle of the binaural sleeve in the field collected image, and rotate it to the horizontal direction, and then realize the segmentation of the rotated binaural part; then, accumulate the vertical angle of the field collected image The gray value of the pixel in the direction determines the length of the stressed part of the pin and the non-stressed part at both ends; finally, the range of the relative ratio between these lengths when the pin works normally and when it fails is summarized, so as to judge the working state of the pin.
Description
technical field [0001] The invention relates to the field of high-speed railway catenary fault detection, in particular to a method for detecting the bad state of catenary rotating double-ear pins based on image processing. Background technique [0002] In the high-speed railway catenary suspension device, the rotating double-ear pin is one of the important fasteners. Due to construction defects or vibration and impact during the long-term operation of the EMU, catenary components may loosen and fall off, and the poor state of the pins also brings hidden dangers to the safe operation of the EMU. This puts forward higher requirements for the structural stability of the catenary support device, and it is necessary to detect pin failures and take measures to eliminate hidden dangers. The 4C system technical specification promulgated by the former Ministry of Railways includes high-definition video monitoring of the suspension part and arm part of the catenary, and involves the...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00
CPCG06T7/0004G06T7/001G06T2207/10004G06T2207/20021G06T2207/20024G06T2207/20132G06T2207/30164G06T2207/30168G06T2207/30236G06T2207/30252
Inventor 高仕斌刘志刚钟俊平张桂南刘文强
Owner SOUTHWEST JIAOTONG UNIV