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

A method, system and device for detecting a windshield damage fault of a railway train

A fault detection and windshield technology, which is applied in the field of fault detection of windshield damage of railway trains, can solve the problems of blurred images and low accuracy of fault detection, and achieve the effects of reducing blurring, improving detection accuracy, and improving accuracy

Active Publication Date: 2021-08-06
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF1 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 problem of low accuracy of fault detection due to the blurred image obtained by preprocessing the image using the traditional median filter method, and proposes a fault detection method, system and device for windshield damage of railway trains

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, system and device for detecting a windshield damage fault of a railway train
  • A method, system and device for detecting a windshield damage fault of a railway train
  • A method, system and device for detecting a windshield damage fault of a railway train

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0051] Specific implementation mode 1. Combination figure 1 This embodiment will be described. A method for detecting damage to a windshield of a railway motor car according to the present embodiment, the method is specifically implemented through the following steps:

[0052] Step 1. Obtain the passing image of the windshield part of the railway train;

[0053] Step 2, performing equalized median filtering on the image obtained in step 1 to obtain an image after equalized median filtering;

[0054] Step 3, using an edge extraction algorithm to detect the edge features of the image after the equalization median filter;

[0055] Step 4: Input the edge features into the trained SVM network, and output the fault detection result through the trained SVM network.

specific Embodiment approach 2

[0056]Specific implementation mode two: the difference between this implementation mode and specific implementation mode one is: the specific process of step two is:

[0057] The acquired image is scanned using a 3×3 pixel window, and the scanning step is 1 pixel;

[0058] In the pixel window, calculate the median z of the center pixel value of the pixel window and the pixel value of the upper left vertex, the upper right vertex, the lower left vertex, and the lower right vertex of the pixel window 1 ;

[0059] In the pixel window, calculate the median z of the center pixel value of the pixel window and the pixel value of the pixel above the center, the pixel value of the pixel left of the center, the pixel value of the pixel below the center, and the pixel value of the pixel right of the center 2 ;

[0060] use z 1 and z 2 Calculate the balanced median filtering result z of the central pixel of the pixel window; until the pixel window traverses to each position of the acq...

specific Embodiment approach 3

[0062] Specific implementation mode three: the difference between this implementation mode and specific implementation mode two is: use z 1 and z 2 Calculate the equalized median filtering result z of the central pixel of the pixel window; the specific process is:

[0063]

[0064] Wherein, e represents the central pixel value in the pixel window, abs (·) represents the absolute value, mean represents the mean value operation, Med represents the median value operation, and t is a positive threshold, which is 10 in the present invention.

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, system and device for detecting damage to a windshield of a railway motor car, which belong to the technical field of fault detection for windshield damage of a railway motor car. The invention solves the problem that the accuracy of fault detection is low due to the fuzzy image obtained by preprocessing the image using the traditional median filtering method. The present invention adopts a balanced median filtering algorithm to retain the detail information of the image while removing most of the noise, reduce the fuzzy degree of the image, and further improve the accuracy of fault detection. In order to reduce the influence of the threshold selection in the Canny algorithm on the edge feature extraction effect, the present invention proposes a GA-Canny algorithm, which uses a genetic algorithm to find the optimal Canny threshold and improves the detection accuracy of the subsequent detection network. The invention can be applied to the fault detection of the windshield damage of the railway train.

Description

technical field [0001] The invention belongs to the technical field of fault detection for windshield damage of railway motor cars, and in particular relates to a fault detection method, system and device for windshield damage of railway motor cars. Background technique [0002] Most of the traditional fault detection of railway trains adopts the method of manually looking at pictures to check whether there is a fault. The detection cost is high and the efficiency is low, and the detection results are easily affected by the fatigue and experience of the train inspectors. Using a computer to realize the automatic fault detection algorithm can effectively reduce the cost, and at the same time avoid the missed detection and false detection of faults caused by the fatigue of the inspectors, and improve the accuracy of fault detection. However, to realize automatic fault detection by means of computer, it is necessary to preprocess the image by using median filter first, and then...

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): G06T7/00G06K9/46G06K9/62G06N3/12
CPCG06T7/0004G06N3/126G06T2207/20032G06T2207/20081G06T2207/30108G06V10/44G06F18/2411
Inventor 韩旭
Owner HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com