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

Rail wagon floor damage fault detection method

A railway freight car and fault detection technology, which is applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve the problems of high detection cost and low detection accuracy, so as to overcome the high detection cost, improve the accuracy rate, and reduce the detection rate. cost effect

Active Publication Date: 2021-01-22
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF13 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem of high detection cost of the traditional automatic fault detection method based on deep learning, and the low detection accuracy of the traditional automatic fault detection method based on feature extraction, and proposes a fault detection for railway wagon floor damage method

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
  • Rail wagon floor damage fault detection method
  • Rail wagon floor damage fault detection method
  • Rail wagon floor damage fault detection method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0013] Specific implementation mode 1. Combination figure 1 This embodiment will be described. A method for detecting a floor damage fault of a railway freight car according to the present embodiment, the method is specifically implemented through the following steps:

[0014] Step 1, collect the passing image of the railway freight car, and obtain the image of the region of interest from the collected passing image;

[0015] Step 2, setting a candidate frame for frame-selecting the floor on the image of the region of interest to obtain a candidate frame image;

[0016] Step 3, extracting the contrast energy feature, color energy feature and SHIFT feature of the candidate frame image obtained in step 2;

[0017] Step 4. Concatenate the contrast energy feature, color energy feature and SHIFT feature extracted in step 3, input the concatenation result into the trained SVM classification network, and the trained SVM classification network outputs the detection result of the flo...

specific Embodiment approach 2

[0021] Embodiment 2: This embodiment differs from Embodiment 1 in that: when the output result of the trained SVM classification network is that the floor is damaged, a fault alarm will be uploaded.

[0022] Otherwise, the detection result output by the SVM classification network is that the floor is not damaged, and then continue to collect the next image for detection.

specific Embodiment approach 3

[0023] Embodiment 3: This embodiment is different from Embodiment 1 in that: when setting a candidate frame for selecting a floor on the ROI image, the method adopted is to select a search algorithm.

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 rail wagon floor damage fault detection method, and belongs to the technical field of rail wagon floor damage fault detection. According to the invention, the problems of high detection cost of the traditional fault automatic detection method based on deep learning and low detection accuracy of the traditional fault automatic detection method based on feature extraction are solved. The invention provides a contrast energy feature extraction algorithm, which is used for extracting contrast energy features of an image, extracting color energy features in the image according to the characteristic that floor color blackening occurs in the image due to a floor damage fault, and combining the color energy features with the contrast energy features and SHIFT features toperform fault detection. When the detection cost is reduced, the fault detection accuracy is improved. The method can be applied to rail wagon floor damage fault detection.

Description

technical field [0001] The invention belongs to the technical field of fault detection for the floor damage of railway freight cars, and in particular relates to a fault detection method for floor damage of railway freight cars. Background technique [0002] In the traditional fault detection of floor damage of railway freight cars, most of them use the method of manually viewing the images of passing vehicles for fault detection, which has low detection efficiency, high labor costs, and is prone to false detections due to the influence of the experience and fatigue of the inspectors. Problems with missed detection. Using computer fault automatic detection method can improve the efficiency and accuracy of fault detection of floor damage and reduce the cost of fault detection. The automatic fault detection method can be roughly divided into the automatic fault detection method using deep learning and the automatic fault detection method using traditional feature extraction. ...

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
IPC IPC(8): G06K9/32G06K9/46G06K9/62
CPCG06V10/25G06V10/56G06F18/2411
Inventor 韩旭
Owner HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com