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

Railway wagon brake beam body breaking fault image identification method

A technology for railway wagon and image recognition, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as omission, low detection efficiency, and fatigue, and achieve the effects of improving detection efficiency, segmentation speed, and accuracy

Inactive Publication Date: 2020-04-28
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF10 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the inspectors are prone to fatigue and omissions during the work process, resulting in low detection efficiency, a fault image recognition method for the breakage of the brake beam of railway freight cars is proposed.

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
  • Railway wagon brake beam body breaking fault image identification method
  • Railway wagon brake beam body breaking fault image identification method
  • Railway wagon brake beam body breaking fault image identification method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0048] Specific embodiment one: reference Figure 1 to Figure 3 To describe this embodiment in detail, the method for recognizing the broken image of the brake beam body of a railway freight car according to this embodiment includes the following steps:

[0049] Step 1: Obtain the high-definition linear array image of the passing truck and establish a sample data set;

[0050] Step 2: Perform data amplification on the sample data set;

[0051] Step 3: Mark the images in the data set;

[0052] Step 4: Generate a data set from the original image and labeled data for model training;

[0053] Step 5: Cut out the part area to be recognized from the image;

[0054] Step 6: Position the beam body part of the brake beam, determine the recognition range, and use the U-NET network to segment the image;

[0055] Step 7: After filtering and image processing the U-NET network segmentation results based on prior knowledge, the image is cropped and spliced;

[0056] Step 8: Input the cropped and spliced ...

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 railway wagon brake beam body breaking fault image recognition method, relates to the technical field of freight train detectio. In order to solve the problem that fault detection is carried out by adopting a manual image checking mode, the detection efficiency is low caused by fatigue and omission of vehicle inspection personnel in the working process in the prior art, manual detection is replaced by an automatic image recognition mode, and the detection efficiency and accuracy are improved. A deep learning algorithm is applied to brake beam body breaking fault automatic identification, and the stability and precision of the overall algorithm are improved. The U-NET model is optimized, the prediction time is shortened, and the segmentation speed is improved. A feature extractor of the SSD is changed into a combination of Resnet50 and FPN from VGG16, overall features and local features are fused through multi-scale target detection, and the precision of a single-stage target detection algorithm SSD in the aspect of small-scale target detection is improved.

Description

Technical field [0001] The invention relates to the technical field of detection of freight trains, in particular to a method for identifying broken images of brake beams of railway freight cars. Background technique [0002] The brake beam is the most important part of the basic braking device of a railway vehicle. When the vehicle is braking, the braking force is transmitted to the brake shoe through the brake beam to stop the vehicle from moving forward. The failure of the brake beam body to break will directly affect the driving safety. Once the failure is found, it needs to be stopped and repaired in time. The traditional brake beam station uses manual image inspection for fault detection. As the inspectors are prone to fatigue and omissions during the work process, missed inspections and wrong inspections occur, which affect driving safety. However, image processing and deep learning methods are used to automatically identify the brake beam broken fault. Manually only nee...

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): G06K9/00G06K9/62
CPCG06V20/10G06F18/241G06F18/214
Inventor 高恩颖
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