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

Image recognition method and system for bearing saddle dislocation faults of railway freight cars based on deep learning

A deep learning, railway freight car technology, applied in neural learning methods, image analysis, image data processing, etc., can solve problems such as low accuracy and low efficiency, achieve efficiency improvement, high flexibility, and save dynamic vehicle inspection personnel. Effect

Active Publication Date: 2020-08-21
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to solve the problems of low efficiency in the current detection method relying on manual viewing of images, and the problem of low accuracy in detection by the existing automatic image processing technology

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
  • Image recognition method and system for bearing saddle dislocation faults of railway freight cars based on deep learning
  • Image recognition method and system for bearing saddle dislocation faults of railway freight cars based on deep learning
  • Image recognition method and system for bearing saddle dislocation faults of railway freight cars based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0054] Specific implementation mode one: combine figure 1 To describe this embodiment,

[0055] This embodiment is a deep learning-based image recognition method for bearing saddle dislocation faults of railway freight cars.

[0056] Before carrying out the image recognition of the dislocation fault image of the bearing saddle of the railway freight car, it is necessary to establish a deep learning network model, including the following steps:

[0057] 1. Create a sample data set

[0058] Set up high-definition image acquisition equipment around the truck track respectively, and acquire high-definition images after the truck passes through the equipment. The images are sharp grayscale images. As truck components may be affected by rain, mud stains, oil stains, black paint and other natural or man-made conditions, and the images taken at different sites may be different. Therefore, bearer saddle images vary widely. Therefore, in the process of collecting saddle image data,...

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 deep learning-based image recognition method and system for bearing saddle dislocation faults of railway freight cars belongs to the technical field of freight train detection. The present invention aims to solve the problems of low efficiency in the current detection method relying on manual viewing of images, and the problem of low detection accuracy in the existing automatic image processing technology. The invention uses a U-shaped deep learning network to predict the image to be detected, predicts the bearing saddle contour area, and obtains the predicted binary image; determines the upper edge line of the bearing saddle outline area according to the binary image, and passes the angle of the upper edge straight line Change to judge whether it is a fault: if the upper edge linear angle deviation is greater than the preset threshold, a fault alarm will be issued for this part of the bearing saddle; if the upper edge linear angle deviation is less than or equal to the set threshold, the next step will be processed. Zhang bears saddle images. The invention is mainly used for bearing saddle dislocation fault image recognition.

Description

technical field [0001] The invention relates to a fault image recognition method for bearing saddle dislocation of railway freight cars. The invention belongs to the technical field of freight train detection. Background technique [0002] The dislocation fault of the truck saddle is a kind of fault that endangers the safety of driving. In the fault detection of the saddle, the existing method is to manually check the image for fault detection. Because the inspectors are prone to fatigue, omissions and other situations during the work process, resulting in missed inspections and wrong inspections, which seriously affect driving safety. [0003] Existing saddle dislocation fault detection of trucks is done manually. In theory, automatic image recognition can also be used for detection, so that missed detection and false detection can be avoided, and detection efficiency and stability can also be improved theoretically. However, the existing deep learning models are all desi...

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): G06T7/00G06T7/12G06N3/08G06N3/04
CPCG06T7/0002G06T7/12G06N3/08G06N3/045
Inventor 孟德剑
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