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

Method for judging state of railway wagon coupler knuckle pin based on image recognition and deep learning

A railway wagon, deep learning technology, applied in the direction of neural learning methods, character and pattern recognition, instruments, etc., can solve the problems that failures cannot be found in time, detection results are inaccurate, etc., to reduce labor costs, improve detection efficiency, improve Effects on Robustness and Accuracy

Active Publication Date: 2020-04-28
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF7 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This technology helps detect or identify any tiny objects on an object's surface more efficiently by automatically analyzing images without human interference. It does this through advanced techniques like convolutional neural networks (CNN) that are trained with data from training examples collected beforehand during testing. By doing these things we aim to reduce labor cost while still maintain high-quality results. Additionally, it suggests applying Deep Learning algorithms such as regression analysis to help better determine if there were smaller defects detected within the dataset. Overall, our technical effect will be improved automated imagery processing systems performance and reduced labor requirements compared to current methods.

Problems solved by technology

This patented technical problem addressed in this patents relating to railroad car coupling devices involves improving their ability to detect failures caused due to crackings that may develop into more significant damage if they happen too late after being detected. Current methods involve visual observation from outside sources like engine oil pressure monitoring systems (EBS) or machine vision cameras, but these techniques have limitations because there could also be other causes affecting the performance of the device itself.

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
  • Method for judging state of railway wagon coupler knuckle pin based on image recognition and deep learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0026] Specific implementation mode one: refer to figure 1 This embodiment is specifically described. The method for judging the state of the railway wagon knuckle pin based on image recognition and deep learning described in this embodiment includes the following steps:

[0027] 1. Dataset creation steps:

[0028] Collect coupler pictures of different types of railway wagon couplers at different times, places and environments from large network databases or actual application environments, and then stretch, rotate and mirror each of the collected pictures separately, using before and after transformation Build a sample library for all the pictures of the coupler, the coupler picture includes the coupler picture under the normal state and the coupler picture under the fault state. For example: collect a coupler picture, then copy three identical pictures, and then stretch, rotate and mirror the three copied pictures respectively to obtain the stretched picture, rotated pictur...

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 method for judging a state of railway wagon coupler knuckle pin based on image recognition and deep learning, and relates to the field of railway wagon fault judgment. The objective of the invention is to solve the problem that faults cannot be found in time easily caused by inaccurate detection results when the faults of trucks are detected manually in the prior art. According to the invention, manual detection is replaced by an image automatic identification mode, the fault identification detection efficiency and accuracy are improved, and the labor cost is reduced.Meanwhile, deep learning is applied to part positioning and fault detection, and the robustness and accuracy of the algorithm can be effectively improved. The small target in the image can be effectively positioned and recognized in a mode of performing coarse positioning by adopting the target detection network and then performing recognition in the positioned screenshot, so that the detection accuracy and precision are improved.

Description

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

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
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