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

A damage detection method for truck bearings

A technology for damage detection and bearings, applied in the direction of neural learning methods, image data processing, biological neural network models, etc., can solve the problems of low accuracy, long time consumption, low efficiency, etc., to improve efficiency, improve operation quality, and flexibility high effect

Active Publication Date: 2021-01-01
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF11 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 long time-consuming and low efficiency in manual detection of truck bearing damage, and the problem of low accuracy in image-based detection of truck bearing damage

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 damage detection method for truck bearings
  • A damage detection method for truck bearings
  • A damage detection method for truck bearings

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0038] The implementation of a method for detecting damage to a truck bearing described in this embodiment is divided into two stages: a training stage and an inference stage.

[0039] 1. Training phase, such as figure 1 Shown:

[0040] 1.1. Image Collection

[0041] Use a line-scan camera, that is, a line-scan camera, to collect images, calculate the shooting frequency of the line-scan camera based on the moving speed of the measured object, and take multiple consecutive pictures, and combine the multiple "strip" images taken In this way, seamless splicing can be realized to generate a two-dimensional image with a large field of view and high precision.

[0042] 1.2. Coarse positioning of the target area

[0043] According to the prior information such as the wheelbase of the truck and the location of the bearing area of ​​the truck, the bearing area of ​​the truck is determined from the two-dimensional image and the image of the bearing area of ​​the truck is extracted, s...

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 damage detection method for freight car bearings, which belongs to the technical field of freight train detection. The invention aims to solve the problems of long time consumption and low efficiency in manual-based truck bearing damage detection and low accuracy in image-based truck bearing damage detection. The present invention collects images and extracts images corresponding to the truck bearing area as the image of the truck bearing area to be identified; inputs the image of the truck bearing area to be identified into the trained Mask-RCNN network for speculation, and obtains the prediction of each picture The results include: multiple ROI categories, frame coordinates, segmentation coordinates, and confidence scores; combined with the prior information of the fault location and the bearing auxiliary category information, the confidence score of the fault is further realized to detect the damage of the truck bearing. It is mainly used for damage detection of truck bearings.

Description

technical field [0001] The invention relates to a method for detecting damage to a truck bearing. The invention belongs to the technical field of freight train detection. Background technique [0002] Railway wagons have always played an important role in transportation, and the railway department needs to conduct safety inspections on railway wagons frequently to ensure the safe and stable operation of railway wagons. In the detection of railway freight cars, in order not to affect the normal running and scheduling of railway freight cars, and in order to improve the detection efficiency, most of them currently rely on manual inspection of images for detection, which will consume a lot of labor costs and time costs. Moreover, this detection technology completely relies on the sense of responsibility and energy of the inspectors. Once too many images are viewed, the detection error rate and missed detection rate will increase significantly. [0003] In the routine inspecti...

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): G06T7/00G06K9/32G06K9/54G06K9/62G06N3/04G06N3/08
CPCG06T7/0008G06N3/08G06T2207/10004G06T2207/20081G06T2207/20084G06T2207/20104G06V10/25G06V10/20G06N3/045G06F18/241G06F18/214
Inventor 庞博
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