Unlock instant, AI-driven research and patent intelligence for your innovation.

Axle defect recognition model construction method and defect recognition method based on machine vision

A defect identification and machine vision technology, applied in the direction of instruments, scientific instruments, measuring devices, etc., can solve problems such as low efficiency, accuracy and consistency of defect identification, and affect production efficiency, so as to meet the requirements of reducing quality and experience and realize Automated analysis, the effect of accurate automated analysis

Active Publication Date: 2020-06-09
BEIJING SHEENLINE GRP CO LTD
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Defect judgment results largely depend on the quality and experience of the inspectors, which can easily lead to missed judgments, misjudgments, and low efficiency; limited by the quality and experience of inspectors, different inspectors may have inconsistent analysis results for the same inspection data, resulting in It is impossible to provide accurate basis for decision-making; in addition, due to the increasing number of rail transit rolling stock and various types of vehicle axles, the contradiction between the increase in wheel axle inspection tasks and the insufficient number of inspection personnel has become increasingly acute; the insufficient number of inspection personnel limits the efficiency of non-destructive testing operations, which is not conducive to Rapid inspection of a large number of axles, thereby affecting production efficiency
At the same time, the existing automatic analysis methods for wheel axle flaw detection cannot meet the requirements of wheel axle flaw detection workmanship, accuracy and consistency of defect identification

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
  • Axle defect recognition model construction method and defect recognition method based on machine vision
  • Axle defect recognition model construction method and defect recognition method based on machine vision
  • Axle defect recognition model construction method and defect recognition method based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] refer to figure 1 : A method for building a machine vision-based wheel axle defect recognition model, comprising the following steps:

[0036] Step S100, using the ultrasonic flaw detection equipment to acquire the detection data of the axle, and storing the detection data in a binary file.

[0037] Due to the different geometric features of the wheel rim, web, rim and hollow shaft, the methods of flaw detection are also different, resulting in different detection images. Ultrasonic axle flaw detection equipment obtains the detection data of axle components according to different shaft or wheel types, configures corresponding channels and scanning methods, and stores the detection data in the form of binary files in the upper computer of the flaw detection equipment. The binary files contain position, amplitude , detection parameters, images and other information.

[0038] The channels are probes, and each channel is a probe, and each probe scans according to a certai...

Embodiment 2

[0054] refer to figure 2 : a machine vision-based wheel axle defect recognition method, comprising the following steps:

[0055] Step Z100, using the ultrasonic flaw detection equipment to obtain the detection data of the wheel axle, storing the detection data in a binary file, and extracting the detection image from the binary file.

[0056] This step is the same as in Embodiment 1, and will not be repeated here.

[0057] Step Z200, using the defect recognition model to perform defect recognition on the inspection image.

[0058] After the processing program loads the defect recognition model, input the detection image, the defect lower limit (the lower limit of the pixel size of the target image), the upper limit of the defect (the upper limit of the pixel size of the target image), stepping (the ratio of image division to a certain size), neighborhood (the number of hits ) and other parameters, the computer automatically matches and recognizes defects and outputs defect ...

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 relates to an axle defect recognition model construction method and defect recognition method based on machine vision. According to the axle defect recognition model construction method,a defect recognition model is constructed based on a machine vision technology, and the accuracy of defect recognition is continuously improved through continuous autonomous learning and training; meanwhile, the machine vision is not limited by personnel experience and quality, the defect recognition accuracy, the operation efficiency and the operation quality are greatly improved, and misjudgment and missed judgment of defects are effectively reduced. The recognition method comprises the following steps: carrying out defect identification by utilizing the defect recognition model; screeningthe identified defects; displaying the screened defects and giving an alarm; and continuously perfecting the defect recognition model by utilizing new defect data.

Description

technical field [0001] The invention is applicable to the field of ultrasonic nondestructive flaw detection, and in particular relates to a machine vision-based method for building a wheel axle defect recognition model and a defect recognition method. Background technique [0002] At present, ultrasonic testing is used for axle flaw detection, with manual analysis of testing data as the main means. The results of the ultrasonic inspection of the wheel axle are displayed in the form of A display, B display, and C display, and then the above-mentioned displayed images are observed by human eyes to judge whether the wheel axle is defective. Defect judgment results largely depend on the quality and experience of the inspectors, which can easily lead to missed judgments, misjudgments, and low efficiency; limited by the quality and experience of inspectors, different inspectors may have inconsistent analysis results for the same inspection data, resulting in It is impossible to p...

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 Applications(China)
IPC IPC(8): G01N29/04
CPCG01N29/048Y02P90/30
Inventor 张旭亮刘士超谭鹰庞龙
Owner BEIJING SHEENLINE GRP CO LTD
Features
  • R&D
  • 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