Rubber sealing ring defect detection method based on deep learning

A rubber sealing ring and deep learning technology, applied in image analysis, image enhancement, instruments, etc., can solve the problems of poor stability of visual inspection method, high detection pressure, easy eye fatigue, etc., achieve accurate model recognition, effective regression, and reduce labor The effect of intensity

Pending Publication Date: 2021-06-25
FOSHAN NANHAI GUANGDONG TECH UNIV CNC EQUIP COOP INNOVATION INST
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to address the deficiencies in the prior art, to provide a method for detecting defects of rubber sealing rings based on deep learning, and to solve the problems of high detection pressure, easy fatigue of the eyes and poor stability of the visual inspection method caused by manual detection in the prior art. Low efficiency and other issues

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
  • Rubber sealing ring defect detection method based on deep learning
  • Rubber sealing ring defect detection method based on deep learning
  • Rubber sealing ring defect detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] Such as Figure 1 to Figure 2 As shown, a deep learning-based rubber sealing ring defect detection method includes the following steps:

[0025] S1. Collect the image data of the rubber sealing ring after mold opening and perform labeling and defect category definition processing to form a training image database, a verification image database and a test image database.

[0026] Wherein, the specific implementation manner of the above-mentioned step S1 is: use the industrial camera to collect the image data of the rubber sealing ring after mold opening, use the labelImg software to label and process the image data of the rubber sealing ring collected to obtain the xml file, and to The image data xml files after labeling and defect category definition processing are classified to form a training image database, a verification image database and a test image database, and generate images corresponding to the training image database, verification image database and test im...

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 rubber sealing ring defect detection method based on deep learning comprises the following steps that image data are collected and marked, defect category definition processing is carried out, and a training image database, a verification image database and a test image database are formed; Establishing a model framework, and training the training image database by using the model framework; S2, performing verification and testing by using the verification image database and the test image database, if the set value is not reached, returning to the step S2 for re-training, If the set value is reached, obtaining a prediction model; S2, testing an output result of the prediction model and feeding back to a rejection mechanism, if the accuracy of the output result is lower than a threshold value, returning to the step S1 to obtain again, If the accuracy of the output result reaches the threshold value, putting into use; According to the invention, the detection work of the rubber sealing ring can be completed in a centralized and high-efficiency manner, the labor intensity is greatly reduced, and the applicability is wide.

Description

technical field [0001] The invention relates to the technical field of automatic visual inspection, in particular to a method for detecting defects of rubber sealing rings based on deep learning. Background technique [0002] As an important industrial product, rubber sealing ring is already a basic component in many industries. Rubber sealing rings have functions such as waterproof, oil-proof, gas-proof, and shock-absorbing, and their quality directly affects the performance and service life of the product, and even threatens personal and property safety. Among all the rubber rings, the O-shaped rubber sealing ring is the most used one, which has simple geometric shape, convenient production and low cost. 1. Uneven cutting, surface damage, grooves, etc. These defects will directly affect the performance of the sealing ring, and will also cause safety problems, causing huge economic losses to the user and the manufacturer. Therefore, before the sealing ring leaves the facto...

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): G06T7/00
CPCG06T7/0004G06T2207/20081G06T2207/20084
Inventor 杨海东李泽辉王华龙
Owner FOSHAN NANHAI GUANGDONG TECH UNIV CNC EQUIP COOP INNOVATION INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap