On line identification method of forming defects of small module plastic gears

Zhaoyao Shi; Yiming Fang; Huixu Song

doi:10.1117/12.2611910

19 November 2021 On line identification method of forming defects of small module plastic gears

Zhaoyao Shi, Yiming Fang, Huixu Song

Proceedings Volume 12059, Tenth International Symposium on Precision Mechanical Measurements; 120590Q (2021) https://doi.org/10.1117/12.2611910
Event: Tenth International Symposium on Precision Mechanical Measurements, 2021, Qingdao, China

Abstract

Due to its anisotropic shrinkage characteristics and the instability of forming process, small module plastic gears are easy to produce complex appearance defects after forming. The traditional manual detection can not accurately identify all kinds of defects, let alone complete the full inspection and statistical analysis. Therefore, a prototype of small module plastic gear on-line detection and sorting system based on machine vision is developed. The system has the function of on-line classification and identification of plastic gear surface defects, and can realize full inspection. The watershed algorithm based on local extreme value and Canny edge extraction algorithm can accurately extract the gear defect area, mark the defect location and count the defect characteristics, complete the determination of defects such as size out of tolerance, shrinkage, burr, surface foreign matter and incompletely filled part in 0.3s, and display the defect location through the human-computer interaction interface, with a discrimination accuracy of 95%.

Citation Download Citation

Zhaoyao Shi, Yiming Fang, and Huixu Song "On line identification method of forming defects of small module plastic gears", Proc. SPIE 12059, Tenth International Symposium on Precision Mechanical Measurements, 120590Q (19 November 2021); https://doi.org/10.1117/12.2611910

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available