EA

Article http://dx.doi.org/10.26855/ea.2023.12.006

Non-destructive Oil Seal Defect Detection Based on Machine Vision

TOTAL VIEWS: 1561

Cheng Lv, Jiaofei Huo*, Mengqi Tian

School of Mechanical Engineering, Xijing University, Xi'an, Shaanxi, China.

*Corresponding author: Jiaofei Huo

Published: January 19,2024

Abstract

Traditional manual oil seal defect detection methods are inefficient and prone to false negatives and false positives. In order to improve the detection efficiency and accuracy, this paper proposes a vision-based oil seal defect detection method. Firstly, an image acquisition system is built to capture oil seal defect images. The images are preprocessed by applying a Gaussian filtering algorithm to smooth the images, and the oil seal images are cropped and position-corrected to be placed at the center. Then, defect region localization and segmentation are performed. Using grayscale difference features, gap and fringe defects are located in the inner lip area of the oil seal, while cut and impact defects are located in the lip region. Finally, defect features are extracted using various algorithms including grayscale linear transformation, histogram equalization, and morphological processing to enhance image features. Defect features are manually selected and then displayed and annotated on the original images. Experimental results demonstrate that this non-destructive detection method exhibits good performance in terms of detection speed, defect detection rate, and false positive rate.

References

[1] Cheng Jinfeng, Fang Guisheng, & Gao Huifang. Research progress on machine vision technology for surface defect detection [J]. Journal of Computer Applications Research, 2023, 40(04): 967-977. DOI: 10.19734/j.issn.1001-3695.2022.08.0426.

[2] Liu Jie, He Zhendong, Wu Zhangliang, et al. Research on online detection system for oil seal defects based on machine vision [J]. Instrumentation Technology and Sensors, 2016(05): 47-50 +88.

[3] Shi Lei & Yu Zhenglin. Research on oil seal defect detection method based on image processing [J]. Journal of Changchun University of Science and Technology (Natural Science Edition), 2021, 44(02): 48-54.

[4] Zhang Guoping, Li Yali, & Xu Xiangyi. Research on the application of image processing technology in oil seal defect detection and recognition [J]. Information Technology and Informatization, 2020(11): 72-73.

[5] Su Hu, Zhang Jiabin, Zhang Bohao, et al. A survey on visual perception-based surface defect detection [J]. Journal of Computer Integrated Manufacturing Systems, 2023, 29(01): 169-191. DOI: 10.13196/j.cims.2023.01.015.

[6] Jiayuan C. Nondestructive testing algorithm of building concrete material defects based on machine learning [J]. Journal of Control and Decision, 2023, 10(2): 143-149.

[7] Zhao Langyue & Wu Yiquan. Research progress on surface defect detection method based on machine vision [J]. Acta Instrumentalis Sinica, 2022, 43(01): 198-219. DOI: 10.19650/j.cnki.cjsi.J2108805.

[8] Zhongkang W L B T. Review of surface defect detection of steel products based on machine vision [J]. IET Image Processing, 2022, 17(2): 303-322.

How to cite this paper

Non-destructive Oil Seal Defect Detection Based on Machine Vision

How to cite this paper: Cheng Lv, Jiaofei Huo, Mengqi Tian. (2023). Non-destructive Oil Seal Defect Detection Based on Machine Vision. Engineering Advances3(6), 469-476.

DOI: http://dx.doi.org/10.26855/ea.2023.12.006