Affiliation:
1. School of Electronic lnformation and Electrical Engineering, Yangtze University, Jingzhou 434100, China
Abstract
In the field of industrial inspection, accurate detection of thread quality is crucial for ensuring mechanical performance. Existing machine-vision-based methods for internal thread defect detection often face challenges in efficient detection and sufficient model training samples due to the influence of mechanical geometric features. This paper introduces a novel image acquisition structure, proposes a data augmentation algorithm based on Generative Adversarial Networks (GANs) to effectively construct high-quality training sets, and employs a YOLO algorithm to achieve internal thread defect detection. Through multi-metric evaluation and comparison with external threads, high-similarity internal thread image generation is achieved. The detection accuracy for internal and external threads reached 94.27% and 93.92%, respectively, effectively detecting internal thread defects.
Reference46 articles.
1. The US Aerospace Industry: A Manufacturing Powerhouse;Soshkin;Bus. Econ.,2016
2. Dang, D., and Wang, J. (2021, January 29–31). Surface Defect Detection Using Singular Value Decomposition. Proceedings of the 2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE), Yunlin, Taiwan.
3. Evolutionary Image Thresholding for Image Segmentation;Int. J. Comput. Vis.,2019
4. A Review of Feature Extraction Methods on Machine Learning;Suhaidi;J. Inf. Syst. Technol. Manag.,2021
5. Alhija, H., Azzeh, M., and Almasalha, F. (2022). Software Defect Prediction Using Support Vector Machine. arXiv.