Paper
6 February 2022 X-ray non-destructive inspection of automobile subframe based on machine learning
Wenhang Dong, Weizhong Hu, Haoqing Niu, Xuechang Zhang, Yongyue Liu
Author Affiliations +
Proceedings Volume 12081, Sixth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2021); 1208114 (2022) https://doi.org/10.1117/12.2624144
Event: Sixth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2021), 2021, Chongqing, China
Abstract
Aiming at the low efficiency of manual detection of X-ray image defects in the production process of casting gearboxes, combined with the machine learning theory in computer vision recognition, a defect detection algorithm based on feature engineering and machine learning is proposed. Through image preprocessing and part X-ray image feature extraction, different feature models are established, and the algorithm is evaluated through different machine learning classifiers. Car subframe products are used for experimental verification. In general, the combination of directional gradient histogram (HOG) and Naive Bayes (GNB) can achieve the best results, with an accuracy rate of 83%. Compared with manual detection, this algorithm effectively improves the classification speed, and the classification accuracy has also been greatly improved, which proves the effectiveness of the proposed algorithm.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wenhang Dong, Weizhong Hu, Haoqing Niu, Xuechang Zhang, and Yongyue Liu "X-ray non-destructive inspection of automobile subframe based on machine learning", Proc. SPIE 12081, Sixth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2021), 1208114 (6 February 2022); https://doi.org/10.1117/12.2624144
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Machine learning

X-rays

X-ray imaging

Defect detection

Inspection

Nondestructive evaluation

Data modeling

Back to Top