Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Automation and Machine Learning
  4. Vol 6, Issue 1, 2025

Metal Defect Detection Algorithm Based on Improved YOLOv11

Download as PDF

DOI: 10.23977/autml.2025.060119 | Downloads: 6 | Views: 93

Author(s)

Ruiming Liu 1, Yunliang Du 1, Xuesong Duan 1, Shuai Huang 1, Yong Liu 1, Zhifei Wang 2

Affiliation(s)

1 School of Electronic Engineering, Jiangsu Ocean University, Lianyungang, Jiangsu, China
2 School of Mechanical and Electrical Engineering, Lianyungang Technical College, Lianyungang, Jiangsu, China

Corresponding Author

Yunliang Du

ABSTRACT

In industrial manufacturing, the inspection of metal products holds significant importance due to the detrimental impact defects such as corrosion, welding issues, holes, cracks, among others, can have on the functionality and longevity of metal components. Conventional methods for detecting metal defects suffer from drawbacks including low efficiency, heavy reliance on human intervention, and limited adaptability to complex environments, thereby falling short of the requirements for modern high-precision and automated detection. To address these challenges, this study introduces an enhanced YOLOv11-AAG model, building upon the YOLOv11 framework, aimed at enhancing the precision and effectiveness of metal defect identification. The enhancements to the original YOLOv11 architecture primarily focus on three key areas: feature extraction, feature fusion network, and detector design. Comparative analysis with YOLOv8, Faster R-CNN, and the baseline YOLOv11 model reveals that the YOLOv11-AAG model achieves an average accuracy of 80.3%, surpassing the 77.1% accuracy of the YOLOv11 model by 3.2%.

KEYWORDS

YOLOv11; Defect Detection; Convolution; Feature Fusion

CITE THIS PAPER

Ruiming Liu, Yunliang Du, Xuesong Duan, Shuai Huang, Yong Liu, Zhifei Wang, Metal Defect Detection Algorithm Based on Improved YOLOv11. Automation and Machine Learning (2025) Vol. 6: 170-180. DOI: http://dx.doi.org/10.23977/autml.2025.060119.

REFERENCES

[1] Zhang Wei, Yuan Gaihong, Zhou Tianyi, et al. Review of metal surface defect detection methods for aerospace equipment based on machine learning [J]. Aerospace Electronic Countermeasures, 2025, 41 (03):43-50.
[2] Li Tengyue. Research on surface defect detection algorithm of trigeminal axis based on TS-YOLO [D]. Zhejiang University of Science and Technology, 2024.
[3] Xu Yedong, Cai Yaheng, Li Yan et al. Lightweight overhead transmission line nest detection network based on YOLOv5s [J]. Electronic Measurement Technology, 2024, 47 (7):138-148.
[4] DONG CH, ZHANG K, XIE ZH Y, et al. An improved cascade RCNN detection method for key components and defects of transmission lines[J]. IET Generation, Transmission Distribution, 2023, 17(19): 4277-4292.
[5] Liang D, Ye JM, Zhao K, et al. Machine vision inspection of bearing defects based on data enhancement and SSD [J]. Mechanical Manufacturing, 2025, 63 (04):18-23.
[6] Xu Changdong. Research on Fan Blade Defect Detection Based on Improved YOLO Algorithm [D]. Hubei University for Nationalities, 2025.
[7] Chen Xi. Object Recognition Based on Micro-network Architecture Search [D]. North China University of Technology, 2022.
[8] Hussain M. YOLO-v1 to YOLO-v8, the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection[J]. Machines, 2023, 11(7): 677.
[9] Yang Hang. Research on speed limit sign recognition technology based on machine visi on [D]. Wuhan University of Technology, 2019.
[10] Zhang Xin. Research on UAV Image Target Detection Based on Improved Convolution al Neural Network [D]. Chongqing Normal University, 2024.
[11] Ming Li, Hao Su, Jia Cheng. CFAI-YOLO: an enhanced pedestrian and vehicle detection algorithm based on YOLOv11s[J/OL].Optoelectronics Letters,1-9[2025-08-10].
[12] Tang Feng. Research and Optimization of Industrial Defect Detection Algorithm Based on Deep Learning [D]. University of Electronic Science and Technology, 2025.
[13] Li Hang. Research on multi-scale target detection method based on anchorless frame [D]. Guilin University of Electronic Technology, 2024.
[14] Wang Xinying. Remote sensing image super-resolution reconstruction method based on multi-scale feature adaptive fusion network [D]. Hubei University of Technology, 2020.
[15] Lei Xin. Digital signal processing of lung medical images based on deep learning [D]. University of Electronic Science and Technology, 2024.
[16] Shen H J, Li H Y, Huang Y P, et al. Vehicle detection method based on adaptive mu lti-scale feature fusion network [J/OL]. Journal of Electronics, 1 -9[2025-08-10].
[17] Thammasanya T, Patiam S, Rodcharoen E, et al. A new approach to classifying polym er type of microplastics based on Faster-RCNN-FPN and spectroscopic imagery under ultraviolet light[J]. Scientific reports, 2024, 14(1): 3529.
[18] Tian Wei Zhou, Yu Luo, Guan Hui Yue, et al. Adaptive Mixed-Scale Feature Fusion Network for Blind AI-Generated Image Quality Assessment [J]. IEEE Transactions on Broadcasting, 2024, 70 (3): 1328-1339.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 3947
Visits: 184278

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.