A Machine Vision–Based Automated Wheel Leak Detection System Using Real-Time Object Detection in the Water Leak Testing Process
Abstract
Water leak testing in automotive wheel manufacturing has traditionally relied on manual visual inspection of bubble formation, introducing subjectivity and limiting repeatability in quality assurance processes. This study developed and experimentally validated a real-time leak detection system based on machine vision, directly integrated with an industrial water leak tester platform. A dataset comprising 686 annotated images was constructed from recorded operational testing sequences and partitioned into 80% training and 20% validation subsets. The network was trained for 150 epochs and deployed within an integrated framework incorporating temporal decision logic and automated event logging to ensure deterministic classification under continuous video streaming. Experimental validation was conducted across five scenarios (A–E), including high-leak, low-leak, no-leak, and in-situ operational testing conditions, totaling 100 trials. The aggregated confusion matrix yielded 60 true positives and 40 true negatives with zero false positives and false negatives, resulting in accuracy, sensitivity, specificity, precision, and F1-score values of 1.0 within the evaluated domain. Receiver operating characteristic and precision–recall analyses confirmed strong class separability and stable decision boundaries. Although the results demonstrated high discriminative performance under controlled and operational settings, further large-scale validation under heterogeneous industrial environments is required to fully assess long-term robustness. The proposed framework provided an automated, objective, and real-time inspection solution aligned with Industry 4.0 principles for intelligent manufacturing systems.
Downloads
References
F. Bonollo, N. Gramegna, and G. Timelli, “High-Pressure Die-Casting: Contradictions and Challenges,” JOM, vol. 67, no. 5, pp. 901–908, 2015, doi: 10.1007/s11837-015-1333-8.
R. Bhosale, P. Kumbhar, K. Mahajan, A. Yachkal, and A. Katarkar, “Study on Leak Testing Methods,” IJSRD - International Journal for Scientific Research & Development, vol. 5, no. 1, Feb. 2017.
L. Du, S.-H. Lee, K.-M. Lee, and Y.-S. Choi, “Lightweight CNN’s Superiority in Industrial Defect Detection: A Case Study of Wind Turbine Blades,” Machines, vol. 14, no. 1, 2026, doi: 10.3390/machines14010069.
B. Yoon, H. Lee, and J. Jeong, “Improved U-Net++ with Patch Split for Micro-Defect Inspection in Silk Screen Printing,” Applied Sciences, vol. 12, no. 9, 2022, doi: 10.3390/app12094679.
S. G. Lee, A. M. Gokhale, G. R. Patel, and M. Evans, “Effect of process parameters on porosity distributions in high-pressure die-cast AM50 Mg-alloy,” Materials Science and Engineering: A, vol. 427, no. 1, pp. 99–111, 2006, doi: https://doi.org/10.1016/j.msea.2006.04.082.
B. Zhang, S. Liu, and Y. C. Shin, “In-Process monitoring of porosity during laser additive manufacturing process,” Addit. Manuf., vol. 28, pp. 497–505, 2019, doi: https://doi.org/10.1016/j.addma.2019.05.030.
Y. Yamada et al., “Evaluation of J factor and leakage quality for high pressure die casting applied to closed-deck type cylinder block,” SAE Technical Papers, Mar. 2011, doi: 10.4271/2011-32-0504.
N. Satterlee, E. Torresani, E. Olevsky, and J. Kang, “Automatic detection and characterization of porosities in cross-section images of metal parts produced by binder jetting using machine learning and image augmentation,” J. Intell. Manuf., vol. 35, pp. 1–23, Mar. 2023, doi: 10.1007/s10845-023-02100-9.
Y. Ota, S. Nukaga, Y. Kanda, and M. Furuya, “Explainable Machine Learning for Bubble Leakage Detection at Tube Array Surfaces in Pool,” Applied Sciences, vol. 15, no. 23, 2025, doi: 10.3390/app152312587.
D. Dabholkar, D. Shenvi, N. Anekar, and O. Joshi, “Design of Wet Leak Test Machine for Radiators: A Study,” IJCET, pp. 343–346, Mar. 2016, doi: 10.14741/Ijcet/22774106/spl.4.2016.68.
J. Shi, Y. Chang, C. Xu, F. Khan, G. Chen, and C. Li, “Real-time leak detection using an infrared camera and Faster R-CNN technique,” Comput. Chem. Eng., vol. 135, p. 106780, 2020, doi: https://doi.org/10.1016/j.compchemeng.2020.106780.
P. Gamage and S. Xie, “A real-time vision system for defect inspection in cast extrusion manufacturing process,” in The International Journal of Advanced Manufacturing Technology, Mar. 2008, pp. 240–245. doi: 10.1109/MMVIP.2007.4430750.
Y. Zhao et al., “Attention-Based Multiscale Feature Fusion for Efficient Surface Defect Detection,” IEEE Trans. Instrum. Meas., vol. 73, pp. 1–10, 2024, doi: 10.1109/TIM.2024.3372229.
G. L. R. Caldas, R. M. Moreira, and M. B. de Souza, “Underwater Gas Leak Quantification by Convolutional Neural Network Using Images,” Processes, vol. 13, no. 1, 2025, doi: 10.3390/pr13010118.
A. Jordt-Sedlazeck, C. Zelenka, J. von Deimling, R. Koch, and K. Köser, “The Bubble Box: Towards an Automated Visual Sensor for 3D Analysis and Characterization of Marine Gas Release Sites,” Sensors, vol. 15, pp. 30716–30735, Mar. 2015, doi: 10.3390/s151229825.
M. Fahimipirehgalin, E. Trunzer, M. Odenweller, and B. Vogel-Heuser, “Automatic Visual Leakage Detection and Localization from Pipelines in Chemical Process Plants Using Machine Vision Techniques,” Engineering, vol. 7, no. 6, pp. 758–776, 2021, doi: https://doi.org/10.1016/j.eng.2020.08.026.
U. Galan, P. Orta, T. Kurfess, and H. Ahuett-Garza, “Surface defect identification and measurement for metal castings by vision system,” Manuf. Lett., vol. 15, pp. 5–8, 2018, doi: https://doi.org/10.1016/j.mfglet.2017.12.001.
M. Nikouei et al., “Small object detection: A comprehensive survey on challenges, techniques and real-world applications,” Intelligent Systems with Applications, vol. 27, p. 200561, 2025, doi: https://doi.org/10.1016/j.iswa.2025.200561.
R. C. Hart and A. Conci, “A Computer Vision Approach to Compute Bubble Flow of Offshore Wells,” in Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Science and Technology Publications, Lda, 2024, pp. 664–671. doi: 10.5220/0012433500003660.
C.-Y. Wang, I.-H. Yeh, and H.-Y. M. Liao, “YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information,” Feb. 2024, [Online]. Available: http://arxiv.org/abs/2402.13616
C. Liu, H. Zou, P. Lv, and R. Zhu, “Fabric defect detection method based on multi-scale fusion attention mechanisms,” Meas. Sci. Technol., vol. 36, no. 1, p. 16214, Nov. 2024, doi: 10.1088/1361-6501/ad8be7.
M. Rahimi, A. Alghassi, M. Ahsan, and J. Haider, “Deep Learning Model for Industrial Leakage Detection Using Acoustic Emission Signal,” Informatics, vol. 7, p. 49, Mar. 2020, doi: 10.3390/informatics7040049.
A. Li, R. Hamzah, and S. K. N. A. Rahim, “A chip X-ray image bubble defect detection model combined with Dual-Former attention mechanism,” Measurement, vol. 248, p. 116871, 2025, doi: https://doi.org/10.1016/j.measurement.2025.116871.
