IJET 2025 Vol.17(1): 40-43
DOI: 10.7763/IJET.2025.V17.1299
Automated Hanging and Mounting System for Batches of Electroplated Components based on YOLO Machine Vision Technology
Chien-Hui Lee1,2, Min-Chi Chiu3,
and
Pei-Hsing Huang1
1. Department of Mechanical Engineering, National Yunlin University of Science and Technology, Yunlin, Taiwan
2. Department of Intelligent Manufacturing, Ling Tung University, Taichung, Taiwan
3. Department of Multimedia Design, National Taichung University of Science and Technology, Taichung, Taiwan
Email: ltu11105@teamail.ltu.edu.tw (C.H.L.); minky413@nutc.edu.tw (M.C.C.)
*Corresponding author
Manuscript received September 15, 2024; revised October 27, 2024; accepted December 15, 2024; published February 25, 2025.
Abstract—This study presents an innovative industrial electroplating automated hanging system aimed at addressing critical challenges prevalent in traditional manufacturing processes, such as labor shortages and high employee turnover. The system integrates TensorFlow and Keras deep learning frameworks, employing the YOLO (You Only Look Once) machine vision recognition model alongside existing image processing techniques. This integration signifies a significant reduction in reliance on manual labor and introduces automation through the incorporation of robotic arms, marking a pivotal advancement in the field of intelligent machinery. Following extensive training and testing on a dataset of 512 target images, the system achieved impressive results: an average precision rate of 97.05%, a recall rate of 100%, an F1 score of 1.00, and an average precision mean average precision of 97.05%. The deployment of a custom C# control interface further enhances operational efficiency and strengthens user interaction, facilitating seamless coordination between software and mechanical systems. Despite a slightly lower production efficiency compared to manual operation, with a throughput of 14 items per minute, the automated assembly system boasts continuous 24-hour operation capability and offers a potential solution to Taiwan's widespread labor shortage issue. The system is projected to recoup its investment within approximately six months if operated continuously for 24 hours a day. Despite its relatively lower production efficiency, the system's continuous operation and economic benefits underscore its significant value. This research not only highlights the potential of the YOLO algorithm in industrial automation but also elucidates the profound impact of deep learning technologies in overcoming labor dependency challenges in traditional industrial environments. Furthermore, the study emphasizes the importance of advanced technologies such as machine learning and robotics in modern industrial processes, offering opportunities for the realization of more sustainable, efficient, and cost-effective manufacturing solutions.
Keywords—deep learning, YOLO algorithm, machine vision, electroplated components, intelligent machinery
Cite: Chien-Hui Lee, Min-Chi Chiu, and Pei-Hsing Huang, "Automated Hanging and Mounting System for Batches of Electroplated Components based on YOLO Machine Vision Technology,"
International Journal of Engineering and Technology, vol. 17, no. 1, pp. 40-43, 2025.
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
