Gerçek Zamanlı Yüzey Görüntüleme ve Veri Seti Oluşturma için Prototip Konveyör Bandının Tasarımı ve Üretimi

Öz

Bu çalışmada, katı alüminyum iletkenlerin üretim süreci sırasında meydana gelebilecek yüzey deformasyonlarının görüntülenerek veri seti oluşturulmasına yönelik, konveyör bant tabanlı bir prototip sistem geliştirilmiştir. Sistem, kontrollü aydınlatma ve ayarlanabilir görüş açısına sahip kapalı bir kutuya entegre edilmiş, saniyede 60 kare hızında 1280x1024 piksel çözünürlükte görüntü alabilen yüksek çözünürlüklü bir kamera kullanılarak çalışmaktadır. Görüntüler, sabit hızda ilerleyen konveyör bandı üzerinde toplanmış ve bu sayede görüntü kalitesinde süreklilik sağlanmıştır. Geliştirilen prototip ile toplamda 1.600 görüntü toplanmış ve bu görüntüler, üç farklı kusur tipine ait olacak şekilde manuel olarak etiketlenmiştir. Elde edilen veri seti, ilerleyen aşamalarda çizik, sıyrık, ezilme gibi yüzey kusurlarının derin öğrenme algoritmaları ile tespit ve sınıflandırılmasına olanak sağlayacak şekilde düzenlenmiştir. Bu yönüyle çalışma, alüminyum iletken üretiminde gerçek zamanlı yapay zeka uygulamaları için gerekli olan görsel veri altyapısını sağlamaktadır. Prototipin tasarımı, düşük maliyetli ve kolay temin edilebilir donanımlar kullanılarak gerçekleştirilmiş olup, üretim hatlarına entegre edilebilir yapıda modüler bir sistem sunmaktadır. Bu çalışmanın temel katkısı, gerçek üretim ortamlarına uygun koşullar altında çalışan bir prototip sistemin geliştirilmesidir. Bu sistem, tutarlı ve ölçeklenebilir veri toplamayı mümkün kılan otomatik görüntü toplama yeteneğine sahiptir. Ayrıca, bu çalışma alüminyum iletkenlerdeki yüzey deformasyonlarını tespit etmek için yeni bir veri kümesi sunar. Geliştirilen altyapı, endüstriyel kalite kontrol sistemleri için yapay zeka tabanlı çözümlerin temelini oluşturmayı hedeflemektedir.

Anahtar Kelimeler

• Derin Öğrenme
• Konveyör Sistem
• Hata Tespiti
• Kalite Kontrol
• Yapay Zekâ
• Makine Tasarımı

Design and Production of a Prototype Conveyor Belt for Real-Time Surface Imaging and Data Set Creation

Öz

In this study, a conveyor belt-based prototype system was developed to create a data set by imaging surface deformations that may occur during the production process of solid aluminum conductors. The system operates using a high-resolution camera integrated into a vision inspection box with controlled lighting and an adjustable viewing angle, capable of capturing images at a resolution of 1280×1024 pixels at a rate of 60 frames per second. The images were collected on the conveyor belt moving at a constant speed, thereby ensuring continuity in image quality. With the developed prototype, a total of 1.600 images were collected and manually labeled as examples of three different defect types. The obtained dataset was organized in a way that will enable the detection and classification of surface defects such as pitting, embossing, and scalping using deep learning algorithms in subsequent stages. In this respect, the study provides the visual data infrastructure necessary for real-time artificial intelligence applications in aluminum conductor production. The prototype was designed using low-cost and easily obtainable hardware and offers a modular system that can be integrated into production lines. The main contribution of this study includes the development of a prototype system that operates under conditions suitable for real production environments. This system is equipped with automated image acquisition capabilities, ensuring consistent and scalable data collection. Additionally, this study provides a new dataset for detecting surface deformations in aluminum conductors. The developed infrastructure aims to form the basis for artificial intelligence-based solutions for industrial quality control systems.

Anahtar Kelimeler

• Deep Learning
• Conveyor System
• Defect Detection
• Quality Control
• Artificial Intelligence
• Machine Design

Kaynakça

1. Chen Y, Ding Y, Zhao F, Zhang E, Wu Z, Shao L. Surface defect detection methods for industrial products: A review. Applied Sciences 2021;11:7657.
2. Tercan H, Meisen T. Machine learning and deep learning based predictive quality in manufacturing: a systematic review. Journal of Intelligent Manufacturing 2022;33:1879-905.
3. Wen X, Shan J, He Y, Song K. Steel surface defect recognition: A survey. Coatings 2022;13:17.
4. Liu X, Miao X, Jiang H, Chen J, Chen Z. Fault diagnosis in power line inspection using normalized multihierarchy embedding matching. IEEE Transactions on Instrumentation and Measurement 2023;72:1-10.
5. Senavirathna SK, Udawatte H, Harischandra N, Fernando M, Ekanayake C. Image-based condition monitoring of transmission line conductors using image processing and deep neural networks. In: 2023 IEEE 17th International Conference on Industrial and Information Systems (ICIIS). 2023, p. 388-93.
6. Zhang Y, Li B, Shang J, Huang X, Zhai P, Geng C. DSA-Net: An Attention-Guided Network for Real-Time Defect Detection of Transmission Line Dampers Applied to UAV Inspections. IEEE Transactions on Instrumentation and Measurement 2023.
7. Wei X, Yang Z, Liu Y, Wei D, Jia L, Li Y. Railway track fastener defect detection based on image processing and deep learning techniques: A comparative study. Engineering Applications of Artificial Intelligence 2019;80:66-81.
8. García DF, Usamentiaga R. Rail surface inspection system using differential topographic images. IEEE Transactions on Industry Applications 2021;57:2994-3003.

9. Ge J, Xie S, Wang Y, Liu J, Zhang H, Zhou B, et al. A system for automated detection of ampoule injection impurities. IEEE Transactions on Automation Science and Engineering 2015;14:1119-28.
10. Sun J, Li C, Wu XJ, Palade V, Fang W. An effective method of weld defect detection and classification based on machine vision. IEEE Transactions on Industrial Informatics 2019;15:6322-33.
11. Zhou X, Wang Y, Zhu Q, Mao J, Xiao C, Lu X, et al. A surface defect detection framework for glass bottle bottom using visual attention model and wavelet transform. IEEE Transactions on Industrial Informatics 2019;16:2189-201.
12. Zhang Y, Huang X, Jia J, Liu X. A recognition technology of transmission lines conductor break and surface damage based on aerial image. IEEE Access 2019;7:59022-36.
13. Liu Y, Wang J, Yu H, Li J, Li F, Zhao Q. A non-invasive system for on-line surface defect detection on special-shaped steel towards real production lines. In: 2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). 2022, p. 1-6.
14. Ma Z, Li Y, Huang M, Huang Q, Cheng J, Tang S. Automated real-time detection of surface defects in manufacturing processes of aluminum alloy strip using a lightweight network architecture. Journal of Intelligent Manufacturing 2023;34:2431-47.
15. Bükücü ÇC, Gökrem L. A new prototype that performs real- time error detection in glass products. International Journal of Engineering Research and Development 2020;12:510-9.
16. Akbaş T, Özarslan C, Hacıyusufoğlu AF. Prototip bir marul tohumu temizleme ve sınıflandırma makinasının tasarımı ve imalatı. Anadolu Tarım Bilimleri Dergisi 2020;35:157-66.
17. Zhuxi M, Li Y, Huang M, Huang Q, Cheng J, Tang S. A lightweight detector based on attention mechanism for aluminum strip surface defect detection. Computers in Industry 2022;136:103585.
18. Wang M, Yang L, Zhao Z, Guo Y. Intelligent prediction of wear location and mechanism using image identification based on improved Faster R-CNN model. Tribology International 2022;169:107466.
19. Nguyen HT, Yu G, Shin N, Kwon G, Kwak W, Kim J. Defective Product Classification System for Smart Factory Based on Deep Learning. Electronics 2021;10:826.
20. Lv S, Ouyang B, Deng Z, Liang T, Jiang S, Zhang K, et al. A dataset for deep learning based detection of printed circuit board surface defect. Scientific Data 2024;11:811.
21. Guclu E, Aydin I, Akin E, Akın E. Enhanced defect detection on steel surfaces using integrated residual refinement module with synthetic data augmentation. Measurement 2025;250:117136.
22. Kim B, Shin M, Hwang S. Design and Development of a Precision Defect Detection System Based on a Line Scan Camera Using Deep Learning. Applied Sciences 2024;14:12054.
23. Ren J, Zhang H, Yue M. YOLOv8-WD: Deep Learning-Based Detection of Defects in Automotive Brake Joint Laser Welds. Applied Sciences 2025;15:1184.
24. Pallavi D, Miller S, Gunay E, Jackman J, Kremer GE, Kremer PA. Deep learning-powered visual inspection for metal surfaces– Impact of annotations on algorithms based on defect characteristics. Advanced Engineering Informatics 2024;62:102727.
25. Vijayakumar A, Vairavasundaram S. Yolo-based object detection models: A review and its applications. Multimedia Tools and Applications 2024:1-40.
26. Russell BC, Torralba A, Murphy KP, Freeman WT. LabelMe: a database and web-based tool for image annotation. International Journal of Computer Vision 2008;77:157-73.