Deteksi Kerusakan Conveyor Belt Real Time Berbasis Yolov11 Edgetpu pada Raspberry Pi 5
DOI:
https://doi.org/10.61124/sinta.v3i1.138Keywords:
conveyor belt, YOLOv11, EdgeTPU, Google Coral, Raspberry Pi 5Abstract
Conveyor belts play a critical role in the cement industry as continuous material transportation systems. Undetected damage such as tear, hole, patch work, and puncture can lead to production downtime, increased maintenance costs, and safety risks. Conventional manual visual inspections are limited in terms of time efficiency, accuracy, and operator subjectivity. This study aims to develop a real-time conveyor belt damage detection system based on deep learning that can be deployed on resource-constrained edge devices. The proposed system employs a YOLOv11 model trained on a combined dataset consisting of field inspection data, public datasets, and automatically collected images, resulting in more than 3,000 augmented training samples. The trained model is converted into TensorFlow Lite format and compiled for Google Coral EdgeTPU to enable efficient deployment on a Raspberry Pi 5 integrated with an RTSP-based IP camera. Training results demonstrate promising performance, achieving a precision of 0.742, recall of 0.730, mAP@50 of 0.764, and mAP@50–95 of 0.553. Implementation in an industrial environment shows stable real-time inference with low latency and reliable detection performance, particularly for the patch work class. The developed system enables continuous and automated conveyor belt condition monitoring, offering potential benefits in reducing downtime and improving maintenance efficiency in industrial applications.
References
A. Rzeszowska, L. Jurdziak, R. Błażej, and P. Lewandowicz, “Analysis of Uncertainty in Conveyor Belt Condition Assessment Using Time-Based Indicators,” Applied Sciences, vol. 15, no. 14, p. 7939, Jul. 2025, doi: 10.3390/app15147939.
X. Guo, X. Liu, H. Zhou, R. Stanislawski, G. Królczyk, and Z. Li, “Belt Tear Detection for Coal Mining Conveyors,” Micromachines (Basel), vol. 13, no. 3, p. 449, Mar. 2022, doi: 10.3390/mi13030449.
W. Liu, Q. Tao, N. Wang, W. Xiao, and C. Pan, “YOLO-STOD: an industrial conveyor belt tear detection model based on Yolov5 algorithm,” Sci Rep, vol. 15, no. 1, p. 1659, Jan. 2025, doi: 10.1038/s41598-024-83619-6.
Y. Hu, Y. Zhang, J. Shen, and G. Wang, “Real-time conveyor belt damage detection method based on improved YOLO,” Engineering Research Express, vol. 7, no. 2, p. 025513, Jun. 2025, doi: 10.1088/2631-8695/adc8fd.
X. Guo et al., “Machine vision based damage detection for conveyor belt safety using Fusion knowledge distillation,” Alexandria Engineering Journal, vol. 71, pp. 161–172, May 2023, doi: 10.1016/j.aej.2023.03.034.
R. Prokscha, M. Schneider, and A. Höß, “Efficient Edge Deployment Demonstrated on YOLOv5 and Coral Edge TPU,” in Industrial Artificial Intelligence Technologies and Applications, New York: River Publishers, 2023, pp. 141–155. doi: 10.1201/9781003377382-11.
A. Ghosh, S. A. Al Mahmud, T. I. R. Uday, and D. Md. Farid, “Assistive Technology for Visually Impaired using Tensor Flow Object Detection in Raspberry Pi and Coral USB Accelerator,” in 2020 IEEE Region 10 Symposium (TENSYMP), IEEE, 2020, pp. 186–189. doi: 10.1109/TENSYMP50017.2020.9230630.
J. Murrugarra-Llerena, L. N. Kirsten, and C. R. Jung, “Can We Trust Bounding Box Annotations for Object Detection?,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun. 2022, pp. 4813–4822.
H. Feng, G. Mu, S. Zhong, P. Zhang, and T. Yuan, “Benchmark Analysis of YOLO Performance on Edge Intelligence Devices,” Cryptography, vol. 6, no. 2, p. 16, Apr. 2022, doi: 10.3390/cryptography6020016.
K.-F. Chen and D.-Y. Hong, “Rewriting Deep Learning Models for Maximizing Edge TPU Utilization,” in 2022 IEEE 28th International Conference on Parallel and Distributed Systems (ICPADS), IEEE, Jan. 2023, pp. 657–664. doi: 10.1109/ICPADS56603.2022.00091.
V. J. Reddi et al., “MLPerf Inference Benchmark,” in 2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA), IEEE, May 2020, pp. 446–459. doi: 10.1109/ISCA45697.2020.00045.
J. Meyer, “Performance with tables and graphs: Effects of training and a visual search model,” Ergonomics, vol. 43, no. 11, pp. 1840–1865, 2000.
S. Afaq and S. Rao, “Significance of epochs on training a neural network,” Int. J. Sci. Technol. Res, vol. 9, no. 06, pp. 485–488, 2020.
M. Zhang, “An Improved Fire Detection Algorithm Based on YOLOv8 Integrated with DGIConv, FourBranchAttention and GSIoU,” HighTech and Innovation Journal, vol. 5, no. 3, pp. 677–689, Sep. 2024, doi: 10.28991/HIJ-2024-05-03-09.
S. S. Ogden and T. Guo, “MDINFERENCE: Balancing Inference Accuracy and Latency for Mobile Applications,” in 2020 IEEE International Conference on Cloud Engineering (IC2E), IEEE, Apr. 2020, pp. 28–39. doi: 10.1109/IC2E48712.2020.00010.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Bijak Bestari, Mulki Indana Zulfa
This work is licensed under a Creative Commons Attribution 4.0 International License.
