DEEP LEARNING-BASED VISION SYSTEM FOR AUTOMATED NIPA PALM FLESH SEPARATOR USING YOLOv11 AND OPC-UA INTEGRATION
DOI:
https://doi.org/10.62985/j.huit_ojs.vol26.no2E.411Keywords:
Nipa palm, PLC, OPC-UA server, YOLOv11Abstract
In line with the trend of sustainable development and the efficient exploitation of natural resources, the demand for processed products derived from agricultural produce is steadily increasing. With advancements in technology, the application of machinery and automation equipment in production has become an essential requirement to enhance productivity and product quality. In this study, the application of the YOLOv11 deep learning model combined with a Mitsubishi FX5U Programmable Logic Controller (PLC) via an OPC Unified Architecture (OPC-UA) server is proposed for a nipa palm flesh separation machine. The image of the nipa palm flesh is fed through the YOLOv11 model for analysis and quality assessment (immature, acceptable, mature). Based on the model's results, the corresponding signal is transmitted to the PLC to control the actuators that perform the separation of the coconut flesh. An OPC-UA intermediate server is used to enable two-way data exchange between the Python program on the computer and the PLC, while also facilitating easy expansion and integration with a monitoring system. The training results of the nipa palm flesh recognition model using YOLOv11 achieved a mAP50 of up to 97.3%. A multi-threading algorithm in Python allows for the simultaneous processing of coconut flesh quality recognition and data exchange with the PLC through the OPC-UA server. The research findings contribute to the construction and development of industrial systems integrated with image processing technology.
References
[1] A. Hassoun, “Food sustainability 4.0: Harnessing fourth industrial revolution technologies for sustainable food systems,” Discover Food, vol. 5, Art. no. 171, 2025, doi: https://doi.org/10.1007/s44187-025-00461-z.
[2] Mekong Agricultural Products, “Nipa palm: A precious gift from the Mekong Delta.” [Online]. Available: https://nongsanmekong.com/dua-nuoc-qua-tang-quy-gia-cua-mien-tay/.
[3] C. M. Badgujar, A. Poulose, and H. Gan, “Agricultural object detection with You Only Look Once (YOLO) algorithm: A bibliometric and systematic literature review,” Computers and Electronics in Agriculture, vol. 223, Art. no. 109090, 2024, doi: https://doi.org/10.1016/j.compag.2024.109090.
[4] T.-L. Le, P.-H. Nguyen, T.-N. Mai, Q.-K. Lam, and S.-T. Tran, “An embedded system with YOLOv5 for automated drug delivery system,” Journal of Technical Education Science, 2026, https://doi.org/10.54644/jte.2025.1758.
[5] G. Peng, K. Wang, J. Ma, B. Cui, and D. Wang, “AGRI-YOLO: A lightweight model for corn weed detection with enhanced YOLO v11n,” Agriculture, vol. 15, Art. no. 1971, 2025, doi: https://doi.org/10.3390/agriculture15181971.
[6] L. T. Ramos and A. D. Sappa, “A comprehensive analysis of YOLO architectures for tomato leaf disease identification,” Scientific Reports, vol. 15, no. 1, Art. no. 26890, 2025, doi: https://doi.org/10.1038/s41598-025-11064-0.
[7] C. M. Badgujar, A. Poulose, and H. Gan, “Agricultural object detection with You Only Look Once (YOLO) algorithm: A bibliometric and systematic literature review,” Computers and Electronics in Agriculture, vol. 223, Art. no. 109090, 2024, doi: https://doi.org/10.1016/j.compag.2024.109090.
[8] S. P. Muniraj and X. Xu, “An implementation of OPC UA for machine-to-machine communications in a smart factory,” Procedia Manufacturing, vol. 53, pp. 52–58, 2021, doi: https://doi.org/10.1016/j.promfg.2021.06.009.
[9] E. Kirdan, F. Rezabek, N. Mülbauer, G. Carle, and M.-O. Pahl, “Real-time performance of OPC UA,” arXiv preprint arXiv:2310.17052, 2023, doi: https://doi.org/10.48550/arXiv.2310.17052.
[10] Z. Luo et al., “OPC UA-based smart manufacturing: System architecture, implementation, and execution,” in Proc. 5th Int. Conf. Enterprise Systems (ES), Beijing, China, 2017, pp. 281–286, doi: https://doi.org/10.1109/ES.2017.53.
[11] N. Holmes, L. Katavich, and X. Xu, “Retrofitting legacy systems for Industry 4.0 via OPC UA and distributed control,” Manufacturing Letters, vol. 44, pp. 1337–1348, 2025, doi: https://doi.org/10.1016/j.mfglet.2025.06.153.
[12] R. Khanam and M. Hussain, “YOLOv11: An overview of the key architectural enhancements,” arXiv preprint arXiv:2410.17725, 2024, doi: https://doi.org/10.48550/arXiv.2410.17725.
