Development of a Smart Monitoring System for Palm Oil Processing Using Internet of Things Technology
Keywords:
internet of things, palm oil mill, smart monitoringAbstract
Palm oil mills operate with limited real-time visibility of their own processes, so that deviations in temperature, level, throughput, and product quality are typically detected through periodic laboratory analysis rather than as they occur. This paper develops a system architecture for Internet of Things based monitoring of palm oil processing and specifies the design requirements that distinguish workable installations from those that fail after commissioning. The study followed a design research approach in which functional requirements were elicited from published mill-level monitoring implementations indexed in Scopus and SINTA, an architecture was synthesised, and evaluation criteria were derived and applied analytically to the proposed design. The resulting architecture comprises four tiers: instrumentation at the unit operation, edge acquisition and local control, a communication and integration layer, and an analytics and visualisation layer. The review of existing implementations indicates that sensing at the continuous settling tank, sterilizer, boiler, and effluent pond is technically straightforward with low-cost microcontroller hardware, but that sensor linearity outside a narrow measurement range, the absence of calibration procedures, and the lack of integration with existing supervisory control systems repeatedly limit operational value. The paper argues that the binding design constraint in this application is not connectivity but measurement traceability, and proposes that any deployment specify calibration intervals, acceptable measurement ranges, and a defined action for each monitored variable before hardware is selected.
References
Abubakar, A., & Ishak, M. Y. (2024). Exploring the intersection of digitalization and sustainability in oil palm production: Challenges, opportunities, and future research agenda. Environmental Science and Pollution Research, 31, 50036–50055. https://doi.org/10.1007/s11356-024-34535-9
Akhtar, M. N., Ansari, E., Alhady, S. S. N., & Abu Bakar, E. (2023). Leveraging on advanced remote sensing- and artificial intelligence-based technologies to manage palm oil plantation for current global scenario: A review. Agriculture, 13(2), 504. https://doi.org/10.3390/agriculture13020504
Booneimsri, P., Kubaha, K., & Chullabodhi, C. (2018). Increasing power generation with enhanced cogeneration using waste energy in palm oil mills. Energy Science & Engineering, 6(3), 154–173. https://doi.org/10.1002/ese3.196
Fakhruddin, & Priayanto, W. (2024). Implementation of IoT-based optical sensors for real-time monitoring in palm oil processing. Jurnal Inotera, 9(2), 482–489.
Ibrahim, Z., Sabri, N., & Isa, D. (2018). Palm oil fresh fruit bunch ripeness grading recognition using convolutional neural network. Journal of Telecommunication, Electronic and Computer Engineering, 10(3–2), 109–113.
Rizal, H. S., & Dachyar, M. (2021). Internet of Things technology selection for palm oil mill maintenance. In Proceedings of the International Conference on Industrial Engineering and Operations Management (pp. 2124–2131). IEOM Society International.
Rosbi, M., Omar, Z., Khairuddin, U., Majeed, A. P. P. A., & Bakar, S. A. R. S. A. (2024). Machine learning for automated oil palm fruit grading: The role of fuzzy C-means segmentation and textural features. Smart Agricultural Technology, 9, 100691.
Savaş, S. (2024). Application of deep ensemble learning for palm disease detection in smart agriculture. Heliyon, 10(17), e37141. https://doi.org/10.1016/j.heliyon.2024.e37141
Saidur, R., Ahamed, J. U., & Masjuki, H. H. (2010). Energy, exergy and economic analysis of industrial boilers. Energy Policy, 38(5), 2188–2197. https://doi.org/10.1016/j.enpol.2009.11.087
Suharjito, Elwirehardja, G. N., & Prayoga, J. S. (2021). Oil palm fresh fruit bunch ripeness classification on mobile devices using deep learning approaches. Computers and Electronics in Agriculture, 188, 106359. https://doi.org/10.1016/j.compag.2021.106359
Suharjito, Junior, F. A., Koeswandy, Y. P., Debi, Nurhayati, P. W., Asrol, M., & Marimin. (2023). Annotated datasets of oil palm fruit bunch piles for ripeness grading using deep learning. Scientific Data, 10, 72. https://doi.org/10.1038/s41597-023-01958-x
