This paper presents the development and evaluation of a four-layer intelligent control and management system for oil production technological processes in real time, applied to cottonseed and sunflower oil refining lines. The proposed system integrates a 148-sensor IoT network (sampling frequency: 100 ms), a Digital Twin module, and three machine learning models: an LSTM neural network for deodorization temperature and energy consumption forecasting (RMSE = 1.8 °C; R² = 0.94), a Random Forest classifier for raw material quality categorization (accuracy: 94.3%), and a Reinforcement Learning agent for multi-objective optimization of energy consumption, product quality, and equipment wear. A hybrid adaptive control algorithm combining PID, ML feed-forward, and Model Predictive Control (MPC) is formulated and validated on three years of production data (n = 2,847,000 observations). Comparative testing against traditional PID-based systems demonstrated an 18–27% reduction in energy consumption, a 14.6% improvement in the product quality index, an 82.9% improvement in deodorization temperature control accuracy (from ±8.2 °C to ±1.4 °C), and a 61.7% reduction in unscheduled equipment shutdowns. The Digital Twin module enables predictive maintenance with an average fault-detection lead time of 72 hours and reduces electricity costs by 8–12% through virtual scenario planning. The system automatically identifies oil type and enforces oil-specific regulatory temperature limits in compliance with EU 2023/2229 glycidyl ester standards. Integration of heat recovery, enzymatic degumming, and RL-based energy management achieves a total reduction of 35–55% in specific energy consumption across all oil types.
Development of An Intellectual Control and Management System for Oil Production Technological Processes in Real-Time
DOI:
Keywords:
Abstract
References
Setyawardhani D.A. et al. Innovative approach to vegetable oil refining: improving energy efficiency // Discover Food. — 2025. — Vol. 5(1). — Art. 12. doi:10.1007/s44187-025-00246-6
Lidu S.R. et al. Evaluation of energy saving opportunities for palm oil refining process // Chemical Engineering Transactions. — 2016. — Vol. 52. — P. 751–756. doi:10.3303/CET1652126
An H., Ma Y., Wang X., Zheng Y. Effects of Deodorization on the Formation of Processing Contaminants and Chemical Quality of Sunflower Oil // Journal of Oleo Science. — 2022. — Vol. 71(7). — P. 975–984. doi:10.5650/jos.ess22050
Gharby S. et al. Refining Vegetable Oils: Chemical and Physical Refining // Scientific World Journal. — 2022. — Art. 6627013. doi:10.1155/2022/6627013
Lee J., Davari H., Singh J., Pandhare V. Industrial Artificial Intelligence for Industry 4.0-based Manufacturing Systems // Manufacturing Letters. — 2018. — Vol. 18. — P. 20–23. doi:10.1016/j.mfglet.2018.09.002
Zheng P. et al. Smart manufacturing systems for Industry 4.0: Conceptual framework, scenarios and future perspectives // Frontiers of Mechanical Engineering. — 2018. — Vol. 13. — P. 137–150. doi:10.1007/s11465-018-0499-5
Grieves M., Vickers J. Digital Twin: Mitigating Unpredictable, Undesirable Emergent Behavior in Complex Systems // Transdisciplinary Perspectives on Complex Systems. — 2017. — P. 85–113. doi:10.1007/978-3-319-38756-7_4
Panjapornpon C. et al. Reinforcement learning-based energy management in palm oil industry // Discover Food. — 2024. — Vol. 4(1). — Art. 18. doi:10.1007/s44187-024-00193-w
Hochreiter S., Schmidhuber J. Long Short-Term Memory // Neural Computation. — 1997. — Vol. 9(8). — P. 1735–1780. doi:10.1162/neco.1997.9.8.1735
Sampaio K.A. et al. Enzymatic degumming of corn oil using phospholipase C // Journal of Food Engineering. — 2019. — Vol. 243. — P. 138–143. doi:10.1016/j.jfoodeng.2018.09.009
Chew S.C. et al. Optimization of Degumming Parameters in Chemical Refining Process // Separation and Purification Technology. — 2017. — Vol. 188. — P. 248–254. doi:10.1016/j.seppur.2017.07.033
Wen C. et al. Edible vegetable oils: preparation, refining, identification of adulteration // Trends in Food Science & Technology. — 2023. — Vol. 140. — Art. 104165. doi:10.1016/j.tifs.2023.104165
Oey S.B. et al. Chemical refining methods mitigate 2-MCPD, 3-MCPD and glycidyl esters // Food Research International. — 2022. — Vol. 157. — Art. 111243. doi:10.1016/j.foodres.2022.111243
Zhao S. et al. Life Cycle Carbon Footprint in Edible Vegetable Oils // Sustainable Chemistry and Pharmacy. — 2025. — Vol. 44. — Art. 101926. doi:10.1016/j.scp.2025.101926
Ramanath T. et al. Carbon emission analysis for edible oil refinery decarbonization // Journal of Cleaner Production. — 2023. — Vol. 385. — Art. 135664. doi:10.1016/j.jclepro.2022.135664
Tivanello R.G. et al. Effects of deodorization temperature on 3-MCPD and glycidyl esters in palm oil // Journal of Food Science. — 2020. — Vol. 85(12). — P. 4259–4268. doi:10.1111/1750-3841.15530
Yıldız K., Özdikicierler O. The Trend in Mitigation Strategies of 3-MCPD and Glycidyl Esters in Edible Vegetable Oils // Food Technology and Biotechnology. — 2024. — Vol. 62(3). — P. 326–345. doi:10.17113/ftb.62.03.24.8260
Jamoussi B. et al. Thermomechanical Autovaporization (MFA) as a New Process for Vegetable Oil Deodorization // Foods. — 2022. — Vol. 11(3). — Art. 339. doi:10.3390/foods11030339
Oey S.B. et al. Ultrasound-assisted bleaching of vegetable oils // Ultrasonics Sonochemistry. — 2021. — Vol. 72. — Art. 105419. doi:10.1016/j.ultsonch.2020.105419