INCREASING THE PREDICTION ACCURACY OF PLANT OIL PRODUCTION PROCESSES THROUGH ADJUSTING THE PARAMETERS OF MACHINE LEARNING MODELS

Authors

• Umidjon Ruziev, Tashkent State Technical University. Address: University street 2, 100095, Tashkent city, Republic of Uzbekistan. E-mail: umidruziev7@gmail.com.Follow
• M.K. Shodiev, Tashkent State Technical University. Address: University street 2, 100095, Tashkent city, Republic of Uzbekistan;
• A.T. Rajabov, Tashkent State Technical University. Address: University street 2, 100095, Tashkent city, Republic of Uzbekistan;

Abstract

Vegetable oil production is characterized by high variability in output indicators due to nonlinear interactions between raw material parameters, equipment modes, and heat and mass transfer conditions. Existing approaches to applying machine learning in this field, as a rule, do not account for the impact of hyperparameter adjustments on forecasting quality across specific technological stages. The article presents a systematic methodology for adjusting model parameters (Ridge regression, SVR, GBM, LSTM) applied to three key tasks: predicting residual oil content in oil cake, color index during bleaching, and free fatty acid content during deodorization. In a set of 1000 observations, including technological, energy, and laboratory indicators, it is shown that adjusting hyperparameters improves forecast quality compared to basic model configurations; the best results were obtained for Gradient Boosting and LSTM.

First Page

52

Last Page

58

References

1. Chew, S.C., Tan, C.P., Nyam, K.L. (2017). RSM for optimizing deodorization parameters in kenaf seed oil. Separation and Purification Technology. 188.
2. Oey, S.B., Goh, K.M., Ngoh, G.C. (2022). Chemical refining methods mitigate 2-MCPD, 3-MCPD and glycidyl esters. Food Research International, 157.
3. Chen, T., Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, California, USA. 785-794. DOI:10.1145/2939672.2939785
4. Lundberg, S.M., Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. arXiv preprint arXiv:1705.07874. doi:10.48550/arXiv.1705.07874
5. Hwang, J., Choi, K., Jeong, S., Lee, S. (2024). Machine learning identification of edible vegetable oils from fatty acid compositions and hyperspectral images. Current Research in Food Science. 8.
6. Jamoussi, B., Abderrabba, M., Hadrich, B. (2022). Deodorization of soybean oil using thermomechanical autovaporization. Journal of Food Engineering, 315.
7. Mu, Y., Zhang, L., Wang, X. (2025). Phospholipase A1 degumming in edible fat systems. LWT. 197.
8. Jamoussi, B., Abderrabba, M., Hadrich, B. (n.d.). Thermomechanical Autovaporization (MFA) as a New Process for Vegetable Oil Deodorization. Foods. 11.
9. Ruziev, U.A. et all. (2026). Innovative approach to vegetable oil refining: improving energy efficiency. American Journal of Applied Science and Technology, 5(1). doi:10.1007/s44187-025-00246-6
10. Bergstra J., Bengio Y. (2012). Random Search for Hyper-Parameter Optimization. JMLR. 13, 281-305.
11. Fouladvand, S., Noshad, M., Goldstein, M.K., Periyakoil, V.J., Chen, J.H. (2023). Mild cognitive impairment: Data-driven prediction, risk factors, and workup. AMIA Summits on Translational Science Proceedings AMIA Summit on Translational Science. 167–175. doi:10.1145/2939672.2939785.

Recommended Citation

Ruziev, Umidjon; Shodiev, M.K.; and Rajabov, A.T. (2026) "INCREASING THE PREDICTION ACCURACY OF PLANT OIL PRODUCTION PROCESSES THROUGH ADJUSTING THE PARAMETERS OF MACHINE LEARNING MODELS," Chemical Technology, Control and Management: Vol. 2026: Iss. 2, Article 7.
DOI: https://doi.org/10.59048/2181-1105.1780