DEVELOPMENT OF A DIGITAL TWIN OF AN INDUSTRIAL BAKERY OVEN BASED ON A HYBRID NEURO-FUZZY CONTROL SYSTEM
DOI:
https://doi.org/10.56132/2791-3368-2026-3-67-203-212Keywords:
digital twin, baking oven, intelligent control, automation, neural network modeling, temperature behavior, machine learningAbstract
The article considers the issue of increasing the efficiency of bread oven control in the context of digitalization of industrial production and the introduction of intelligent control technologies. Such technological solutions are relevant not only for industrial enterprises but also for the digital transformation of logistical support systems, including food production logistics within military infrastructure. The aim of the study is to develop a digital twin of a bread-baking oven based on an intelligent control system that ensures temperature stability and enhances the quality of the finished product. The proposed model integrates methods for predicting technological states with adaptive regulation of process parameters, while accounting for industrial constraints and expert knowledge. A decision-making system is established to enable real-time adjustment of equipment operating modes based on the analysis of large volumes of industrial data. The simulation results demonstrated increased control accuracy, reduced fluctuations in technological parameters, and improved stability of furnace operations. The proposed approach is based on combining fuzzy logic with a multilayer perceptron (MLP). A synthetic dataset was generated using the simulation model to train and test the neural network. The results showed a coefficient of determination (R²) of 0.87 and a mean absolute error (MAE) of 1.92 for the multilayer perceptron with a 4-32-16-2 architecture. The simulation results indicated the potential to increase the time during which technological parameters remain within permissible limits to 92.4%.
Downloads
References
1. Dankar F. K., Ibrahim M. Fake it till you make it: Guidelines for effective synthetic data generation /Applied Sciences. – 2021. – Т. 11. – №. 5. – С. 2158.
2. Suchintita Das R., Tiwari B. K., Garcia-Vaquero M. The fundamentals of bread making: The science of bread //Traditional European breads: An illustrative compendium of ancestral knowledge and cultural heritage. – Cham: Springer International Publishing, 2023. – С. 1-40.
3. Cappelli A., Bettaccini L., Cini E. The kneading process: A systematic review of the effects on dough rheology and resulting bread characteristics, including improvement strategies //Trends in Food Science & Technology. – 2020. – Т. 104. – С. 91-101.
4. Feng Y. et al. Dynamic changes in glutenin macropolymer during different dough mixing and resting processes /Molecules. – 2021. – Т. 26. – №. 3. – С. 541.
5. Vidal L. M. et al. Micro-scale shear kneading—gluten network development under multiple stress–relaxation steps and evaluation via multiwave rheology //Polymers. – 2022. – Т. 14. – №. 4. – С. 846.
6. Issabekova L. et al. Temperature and Humidity Control System Based on Baking Ovens Using Fuzzy Logic //2023 IEEE International Conference on Smart Information Systems and Technologies (SIST). – IEEE, 2023. – С. 573-578.
7. Абалдова С.Ю. Разработка нечеткой экспертной системы оценки управления качеством машиностроительного предприятия // Междунар. научн.-практ. конф. «Инновационное развитие экономики России: ключевые проблемы и решения» - Иваново: ГОУВПО Ивановский государственный химико-технологический университет, 2010. - С. 225-221
8. Valentine D. T., Hahn B. H. Essential MATLAB for engineers and scientists. – Academic Press, 2022.
9. Attaway D. C. Matlab: a practical introduction to programming and problem solving. – Butterworth-Heinemann, 2022.
10. Costa L. et al. Multilayer perception//Introduction to Computational Intelligence. – 2023. – Т. 105.
