This paper presents an intelligent predictive system designed to support real-time decision making in the control of rubber blend mixing processes. The core of the system is a General Regression Neural Network (GRNN), which accurately predicts key process parameters, such as viscosity (expressed as torque), temperature, and energy consumption across varying masses of the processed material. The model can evaluate the mixing progress based on the initial 10% of input data, allowing early intervention and process optimisation. Experimental validation was conducted using a Brabender Plastograph EC Plus with a natural rubber-based blend in the mass range of 60-75 g. The GRNN kernel width parameter (σ) was optimised through a 10-fold cross-validation. High predictive accuracy was confirmed by values of the coefficient of determination (R2) approaching 1, and consistently low values of the root mean square error (RMSE). This system offers a robust and scalable solution for intelligent process control, productivity enhancement, and quality assurance across diverse industrial applications, beyond rubber blending.

Department of Computer Science and Engineering Maharaja Agrasen Institute of Technology GGSIP University New Delhi 110078 India

Department of Electrical Engineering Automation and Informatics Faculty of Engineering Slovak University of Agriculture in Nitra Tr A Hlinku 2 949 76 Nitra Slovakia

Department of Industrial Engineering College of Engineering and Technology American University of the Middle East Egaila 54200 Kuwait

Department of Mechanical Engineering Faculty of Technology Institute of Technology and Business in České Budějovice Okružní 10 370 01 České Budějovice Czech Republic

Department of Numerical Methods and Computational Modelling Faculty of Industrial Technologies in Púchov Alexander Dubček University of Trenčín Ivana Krasku 491 30 020 01 Púchov Slovakia

Zobrazit více v PubMed

Dick J.S. Rubber Technology—Compounding and Testing for Performance. 3rd ed. Hanser; Munich, Germany: 2020.

Wang M.J., Morris M. Rubber Reinforcement with Particulate Fillers. 1st ed. Hanser; Munich, Germany: 2021.

Wypych G. Handbook of Fillers. 5th ed. ChemTec; Toronto, ON, Canada: 2021.

Dick J.S., Pawlowski H. Practical Rubber Rheology and Dynamic Properties. 1st ed. Hanser; Munich, Germany: 2023.

Mark J.E., Erman B., Roland C.M. The Science and Technology of Rubber. 4th ed. Elsevier; Amsterdam, The Netherlands: 2013.

Ahmed I., Poudyal H., Chandy A. Fill Factor Effects in Highly-Viscous Non-Isothermal Rubber Mixing Simulations. Int. Polym. Process. 2019;34:182–194. doi: 10.3139/217.3694. DOI

Shanling H., Wenzheng D., He S., Peng X., Shoudong Z., Long C., Yong L. Real-time rubber quality model based on CNN-LSTM deep learning theory. Mater. Today Commun. 2023;35:106110. doi: 10.1016/j.mtcomm.2023.106110. DOI

Ghoreishy M.H.R. A state-of-the-art review on the mathematical modelling and computer simulation of rubber vulcanization process. Iran. Polym. J. 2016;25:89–109. doi: 10.1007/s13726-015-0405-5. DOI

Kopal I., Labaj I., Vršková J., Harničárová M., Valíček J., Tozan H. Intelligent Modelling of the Real Dynamic Viscosity of Rubber Blends Using Parallel Computing. Polymers. 2023;15:3636. doi: 10.3390/polym15173636. PubMed DOI PMC

Kumar P., Singh S.K. Artificial Neural Networks: A Complete Introduction. 1st ed. Lambert; Saarbrücken, Germany: 2022.

Hammad M.M. Artificial Neural Network and Deep Learning: Fundamentals and Theory. 1st ed. Convex; London, UK: 2024.

Mercioni M.A., Holban S. A Brief Review of the Most Recent Activation Functions for Neural Networks; Proceedings of the 17th International Conference on Engineering of Modern Electric Systems (EMES); Oradea, Romania. 1–2 June 2023; pp. 1–6.

Madhiarasan M., Louzazni M. Analysis of Artificial Neural Network: Architecture, Types, and Forecasting Applications. J. Electr. Comput. Eng. 2022;2022:5416722. doi: 10.1155/2022/5416722. DOI

Krzywanski J., Sosnowski M., Grabowska K., Zylka A., Lasek L., Kijo-Kleczkowska A. Advanced Computational Methods for Modelling, Prediction and Optimisation—A Review. Materials. 2024;17:3521. doi: 10.3390/ma17143521. PubMed DOI PMC

Ye J.C. Geometry of Deep Learning: A Signal Processing Perspective. Springer; Singapore: 2022. Artificial Neural Networks and Backpropagation; pp. 91–112.

Abdolrasol M.G.M., Hussain S.M.S., Ustun T.S., Sarker M.R., Hannan M.A., Mohamed R., Ali J.A., Mekhilef S., Milad A. Artificial Neural Networks Based Optimisation Techniques: A Review. Electronics. 2021;10:2689. doi: 10.3390/electronics10212689. DOI

Goulermas J.Y., Zeng X.-J., Liatsis P., Ralph J.F. Generalized Regression Neural Networks with Multiple-Bandwidth Sharing and Hybrid Optimisation. IEEE Trans. Syst. Man Cybern. B. 2007;37:1434–1445. doi: 10.1109/TSMCB.2007.904541. PubMed DOI

Sadollah A., Travieso-Gonzalez C.M., editors. Recent Trends in Artificial Neural Networks—From Training to Prediction. 1st ed. IntechOpen; London, UK: 2020.

Bratina M., Šušterič Z., Šter B., Lottič U., Dobnikar A. Predictive Control of Rubber Mixing Process Based on Neural Network Models. KGK Kautsch. Gummi Kunstst. 2009;62:378–382.

Golmohammadi M., Aryanpour M. Analysis and evaluation of machine learning applications in materials design and discovery. Mater. Today Commun. 2023;35:105494. doi: 10.1016/j.mtcomm.2023.105494. DOI

Bahiuddin I., Mazlan S.A., Imaduddin F., Shapiai M.I., Ubaidillah, Sugeng D.A. Review of modelling schemes and machine learning algorithms for fluid rheological behaviour analysis. J. Mech. Behav. Mater. 2024;33:20220309. doi: 10.1515/jmbm-2022-0309. DOI

Lukas M., Leineweber S., Reitz B., Overmeyer L., Aschemann A., Klie B., Giese U. Minimising Temperature Deviations in Rubber Mixing Process by Using Artificial Neural Networks. Rubber Chem. Technol. 2024;97:371–379. doi: 10.5254/rct.24.00003. DOI

Park K., Park H., Bae H. A Data-Driven Recipe Simulation for Synthetic Rubber Production. IEEE Access. 2022;10:129408–129418. doi: 10.1109/ACCESS.2022.3228241. DOI

Raj A., Tyagi B., Sharma G.S., Sahai A., Sharma R.S. Optimising the process parameters with statistical and soft computing techniques for enhanced mechanical properties of acrylonitrile butadiene styrene material samples fabricated via fused filament fabrication technique. Prog. Addit. Manuf. 2025;10:2559–2583. doi: 10.1007/s40964-024-00767-x. DOI

Calabia R.O.A., Gomez J.E.D., Lasala I.M., Ligsay C.M.A., Maalihan R.D., Aquino A.P., Sangalang R.H. Epoxidised Philippine natural rubber for tough and versatile 3D printable resins: A mixture design and neural network approach. J. Rubber Res. 2025:1–13. doi: 10.1007/s42464-025-00302-9. DOI

Specht D.F. A general regression neural network. IEEE Trans. Neural Netw. 1991;2:568–576. doi: 10.1109/72.97934. PubMed DOI

Al-Mahasneh A.J., Anavatti S., Garratt, Pratama M. Applications of General Regression Neural Networks in Dynamic Systems. In: Asadpour V., editor. Digital Systems. IntechOpen; London, UK: 2018. pp. 133–154.

Rubber Test Mixes—Preparation, Mixing and Vulcanization: Equipment and Procedures. International Organisation for Standardisation (ISO); Geneva, Switzerland: 2014.

Liu H., Gao N., Meng Z., Zhang A., Wen C., Li H., Zhang J. Construction and Test of Baler Feed Rate Detection Model Based on Power Monitoring. Agronomy. 2023;13:425. doi: 10.3390/agronomy13020425. DOI

Kwaśniewski D., Juliszewski T., Walczyk J., Tylek P., Adamczyk F., Szczepaniak J. Fuel Consumption and Effectiveness of Elimination of Energy-crop Willow Plantation. Agric. Eng. 2017;21:55–63. doi: 10.1515/agriceng-2017-0036. DOI

Kim Y., Kim M.K., Fu N., Liu J., Wang J., Srebric J. Investigating the Impact of Data Normalisation Methods on Predicting Electricity Consumption in a Building Using different Artificial Neural Network Models. Sustain. Cities Soc. 2024;105:105570

Ghosh S. Kernel Smoothing: Principles, Methods and Applications. 1st ed. Wiley; Hoboken, NJ, USA: 2018.

Helias M., Dahmen D. Statistical Field Theory for Neural Networks. 1st ed. Springer; Berlin, Germany: 2020.

Probert M. Machine learning with neural networks: An introduction for scientists and engineers. Contemp. Phys. 2021;62:236–237. doi: 10.1080/00107514.2022.2038687. DOI

Mahlich C., Vente T., Beel J. e-Fold Cross-Validation for energy-aware Machine Learning Evaluations. arXiv. 20242410.09463

Zhao Q., Niu F., Liu J., Yin H. Research Progress of Natural Rubber Wet Mixing Technology. Polymers. 2024;16:1899. doi: 10.3390/polym16131899. PubMed DOI PMC

Du Z., Du Y., Gong Y., Liu G., Li Z., Yu G., Zhao S. Effects of mixing temperature on the extrusion rheological behaviours of rubber-based compounds. RSC Adv. 2021;11:35703–35710. doi: 10.1039/D1RA05929G. PubMed DOI PMC

Payungwong N., Wu J., Sakdapipanich J. Unlocking the potential of natural rubber: A review of rubber particle sizes and their impact on properties. Polymer. 2024;308:127419. doi: 10.1016/j.polymer.2024.127419. DOI

Wang S.Q., Ravindranath S., Wang Y., Boukany P. New theoretical considerations in polymer rheology: Elastic breakdown of chain entanglement network. J. Chem. Phys. 2007;127:064903. doi: 10.1063/1.2753156. PubMed DOI

Patti A., Lecocq H., Acierno D., Cassagnau P. The universal usefulness of stearic acid as surface modifier: Applications to the polymer formulations and composite processing. J. Ind. Eng. Chem. 2021;96:1–33. doi: 10.1016/j.jiec.2021.01.024. DOI

Lin Y., Zhang A., Wang L. Premature vulcanization behaviours of rubber compounds under high shear rates processing. J. Appl. Polym. Sci. 2006;102:5414–5420. doi: 10.1002/app.25053. DOI

Bondarenko A.V., Islamov S.R., Ignatyev K.V., Mardashov D.V. Laboratory studies of polymer compositions for well-kill under increased fracturing. PJPME. 2020;20:37–48. doi: 10.15593/2224-9923/2020.1.4. DOI

Belousov A., Lushpeev V., Sokolov A., Sultanbekov R., Tyan Y., Ovchinnikov E., Shvets A., Bushuev V., Islamov S. Experimental Research of the Possibility of Applying the Hartmann–Sprenger Effect to Regulate the Pressure of Natural Gas in Non-Stationary Conditions. Processes. 2025;13:1189. doi: 10.3390/pr13041189. DOI