Kopal Ivan, Labaj Ivan, Vršková Juliána, Harničárová Marta, Valíček Jan, Bakošová Alžbeta, Tozan Hakan, Khanna Ashish
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.
Department of Electrical Engineering, Automation and Informatics, Faculty of Engineering, Slovak University of Agriculture in Nitra, Tr. A. Hlinku 2, 949 76 Nitra, Slovakia.
Polymers (Basel). 2025 Jul 3;17(13):1868. doi: 10.3390/polym17131868.
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 (R) 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.
本文提出了一种智能预测系统，旨在支持橡胶共混物混合过程控制中的实时决策。该系统的核心是广义回归神经网络（GRNN），它能准确预测关键工艺参数，如粘度（以扭矩表示）、温度以及不同质量加工材料的能耗。该模型可根据输入数据的前10%评估混合进度，从而实现早期干预和工艺优化。使用布拉本德塑度仪EC Plus对质量范围为60 - 75克的天然橡胶基共混物进行了实验验证。通过10折交叉验证对GRNN核宽度参数（σ）进行了优化。决定系数（R）值接近1以及均方根误差（RMSE）始终较低，证实了该模型具有较高的预测准确性。该系统为智能过程控制、提高生产率和质量保证提供了一个强大且可扩展的解决方案，适用于橡胶共混以外的各种工业应用。
