The extensive use of polypropylene (PP) in various industries has heightened interest in developing efficient methods for recycling and optimising its mixtures. This study focuses on formulating predictive models for the Melt Flow Rate (MFR) and shear viscosity of PP blends. The investigation involved characterising various grades, including virgin homopolymers, copolymers, and post-consumer recyclates, in accordance with ISO 1133 standards. The research examined both binary and ternary blends, utilising traditional mixing rules and symbolic regression to predict rheological properties. High accuracy was achieved with the Arrhenius and Cragoe models, attaining R² values over 0.99. Symbolic regression further enhanced these models, offering significant improvements. To mitigate overfitting, empirical noise and variable swapping were introduced, increasing the models’ robustness and generalisability. The results demonstrated that the developed models could reliably predict MFR and shear viscosity, providing a valuable tool for improving the quality and consistency of PP mixtures. These advancements support the development of recycling technologies and sustainable practices in the polymer industry by optimising processing and enhancing the use of recycled materials.

The extensive use of polypropylene (PP) in various industries necessitates the development of efficient and reliable methods for predicting the mechanical properties of PP compounds. This study presents the development of an analytical model (AM) designed to predict the tensile modulus for a dataset of 64 PP compounds with various fillers and additives, including chalk, impact strength modifiers, and peroxide additives. The AM, incorporating both logarithmic and linear components, was benchmarked against an artificial neural network (ANN) to evaluate its performance. The results demonstrate that the AM consistently outperforms the ANN, achieving lower mean absolute error (MAE) and higher coefficient of determination (R²) values. A maximum R² of 0.98 could be achieved in predicting the tensile modulus. The simplicity and robustness of the AM with its 14 fitting parameters compared to the ~1300 parameters of the ANN make it a useful tool for the plastics industry, providing a practical approach to optimising compound formulations with minimal empirical testing.

The extensive use of polypropylene (PP) in various industries has heightened interest in devel-oping efficient methods for recycling and optimising its mixtures. This study focuses on formu-lating predictive models for the Melt Flow Rate (MFR) and shear viscosity of PP blends. The in-vestigation involved characterising various grades, including virgin homopolymers, copolymers, and post-consumer recyclates, in accordance with ISO 1133 standards. The research examined both binary and ternary blends, utilising traditional mixing rules and symbolic regression to predict rheological properties. High accuracy was achieved with the Arrhenius and Cragoe models, at-taining R² values over 0.99. Symbolic regression further enhanced these models, offering signif-icant improvements. To mitigate overfitting, empirical noise and variable swapping were in-troduced, increasing the models' robustness and generalisability. The results demonstrated that the developed models could reliably predict MFR and shear viscosity, providing a valuable tool for improving the quality and consistency of PP mixtures. These advancements support the de-velopment of recycling technologies and sustainable practices in the polymer industry by opti-mising processing and enhancing the use of recycled materials.

The need for an efficient adaptation of existing polypropylene (PP) formulations or the creation of new formulations has become increasingly important in various industries. Variations in viscosity resulting from changes in raw materials, fillers, and additives can have a significant impact on the processing and quality of PP products. This study presents the development of an analytical model designed to predict the shear viscosity of complex PP blends. By integrating established mixing rules with novel fitting parameters, the model provides a systematic and efficient method for managing variability in PP formulations. Experimental data from binary and multi-component blends were used to validate the model, demonstrating high prediction accuracy over a range of shear rates. The proposed model serves as a valuable tool for compounders and manufacturers to optimise PP formulations and develop new recipes with consistent processing and product quality. Future work will include industrial-scale trials and further evaluation against advanced machine learning approaches.

The extensive use of polypropylene (PP) in various industries necessitates the development of efficient and reliable methods for predicting the mechanical properties of PP compounds. This study presents the development of an analytical model (AM) designed to predict the tensile modulus of PP compounds with various fillers and additives, including chalk, impact strength modifiers, and peroxide additives. The AM, incorporating both logarithmic and linear compo-nents, was benchmarked against an Artificial Neural Network (ANN) to evaluate its performance. The results demonstrate that the AM consistently outperforms the ANN, achieving lower Mean Absolute Error (MAE) and higher Coefficient of Determination (R²) values. The simplicity and robustness of the AM make it a useful tool for the plastics industry, providing a practical approach to optimising compound formulations with minimal empirical testing.

This study investigates the potential of data-driven modeling to monitor and predict mechanical properties of extruded film using recyclates. The first step is to investigate whether a process parameter can indicate the input material quality of the material, which can vary significantly due to the use of recyclate. The die pressure was shown to be a key indicator due to its strong correlation with viscosity and material degradation. The second step is to explore the ability of machine learning models—Generalized Additive Models, Linear Regression, and Random Forest—to predict film tensile strength and modulus based on extrusion process and material parameters. The results demonstrate that including Melt Flow Rate and shear viscosity in addition to pressure and feedstock type (Virgin, PIR, and PCR) significantly improves model accuracy, with Generalized Additive Models achieving the highest R² of 85.7% for tensile strength prediction. Additionally, the observed variability between different recyclate streams highlights the need for a more detailed classification of recyclates to better predict and optimize the mechanical performance of the film. While data-driven approaches for predicting properties show promise, their effectiveness remains limited by data availability and feedstock variability. Expanding datasets and improving process stability will be critical to refining predictive models for industrial application.