Abstract
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 (R(2)) values. A maximum R(2) 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.