Integration of Neural Networks and First-Principles Model for Optimizing l-Lactide Branched Polymerization.

Abstract

Addressing the growing demand for sustainable materials, this research paves the way for the efficient consumption and sustainable production of branched polylactide (PLA). A novel hybrid modeling approach combines first-principles (FP) model with artificial neural network (ANN) for ring-opening polymerization (ROP). The hybrid ANN, trained with FP model data, demonstrated optimal performance with a hidden layer of 20 neurons, achieving a root mean square error (RMSE) of 0.004 and a regression coefficient (R²) of 0.99. The hybrid model accurately predicted key polymer properties, including average molecular weights (Mn and Mw), polydispersity index (PDI), degree of branching (DB), monomer conversion, and polymerization time. Validation was performed on various branched PLA compositions (PLLH80, PLLH94, and PLLH97). Multiobjective optimization (MOO) using NSGA-II showed strong agreement between FP model and hybrid ANN across six case studies, highlighting their effectiveness in predicting polymerization outcomes.