Polyurethanes synthetized with polyols of distinct molar masses: Use of the artificial neural network for prediction of degree of polymerization

Abstract

The molar mass of the polyurethanes (PUs)' reagents directly influences their thermal response, affecting both the polymerization process and the enthalpy and the degree of reaction. This study reports applying an artificial neural network (ANN), associated with surface response methodology (SRM) models, to predict the calorimetric behavior of certain PU's bulk polymerizations. A noncatalyzed reaction between an aliphatic hexamethylene diisocyanate (HDI) and a polycarbonate diol (PCD) with distinct molar masses (500, 1000, and 2000 g/mol) was proposed. A high level of reliability of the predicted calorimetric curves was obtained due to an excellent agreement between theoretical and modeled results, enabling creating a 3D surface response to predict the reaction kinetics. Also, it was possible to observe that the polymerization kinetics is affected by the OH group's association phenomena. The applied methodology can be extended for other materials or properties of interest.

Experimental and artificial neural network approach for prediction of dynamic mechanical behavior of sisal/glass hybrid composites

“…Fitted plot, residual plot, and regression plot were produced for all samples. The surface response methodology (SRM) followed the same procedure as previous studies 20,21 using ANN prediction data.…”

Application of the Artificial Neural Network (ANN) Approach for Prediction of the Kinetic Parameters of Lignocellulosic Fibers

“…With the network training, we can feed the network with different curves and predicted new curves. The main drawback is that the curves outside the lower and higher heating rate cannot be created due to the accumulation of errors [22,23].…”

Polymer Reaction Engineering meets Explainable Machine Learning

“…In the glass transition temperature and other properties of polymers were evaluated and the performance of ensemblelearning methods (e.g., random forest, XGBoost), neural networks and other regression methods was compared. Various ML methods (including random forest and XGBoost) were applied to predict the conversion and molar mass distribution using multi-target regression (Curteanu, Leon, Mircea-Vicoveanu, & Logofătu, 2021;Da Tan et al, 2022;Dall Agnol, Ornaghi, Monticeli, Dias, & Bianchi, 2021;Ghiba, Drăgoi, & Curteanu, 2021).…”