No abstract

The glass transition temperature (T g ) is a fundamental property of polymers that strongly influences both mechanical and flow characteristics of the material. In many important polymers, configurational entropy of side chains is a dominant factor determining it. In contrast, the thermal transition in polyurethanes is thought to be determined by a combination of steric and electronic factors from the dispersed hard segments within the soft segment medium. Here, we present a machine learning model for the T g in linear polyurethanes and aim to uncover the underlying physicochemical parameters that determine this. The model was trained on literature data from 43 industrially relevant combinations of polyols and isocyanates using descriptors derived from quantum chemistry, cheminformatics, and solution thermodynamics forming the feature space. Random forest and regularized regression were then compared to build a sparse linear model from six descriptors. Consistent with empirical understanding of polyurethane chemistry, this study indicates the characteristics of isocyanate monomers strongly determine the increase in T g . Accurate predictions of T g from the model are demonstrated, and the significance of the features is discussed. The results suggest that the tools of machine learning can provide both physical insights as well as accurate predictions of complex material properties.

Predicting the properties of complex polymeric materials based on monomer chemistry requires modeling physical interactions that bridge molecular, interchain, microstructure, and bulk length scales. For polyurethanes, a polymer class with global commercial and industrial significance, these multiscale challenges are intrinsic due to the thermodynamic incompatibility of the urethane and polyol-rich domains, resulting in heterogeneities from molecular to microstructural length scales. Machine learning can model patterns in data to establish a relationship between the monomer chemistry and bulk material properties, but this is made difficult by small data sets and a diverse set of monomers. Using a data set of 63 industrially relevant and complex elastomers, we demonstrate that accurate machine learning predictions are possible when monomer chemistry is used to estimate interactions at interchain length scales. Here, these features were used to accurately (r 2 = 0.91) predict the Young’s modulus of polyurethane and polyurethane–urea elastomers. Furthermore, by a query of the trained model for compositions that yield a target modulus within the range of accessible values, the capabilities of using this methodology as a design tool are demonstrated. The presented methodology could become increasingly useful in building models for materials with small data sets and may guide the interpretation of the underlying physicochemical forces.

No abstract

No abstract