18580774. MACHINE LEARNING-BASED POLYMER SURFACE ENERGY PREDICTION SYSTEM (3M INNOVATIVE PROPERTIES COMPANY)

MACHINE LEARNING-BASED POLYMER SURFACE ENERGY PREDICTION SYSTEM

Organization Name

3M INNOVATIVE PROPERTIES COMPANY

Inventor(s)

Richard B. Ross of Cottage Grove MN (US)

Shruti Venkatram of Atlanta GA (US)

MACHINE LEARNING-BASED POLYMER SURFACE ENERGY PREDICTION SYSTEM

This abstract first appeared for US patent application 18580774 titled 'MACHINE LEARNING-BASED POLYMER SURFACE ENERGY PREDICTION SYSTEM

Original Abstract Submitted

A method includes determining a plurality of molecular descriptors, each molecular descriptor of the plurality of molecular descriptors associated with at least one of an atomic scale property, a molecular scale property, and a compound-scale property. The method further includes selecting, by a selection operator and based on a minimization of an error, a subset of the plurality of molecular descriptors that affect a polymer surface energy, training a machine learning model to predict a polymer surface energy of a given polymer based on the subset of molecular descriptors and predicting, via the trained machine learning model, a surface energy of an input polymer.