US 12,327,617 B2
Hybrid machine learning methods of training and using models to predict formulation properties
Fabio Aguirre Vargas, Lake Jackson, TX (US); Sukrit Mukhopadhyay, Midland, MI (US); Jerome Claracq, Ghent (BE); Bart Rijksen, Middelburg (NL); Valeriy V. Ginzburg, Midland, MI (US); Paul Cookson, Cheadle (GB); Alix Schmidt, Midland, MI (US); and Shachit Shankaran Iyer, Pearland, TX (US)
Assigned to Dow Global Technologies LLC, Midland, MI (US)
Filed by Dow Global Technologies LLC, Midland, MI (US)
Filed on Dec. 20, 2022, as Appl. No. 18/085,318.
Prior Publication US 2024/0203537 A1, Jun. 20, 2024
Int. Cl. G16C 20/30 (2019.01); G16C 20/70 (2019.01)
CPC G16C 20/30 (2019.02) [G16C 20/70 (2019.02)] 20 Claims
OG exemplary drawing
 
1. A method of training a machine learning module to predict one or more target product composition properties for a prospective polyurethane chemical formulation, comprising:
(a) constructing or updating a training data set from variable parameters comprising at least one selected from each of:
(i) one or more of chemical components and process conditions,
(ii) one or more polyurethane specific descriptors, and
(iii) the one or more target product composition properties;
(b) performing feature selection on the training data set to determine a subset of driving variable parameters for calculating the one or more target product properties, wherein the subset of driving variable parameters comprises at least one polyurethane specific descriptor;
(c) building one or more machine learning models using one or more model architectures and analyze the training data set and subset of driving variable parameters used in calculating the one or more target product properties, wherein the subset of driving variable parameters comprises at least one selected from a group consisting of hydroxyl number for polyols, isocyanate index, weight averaged solids content in polyol, total amount of additives, primary hydroxyl content of polyols, and total amount of crosslinkers;
(d) validating the one or more machine learning models by inputting a testing data set and determining an associated error for the one or more machine learning models calculating the one or more target product properties;
(e) selecting at least one of the one or more machine learning models and generating prediction intervals for the one or more machine learning models;
(f) interpreting the one or more machine learning models and analyzing the one or more target product properties calculated by the one or more machine learning models;
(g) determining if the one or more target product properties calculated by the one or more machine learning models are acceptable based on pre-defined criteria; and
(h) deploying one or more trained machine learning models;
wherein the method is performed by one or more processors.