Development of structure–property relationships that allow independent control of glass transition temperature, melting temperature, and rheology in a library of bio-based succinate polyester polyols

Polymer ◽  
2017 ◽  
Vol 114 ◽  
pp. 103-112 ◽  
Author(s):  
Alan K. Schrock ◽  
Heather S.C. Hamilton ◽  
Baylen D. Thompson ◽  
Kenneth Ulrich ◽  
Cathlene del Rosario ◽  
...  
Keyword(s):  
Glass Transition ◽  
Transition Temperature ◽  
Glass Transition Temperature ◽  
Melting Temperature ◽  
Structure Property ◽  
Independent Control ◽  
Structure Property Relationships ◽  
Temperature Melting

scholarly journals Comparison of Machine Learning Methods towards Developing Interpretable Polyamide Property Prediction

Polymers ◽  
2021 ◽  
Vol 13 (21) ◽  
pp. 3653
Author(s):  
Franklin Langlang Lee ◽  
Jaehong Park ◽  
Sushmit Goyal ◽  
Yousef Qaroush ◽  
Shihu Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Glass Transition ◽  
Transition Temperature ◽  
Glass Transition Temperature ◽  
Melting Temperature ◽  
Linear Models ◽  
Chemical Properties ◽  
Tensile Modulus ◽  
Rotational Degree ◽  
Structure Property

Polyamides are often used for their superior thermal, mechanical, and chemical properties. They form a diverse set of materials that have a large variation in properties between linear to aromatic compounds, which renders the traditional quantitative structure–property relationship (QSPR) challenging. We use extended connectivity fingerprints (ECFP) and traditional QSPR fingerprints to develop machine learning models to perform high fidelity prediction of glass transition temperature (Tg), melting temperature (Tm), density (ρ), and tensile modulus (E). The non-linear model using random forest is in general found to be more accurate than linear regression; however, using feature selection or regularization, the accuracy of linear models is shown to be improved significantly to become comparable to the more complex nonlinear algorithm. We find that none of the models or fingerprints were able to accurately predict the tensile modulus E, which we hypothesize is due to heterogeneity in data and data sources, as well as inherent challenges in measuring it. Finally, QSPR models revealed that the fraction of rotatable bonds, and the rotational degree of freedom affects polyamide properties most profoundly and can be used for back of the envelope calculations for a quick estimate of the polymer attributes (glass transition temperature, melting temperature, and density). These QSPR models, although having slightly lower prediction accuracy, show the most promise for the polymer chemist seeking to develop an intuition of ways to modify the chemistry to enhance specific attributes.

Structure-Property Relationships in Elastomer-Modified Terpolymer Systems

1971 ◽  
Vol 44 (1) ◽  
pp. 62-70
Author(s):  
E. M. Hagerman
Keyword(s):  
Molecular Weight ◽  
Glass Transition ◽  
Transition Temperature ◽  
Glass Transition Temperature ◽  
Impact Resistance ◽  
Acrylonitrile Butadiene Styrene ◽  
Matrix Composition ◽  
Structure Property ◽  
Constant Matrix ◽  
Izod Impact

Abstract A number of terpolymers, incorporating as the elastomer phase polybutadiene, polyisoprene, poly-2,3-dimethylbutadiene, poly(butadiene-co-styrene), and poly(butadiene-co-2-methyl-5-vinylpyridine), were studied. Matrices were composed of poly(styrene-co-aerylonitrile) (SAN), poly(α-methylstyrene-eo-acrylonitrile), and poly(styrene-co-acenaphthylene). At constant elastomer content and elastomer molecular weight in systems employing a SAN matrix, Izod impact resistance was found to vary inversely with rising elastomer-glass transition temperature. In systems of various matrix composition, using a polybutadiene elastomer, heat deflection temperatures were found to vary directly and impact resistance inversely with rising matrix-glass transition temperature. In acrylonitrile-butadiene-styrene (ABS), systems of constant matrix composition and elastomer content, varying the elastomer molecular weight from 0.6 to 2.6×105 resulted in increasing the Izod impact resistance from 0.67 to 12.8 ft-1b/in. of notch.

scholarly journals Predicting Polymer’s Glass Transition Temperature by A Chemical Language Processing Model

2021 ◽  
Author(s):  
Guang Chen ◽  
Lei Tao ◽  
Ying Li
Keyword(s):  
Glass Transition ◽  
Transition Temperature ◽  
Glass Transition Temperature ◽  
Language Processing ◽  
High Throughput Screening ◽  
Molecular Descriptors ◽  
Feature Representation ◽  
Structure Property ◽  
Repeat Units ◽  
Chemical Language

We propose a chemical language processing model to predict polymers’ glass transition temperature (Tg) through a polymer language (SMILES, Simplified Molecular Input Line Entry System) embedding and recurrent neural network. This model only receives the SMILES strings of polymer’s repeat units as inputs and considers the SMILES strings as sequential data at the character level. Using this method, there is no need to calculate any additional molecular descriptors or fingerprints of polymers, and thereby, being very computationally efficient and simple. More importantly, it avoids the difficulties to generate molecular descriptors for repeat units containing polymerization point `*’. Results show that the trained model demonstrates reasonable prediction accuracy on unseen polymer’s Tg. Besides, this model is further applied for high-throughput screening on an unlabeled polymer database to identify high-temperature polymers that are desired for applications in extreme environments. Our work demonstrates that the SMILES strings of polymer’s repeat units can be used as an effective feature representation to develop a chemical language processing model for predictions of Tg. The framework of this model is general and can be used to construct structure-property relationships for other polymer’s properties.

Sign in / Sign up

Export Citation Format

Share Document