Design rules for glass formation from model molecules designed by a neural-network-biased genetic algorithm

Soft Matter ◽  
2019 ◽  
Vol 15 (39) ◽  
pp. 7795-7808 ◽  
Author(s):  
Venkatesh Meenakshisundaram ◽  
Jui-Hsiang Hung ◽  
David S. Simmons
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Glass Transition ◽  
Transition Temperature ◽  
Glass Transition Temperature ◽  
Glass Formation ◽  
Molecular Geometry ◽  
Design Model ◽  
Design Rules ◽  
Model Glass

A neural-network-biased genetic algorithm is employed to design model glass formers exhibiting extremes of fragility of glass formation, elucidating connections between molecular geometry, thermodynamics, fragility, and glass-transition temperature.

scholarly journals A Deep Neural Network for Accurate and Robust Prediction of the Glass Transition Temperature of Polyhydroxyalkanoate Homo- and Copolymers

Materials ◽  
2020 ◽  
Vol 13 (24) ◽  
pp. 5701
Author(s):  
Zhuoying Jiang ◽  
Jiajie Hu ◽  
Babetta L. Marrone ◽  
Ghanshyam Pilania ◽  
Xiong (Bill) Yu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Glass Transition ◽  
Transition Temperature ◽  
Glass Transition Temperature ◽  
Deep Neural Network ◽  
Learning Model ◽  
Support Vector ◽  
Model Framework ◽  
Machine Learning Model

The purpose of this study was to develop a data-driven machine learning model to predict the performance properties of polyhydroxyalkanoates (PHAs), a group of biosourced polyesters featuring excellent performance, to guide future design and synthesis experiments. A deep neural network (DNN) machine learning model was built for predicting the glass transition temperature, Tg, of PHA homo- and copolymers. Molecular fingerprints were used to capture the structural and atomic information of PHA monomers. The other input variables included the molecular weight, the polydispersity index, and the percentage of each monomer in the homo- and copolymers. The results indicate that the DNN model achieves high accuracy in estimation of the glass transition temperature of PHAs. In addition, the symmetry of the DNN model is ensured by incorporating symmetry data in the training process. The DNN model achieved better performance than the support vector machine (SVD), a nonlinear ML model and least absolute shrinkage and selection operator (LASSO), a sparse linear regression model. The relative importance of factors affecting the DNN model prediction were analyzed. Sensitivity of the DNN model, including strategies to deal with missing data, were also investigated. Compared with commonly used machine learning models incorporating quantitative structure–property (QSPR) relationships, it does not require an explicit descriptor selection step but shows a comparable performance. The machine learning model framework can be readily extended to predict other properties.

Prediction of the glass transition temperature of (meth)acrylic polymers containing phenyl groups by recursive neural network

Polymer ◽  
2007 ◽  
Vol 48 (24) ◽  
pp. 7121-7129 ◽  
Author(s):  
Carlo Bertinetto ◽  
Celia Duce ◽  
Alessio Micheli ◽  
Roberto Solaro ◽  
Antonina Starita ◽  
...  
Keyword(s):  
Neural Network ◽  
Glass Transition ◽  
Transition Temperature ◽  
Glass Transition Temperature ◽  
Acrylic Polymers ◽  
Recursive Neural Network

Critical Cooling Rate Vs. Reduced Glass Transition: Scaling Factors and Master Curves

1998 ◽  
Vol 554 ◽  
Author(s):  
N. Clavaguera ◽  
M. T. Clavaguera-Mora
Keyword(s):  
Glass Transition ◽  
Transition Temperature ◽  
Glass Transition Temperature ◽  
Cooling Rate ◽  
Glass Formation ◽  
Supercooled Liquid ◽  
High Viscosity ◽  
Master Curves ◽  
Critical Cooling Rate ◽  
Equilibrium Solidification

AbstractThe aim of the present paper is to analyse the glass formation and stability of bulk metallic glasses. Attention is focused to metallic alloys as systems which may develop a large glassforming ability. Glass formation when quenching from the liquid state is discussed in terms of the thermodynamics and kinetics of the stable/metastable competing phases. Thermodynamics is required to relate glass transition temperature, Tg, to the energetics of the supercooled liquid. Kinetic destabilisation of equilibrium solidification and, consequently, glass forming ability are favoured by the high viscosity values achieved under continuous cooling. The relative thermal stability of the supercooled liquid depends on the thermodynamic driving force and interfacial energy between each competing nucleating phase and the molten alloy. It is shown that the quantities representative of the process, once scaled, have a temperature dependence that is mostly fixed by the reduced glass transition temperature, Tgr= Tg/Tm, Tm being the melting temperature. Based on the classical models of nucleation and crystal growth, the reduced critical cooling rate is shown to follow master curves when plotted against Tgr. Experimental trends for specific systems are compared to predicted values from these master curves.

Sign in / Sign up

Export Citation Format

Share Document