Machine learning glass transition temperature of polymers

Zhang, Yun; Xu, Xiaojie

doi:10.1016/j.heliyon.2020.e05055

Cited by 64 publications

(31 citation statements)

References 50 publications

(76 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The introduction of the methodology follows previous studies 36‐59 . GPRs are nonparametric probabilistic models.…”

Section: Methodsmentioning

confidence: 99%

“…The model is highly stable and accurate that contributes to efficient and low‐cost lattice constant estimations and understandings of which based on ionic radii and electronegativities of both ternary and mixed pyrochlores. As a machine learning technique, 34,35 the GPR model has been used various areas of materials science and engineering to acquire important physicochemical parameters through rapid and robust predictions 36‐59 . This model could serve as a guideline for pyrochlore lattice design and might be adopted for lattice mismatch estimations in thin film configurations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning the lattice constant of cubic pyrochlore compounds

Zhang

2021

Int J Applied Ceramic Tech

Self Cite

View full text Add to dashboard Cite

Pyrochlores, with a general formula A 2 B 2 X 7 , are promising candidates in many potential applications due to their wide varieties of physical properties. Different combinations of cations and anions in the crystal structure enable the tailoring of their properties and functionalities. For cubic pyrochlores, the lattice constant, a, is an integrated result of stoichiometry, ionic radii, and electronegativities of alloying elements.It also has significant impacts on stabilities, electronic structures, ionic conductivities, and thus performance of materials. Here, we develop the Gaussian process regression model to shed light on the relationship among ionic radii, electronegativities, and lattice constants for cubic pyrochlores. The dataset includes ternary pyrochlores and mixed pyrochlores with co-doping and multi-doping situations. One hundred and thirty-nine samples with lattice constants between 9.287 and 11.150 Å are examined.The model is highly stable and accurate that contributes to efficient and low-cost lattice constant estimations.

show abstract

“…The introduction of the methodology follows previous studies 36‐59 . GPRs are nonparametric probabilistic models.…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine learning the lattice constant of cubic pyrochlore compounds

Zhang

2021

Int J Applied Ceramic Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…Glass transition temperature (

) of polymers is an important physical property, which has been studied extensively in polymer science and engineering [ 1 , 2 , 3 , 4 , 5 , 6 ].

characterizes a second-order phase transition over which polymers can change between a rubbery state and a glassy state with Young’s modulus ranging from MPa to GPa [ 7 ].…”

Section: Introductionmentioning

confidence: 99%

Predicting Polymers’ Glass Transition Temperature by a Chemical Language Processing Model

Chen

Tao

2021

Polymers

View full text Add to dashboard Cite

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 a 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. 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 performance 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 repeat units can be used as an effective feature representation to develop a chemical language processing model for predictions of polymer Tg. The framework of this model is general and can be used to construct structure–property relationships for other polymer properties.

show abstract

“…It has been clarified that a weld line is generated on the surface of a molded product, and the transcription of the cavity wall onto the surface of a molded product fails while the melt at the melt front meeting area forms a skin layer [ 4 ]. Therefore, the formation of a skin layer should be delayed; concretely, the cavity wall is heated to the glass transition point T g or higher to ensure that the melt flowing near the cavity wall does not transform from rubber state to glass state [ 5 ]. When the melt is pressed to the cavity wall in this state upon the application of melt pressure and then cooled, the V-shaped groove of the weld line disappears and the transferability is improved, as in a previous report [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

Effects of Heating and Cooling of Injection Mold Cavity Surface and Melt Flow Control on Properties of Carbon Fiber Reinforced Semi-Aromatic Polyamide Molded Products

Murata

Kanno

2021

Polymers

View full text Add to dashboard Cite

Fiber reinforced thermoplastics (FRTP), reinforced with glass or carbon fibers, are used to improve the mechanical strength of injection-molded products. However, FRTP has problems such as the formation of weld lines, the deterioration of appearance due to the exposure of fibers on the molded product surface, and the deterioration of the strength of molded products due to the fiber orientation in the molded products. We have designed and fabricated an injection mold capable of melt flow control and induction heating and cooling. This mold can both heat and cool the injection mold. It can also control the melt flow direction using a movable core pin. In this study, the above-mentioned mold was used for the molding of carbon fiber reinforced semi-aromatic polyamide. As a result, we found that increasing the heating temperature of the mold and increasing melt flow control volume contribute to the prevention of the generation of a weld line and the exposure of fibers on the molded product surface, as well as to the formation of a flat surface and increased bending strength. The relationships of these results with the carbon fiber orientation in the molded products and the crystallization of semi-aromatic polyamide were also examined in this study.

show abstract

Machine learning glass transition temperature of polymers

Cited by 64 publications

References 50 publications

Machine learning the lattice constant of cubic pyrochlore compounds

Machine learning the lattice constant of cubic pyrochlore compounds

Predicting Polymers’ Glass Transition Temperature by a Chemical Language Processing Model

Effects of Heating and Cooling of Injection Mold Cavity Surface and Melt Flow Control on Properties of Carbon Fiber Reinforced Semi-Aromatic Polyamide Molded Products

Contact Info

Product

Resources

About