Determination of glass transition temperature of polyimides from atomistic molecular dynamics simulations and <scp>machine‐learning</scp> algorithms

Wen, Chengyuan; Liu, Binghan; Wolfgang, Josh D.; Long, Timothy Edward; Odle, Roy; Cheng, Shengfeng

doi:10.1002/pol.20200050

Cited by 27 publications

(32 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leveraging these descriptors, such as electrostatic, hydrogen bonding, and microstructures of the hard segments, in the model can improve ML model performances. Furthermore, the sampling method of the training dataset can also impact the model performances, especially for studies with a small database [ 86 ].…”

Section: Discussionmentioning

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

Section: Discussionmentioning

confidence: 99%

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

Chen

Tao

2021

Polymers

View full text Add to dashboard Cite

show abstract

“…Due to the synthetic difficulty of designed candidates and time-consuming experiments, the amount of dielectric property data is substantially limited. As an effective alternative approach, high-throughput computations [47] using first-principles theory [43,44,[48][49][50][51][52][53], molecular dynamics (MD) [45,54,55], phasefiled model [46,56,57] and finite-element method [58,59] have been employed to acquire property data, as shown in Figure 2a. Most dielectric properties of interest, for example, permittivity, conduction loss, breakdown strength, glass transmission temperature (T g ) and thermal conductivity, can be directly calculated or indirectly represented with some correlated parameters.…”

Section: Datasetmentioning

confidence: 99%

Review of machine learning‐driven design of polymer‐based dielectrics

Zhu

Deng

Lei

et al. 2021

IET Nanodielectrics

View full text Add to dashboard Cite

Polymer-based dielectrics are extensively applied in various electrical and electronic devices such as capacitors, power transmission cables and microchips, in which a variety of distinct performances such as the dielectric and thermal properties are desired. To fulfil these properties, the emerging machine learning (ML) technique has been used to establish a surrogate model for the structure-property linkage analysis, which provides an effective tool for the rational design of the chemical and morphological structure of polymers/nanocomposites. In this article, the authors reviewed the recent progress in the ML algorithms and their applications in the rational design of polymer-based dielectrics. The main routes for collecting training data including online libraries, experiments and high-throughput computations are first summarized. The fingerprints charactering the microstructures of polymers/nanocomposites are presented, followed by the illustration of ML models to establish a mapping between the fingerprinted input and the target properties. Further, inverse design methods such as evolution searching strategies and generative models are described, which are exploited to accelerate the discovery of new polymer-based dielectrics. Moreover, structure-property linkage analysis techniques such as Pearson correlation calculation, decision-tree-based methods and interpretable neural networks are summarized to identify the key features affecting the target properties. The future development prospects of the ML-driven design method for polymer-based dielectrics are also presented in this review. K E Y W O R D S fingerprinting, inverse design, machine learning, polymer-based dielectrics, structure-property linkage analysisThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

show abstract

“…By contrast, the glass state morphology of polymeric materials will be converted to a rubbery state when the temperature is above T g . 19 In a rubbery state, materials such as PI will lose their practical value. The DSC curves of the neat PI and NG/PI composites are shown in Figure 2.…”

Section: Glass Transition Behaviormentioning

confidence: 99%

Friction and wear behavior of polyimide matrix composites filled with nanographite

Wan

Yao

et al. 2021

J of Applied Polymer Sci

View full text Add to dashboard Cite

In this study, nanographite (NG), as a lubricant additive, and polyimide (PI) were used to fabricate NG/PI composites via a hot compression molding process. The tribological properties of the NG/PI composites with different NG mass contents (0-10 wt%) were tested using a reciprocating ball-on-disc contact tribometer matched with a GCr15 rubbing pair. The thermal stability, surface hardness, and compression strength of the composites were discussed. The results revealed that a small quantity of nanofillers greatly reduced the friction coefficient and increased the wear resistance of the NG/PI composites. Despite a minor decrease in mechanical performance, the composite with 5 wt% of NG filler exhibited improved tribological properties; it showed a 55.63% reduction in the friction coefficient and a reduction of 97.39% in the wear rate compared with neat PI. Moreover, an increase in the glass transition temperature (T g ) of the NG/PI composites indicated the enhancement of their thermal stability and wear resistance. Scanning electron microscopy (SEM) analyses showed that the main wear mechanism of the composites was fatigue wear. These findings suggest that the 5 wt% NG/PI composite could be a significant contribution to the field of tribological engineering plastics.

show abstract

Determination of glass transition temperature of polyimides from atomistic molecular dynamics simulations and machine‐learning algorithms

Cited by 27 publications

References 61 publications

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

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

Review of machine learning‐driven design of polymer‐based dielectrics

Friction and wear behavior of polyimide matrix composites filled with nanographite

Contact Info

Product

Resources

About