Machine-learning-driven discovery of polymers molecular structures with high thermal conductivity

Zhu, Ming-Xiao; Song, Heng-Gao; Yu, Qiu-Cheng; Chen, Jiming; Zhang, Hongyu

doi:10.1016/j.ijheatmasstransfer.2020.120381

Cited by 45 publications

(41 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the electronic, ionic and total dielectric constant can be computed by the density functional perturbation theory as well [12,22]. The thermodynamic properties of polymers or nanocomposites such as glass transmission temperature and thermal conductivity can be readily computed by MD simulations, for example, the non-equilibrium MD have been extensively adopted to calculate the thermal conductivity (Figure 2d) [25,45]. Given the expensive computational cost of firstprinciple methods, small, length-scale models (<100 atoms) are generally built to characterize the dielectric properties.…”

Section: Datasetmentioning

confidence: 99%

“…are welldeveloped ML algorithms that mimic the human brain to learn the linkages between certain descriptors and properties based on experience [94][95][96][97][98][99][100][101]. Figure 4b depicts the general architecture of the ANN, in which polymer fingerprints form the input layer [25]. The hidden layers build the relationships between the input and output layers, and the output layer represents the fitness of the candidate polymers.…”

Section: Algorithmmentioning

confidence: 99%

“…As for CNN, conventional and pool layers are added to extract key features from the input layer and 4 The schematic of (a) Gaussian process regression, (b) artificial neural networks and (c) convolutional neural networks [25]. Reprinted with permission from Zhu et al [25]. Copyright 2020, Elsevier.…”

Section: Algorithmmentioning

confidence: 99%

“…Based on the high-throughput phasefield calculations, Shen et al presented a ML strategy to evaluate the energy storage capability of polymer nanocomposites [24]. We have also schemed ML models to accelerate the rational design of polymers with high thermal conductivity and polymer nanocomposites with desired dielectric properties [25,26].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Section: Datasetmentioning

confidence: 99%

Section: Algorithmmentioning

confidence: 99%

Section: Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

show abstract

“…However, most of the current training data for ML algorithms in polymer applications are derived from the DFT calculations of monomeric or small oligomeric substances ( Webb et al, 2020 ). Additionally, the polymeric structures used in the current ML models are mostly represented by a simplified molecular-input line-entry system (SMILES) of the monomers for simplification ( Chandrasekaran et al, 2020 ; Zhu et al, 2020 ; Nazarova et al, 2021 ). We know that SMILES is one of the most popular methods to represent molecules because it is handy and readable for both humans and machines.…”

Section: Introductionmentioning

confidence: 99%

Integration of Machine Learning and Coarse-Grained Molecular Simulations for Polymer Materials: Physical Understandings and Molecular Design

2022

View full text Add to dashboard Cite

In recent years, the synthesis of monomer sequence-defined polymers has expanded into broad-spectrum applications in biomedical, chemical, and materials science fields. Pursuing the characterization and inverse design of these polymer systems requires our fundamental understanding not only at the individual monomer level, but also considering the chain scales, such as polymer configuration, self-assembly, and phase separation. However, our accessibility to this field is still rudimentary due to the limitations of traditional design approaches, the complexity of chemical space along with the burdened cost and time issues that prevent us from unveiling the underlying monomer sequence-structure-property relationships. Fortunately, thanks to the recent advancements in molecular dynamics simulations and machine learning (ML) algorithms, the bottlenecks in the tasks of establishing the structure-function correlation of the polymer chains can be overcome. In this review, we will discuss the applications of the integration between ML techniques and coarse-grained molecular dynamics (CGMD) simulations to solve the current issues in polymer science at the chain level. In particular, we focus on the case studies in three important topics—polymeric configuration characterization, feed-forward property prediction, and inverse design—in which CGMD simulations are leveraged to generate training datasets to develop ML-based surrogate models for specific polymer systems and designs. By doing so, this computational hybridization allows us to well establish the monomer sequence-functional behavior relationship of the polymers as well as guide us toward the best polymer chain candidates for the inverse design in undiscovered chemical space with reasonable computational cost and time. Even though there are still limitations and challenges ahead in this field, we finally conclude that this CGMD/ML integration is very promising, not only in the attempt of bridging the monomeric and macroscopic characterizations of polymer materials, but also enabling further tailored designs for sequence-specific polymers with superior properties in many practical applications.

show abstract

Machine Learning‐Assisted Research and Development of Chemiresistive Gas Sensors

Yuan,

Luo,

Meng

2024

Adv Eng Mater

View full text Add to dashboard Cite

The traditional trial‐and‐error testing to develop high‐performance chemiresistive gas sensors is inefficient and fails to meet the high demand for sensors in various industries. Machine learning can address the limitations of trial‐and‐error testing and can be effectively utilized for enhancing, developing, and designing sensors. This review first discusses the prediction of critical mechanism parameters of gas‐sensitive materials by machine learning, including adsorption energy, band gap, thermal conductivity, and dielectric constant. Secondly, it proposes that machine learning can improve five performance indexes: selectivity, response/recovery time, stability, sensitivity, and accuracy. Machine learning also facilitates the development and structural design of gas‐sensitive new materials. In addition, the potential of machine learning to optimize the sensor arrays is investigated, including reducing the number of sensors, identifying the best array combination, and improving recognition and detection capabilities. Finally, this paper discusses the challenges and limitations of machine‐learning assisted chemiresistive gas sensors in practical applications and envisions their future development.This article is protected by copyright. All rights reserved.

show abstract

Machine-learning-driven discovery of polymers molecular structures with high thermal conductivity

Cited by 45 publications

References 44 publications

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

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

Integration of Machine Learning and Coarse-Grained Molecular Simulations for Polymer Materials: Physical Understandings and Molecular Design

Machine Learning‐Assisted Research and Development of Chemiresistive Gas Sensors

Contact Info

Product

Resources

About