相关实验视频

Updated: Jun 21, 2025

Cooling Rate Dependent Ellipsometry Measurements to Determine the Dynamics of Thin Glassy Films

Cooling Rate Dependent Ellipsometry Measurements to Determine the Dynamics of Thin Glassy Films

Published on: January 26, 2016

基于机器学习的聚胺玻璃过渡温度的预测和解释性研究,具有定量结构-属性关系 (T_g-QSPR)

Tianyong Zhang^1,2,3, Suisui Wang¹, Yamei Chai¹

¹Tianjin Key Laboratory of Applied Catalysis Science and Technology, School of Chemical Engineering and Technology, Tianjin University, Tianjin 300354, China.

The journal of physical chemistry. B

|July 9, 2024

概括

机器学习模型使用分子描述器预测聚胺玻璃过渡温度 (Tg). CATBoost 模型实现了高精度,加速了 PI 的设计和开发.

科学领域:

材料科学材料科学材料科学
计算化学计算化学
聚合物科学聚合物科学

背景情况:

玻璃过渡温度 (Tg) 是聚胺 (PI) 的一个关键性质.
对Tg的预测建模可以简化PI材料的设计和开发.
准确的Tg预测需要强大的定量结构与属性关系 (QSPR) 模型.

研究的目的:

开发精确的基于机器学习的QSPR模型,用于预测聚胺的Tg.
确定影响聚胺Tg的关键分子描述器.
在新PI材料上验证开发模型的预测性能.

主要方法:

汇集了1257个PI的数据集,并通过实验确定了Tg值.
使用RDKit计算了210个分子描述符,并应用了6种特征选择方法.
使用五个集合学习算法和一个深度学习算法构建了Tg-QSPR模型,包括CATBoost.

主要成果:

在CATBoost模型实现了最高的预测准确度,R2=0.823,MAE=20.1°C,RMSE=29.0°C在测试组.
NumRotatableBonds描述符被确定为一个与Tg负相关的显著因素.
对10张新的PI片的模型验证显示了低绝对误差 (2.526.9°C) 和百分比误差 (1.012.8%).

结论:

机器学习模型,特别是像CATBoost这样的组合方法,可以准确地预测聚胺Tg.
该研究强调了大型多样化数据集和特征选择对于强大的预测建模的重要性.
开发的Tg-QSPR模型为加速新型聚胺的设计和性能预测提供了宝贵的工具.

更多相关视频

Orientational Transition in a Liquid Crystal Triggered by the Thermodynamic Growth of Interfacial Wetting Sheets

Orientational Transition in a Liquid Crystal Triggered by the Thermodynamic Growth of Interfacial Wetting Sheets

Published on: May 15, 2017

Characterizing Dissipative Elastic Metamaterials Produced by Additive Manufacturing

Characterizing Dissipative Elastic Metamaterials Produced by Additive Manufacturing

Published on: June 28, 2024

相关概念视频

Polymer Classification: Crystallinity

Polymer Classification: Crystallinity

Unlike ionic or small covalent molecules, polymers do not form crystalline solids due to the diffusion limitations of their long-chain structures. However, polymers contain microscopic crystalline domains separated by amorphous domains.
Crystalline domains are the regions where polymer chains are aligned in an orderly manner and held together in proximity by intermolecular forces. For example, chains in the crystalline domains of polyethylene and nylon are bound together by van der Waals...

Polymer Classification: Stereospecificity

Polymer Classification: Stereospecificity

Polymerization generates chiral centers along the entire backbone of a polymer chain. Accordingly, the stereochemistry of the substituent group has a significant effect on polymer properties. Polymers formed from monosubstituted alkene monomers feature chiral carbons at every alternate position in the polymer backbone. Relative to the predominant orientation of substituents at the adjacent chiral carbons, the polymer can exist in three different configurations: isotactic, syndiotactic, and...