硅酸盐学报

改进的Wasserstein生成式对抗网络用于氧化物玻璃电学性能的数据增强建模

PDF下载

田静 ¹ , 李苑 ¹ , 官敏 ² , 郑际杰 ³ , 储静远 ² , 刘涌 ¹ , 韩高荣 ¹^,⁴

硅酸盐学报 | 先进玻璃材料技术与产业发展专题—研究论文 2025,53(10): 2766-2776

收起

硅酸盐学报 |先进玻璃材料技术与产业发展专题—研究论文 2025 , 53 (10) : 2766 -2776

改进的Wasserstein生成式对抗网络用于氧化物玻璃电学性能的数据增强建模

全屏

田静¹, 李苑¹, 官敏², 郑际杰³, 储静远², 刘涌¹, 韩高荣¹^,⁴

作者信息

^1．浙江大学材料科学与工程学院，杭州 310058

^2．中国建材国际工程集团有限公司，上海 200063

^3．玻璃新材料创新中心（安徽）有限公司，安徽蚌埠 233000

^4．浙江大学宁波国际科创中心，浙江宁波 315100

通讯作者:

刘涌（1979—），男，副教授。

作者简介:

田静（1998—），女，博士研究生。

Modeling Electrical Properties of Oxide Glass via Improved Wasserstein Generative Adversarial Network for Data Augmentation

Jing TIAN¹, Yuan LI¹, Min GUAN², Jijie ZHENG³, Jingyuan CHU², Yong LIU¹, Gaorong HAN¹^,⁴

Affiliations

^1.School of Material Science and Engineering, Zhejiang University, Hangzhou 310058, China

^2.China Triumph International Engineering Co., Ltd., Shanghai 200063, China

^3.Innovation Center for Advanced Glass Materials (Anhui) Co., Ltd., Bengbu 233000, Anhui, China

^4.Ningbo Innovation Center, Zhejiang University, Ningbo 315100, Zhejiang, China

Corresponding Author:

LIU Yong (1979-), male, Ph.D., Associate Professor. E-mail: liuyong.mse@zju.edu.cn

TIAN Jing (1998-), female, Doctoral candidate. E-mail: 12326039@zju.edu.cn

出版时间: 2025-10-20 doi: 10.14062/j.issn.0454-5648.20250278

文章导航

摘要

收起

随着氧化物玻璃在电子信息领域的应用日益广泛，其电学性能作为关键性指标也愈发受到重视。尽管数据驱动的机器学习方法在玻璃性能预测中已取得显著进展，但其在小数据集场景下的应用仍面临挑战。针对氧化物玻璃电学性能数据不足的核心问题，引入带梯度惩罚项和组分惩罚项的改进Wasserstein生成式对抗网络（WGAN-GP-CP），构建了适用于玻璃材料的数据增强框架，并设计了新型样本质量评估方式。该框架在生成器损失函数中引入组分惩罚项，能够生成高质量的合成样本，有效扩展现有数据集。对比研究表明，数据增强显著缓解了模型过拟合问题，同时显著提升其泛化能力。基于建立的组分-性能预测模型，通过SHAP单特征分析和特征交互分析进一步揭示了氧化物组分特征对玻璃电学性能的影响机制及特征间的交互作用。以上结果不仅为氧化物玻璃电学性能预测提供了可靠的模型支持，更为数据稀缺场景下高性能数据驱动模型的开发提供了新思路。

关键词

氧化物玻璃 / 电学性能 / 机器学习 / 数据增强 / SHAP分析

Abstract

收起

Introduction

With the advancement of the Materials Genome Initiative and the establishment and improvement of the glass database, data-driven machine-learning methods penetrate the field of glass materials, and remarkable progress is made in the modeling of the physical, mechanical, and optical properties of glass materials. In recent years, oxide glasses have found increasingly widespread applications in the field of electronic applications, and their electrical properties as critical indicators have attracted much attention. However, modeling on the electrical properties of oxide glasses remains a challenge, and insufficient data suppress the model's performance. To address the issue of limited data availability on the electrical properties of oxide glasses, this work was to propose a data augmentation framework named WGAN-GP-CP tailored for glass materials.

Methods

Based on the Wasserstein generative adversarial network with gradient penalty (WGAN-GP) model, an additional composition penalty term (CP) was added to the generator's loss function, and a method for evaluating sample quality was proposed, which could assess the quality of the generated samples from three aspects, i.e., diversity, accuracy, and uniqueness. Moreover, the XGBoost algorithm was employed for model training, and the model was interpreted through SHAP single-feature analysis and feature interaction analysis.

Results and discussion

The trained generators can generate high-quality synthetic samples, expanding the existing datasets effectively. The results of comparative studies demonstrate that the data-augmented models exhibit mitigated overfitting and significantly enhanced generalization capability. The generalization performances of the room-temperature bulk resistivity, relative dielectric constant, and dielectric loss models increase from 0.784 to 0.838, 0.862 to 0.897, and 0.801 to 0.861, respectively. The results obtained from SHAP analysis are generally consistent with the classical physicochemical understanding of the electrical properties of oxide glasses. In addition, some interesting mixing effects and interactive relationships are also revealed.

Conclusions

The data augmentation framework proposed in this work offered a strategy for developing high-performance data-driven models under data scarcity conditions. The insights from SHAP single-feature analysis and feature interaction analysis could provide an important guidance for a deeper understanding of the relationship between the composition and electrical properties of oxide glasses. This research shifted the optimization of oxide glass electrical properties from empirically driven trial-and-error methods to data-driven scientific design frameworks, laying a foundation for the development of high-performance glass materials in the field of electronic applications.

Key words

oxide glasses / electrical properties / machine learning / data augmentation / SHAP analysis

引用本文

田静, 李苑, 官敏, 郑际杰, 储静远, 刘涌, 韩高荣. 改进的Wasserstein生成式对抗网络用于氧化物玻璃电学性能的数据增强建模. 硅酸盐学报, 2025 , 53 (10) : 2766 -2776 . DOI: 10.14062/j.issn.0454-5648.20250278

Jing TIAN, Yuan LI, Min GUAN, Jijie ZHENG, Jingyuan CHU, Yong LIU, Gaorong HAN. Modeling Electrical Properties of Oxide Glass via Improved Wasserstein Generative Adversarial Network for Data Augmentation[J]. Journal of the Chinese Ceramic Society, 2025 , 53 (10) : 2766 -2776 . DOI: 10.14062/j.issn.0454-5648.20250278

基金

收起

国家“十四五”重点研发计划(2022YFB3603300)
上海市2022年度科技创新行动计划国际科技合作项目(22520730500)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

2025年第53卷第10期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.14062/j.issn.0454-5648.20250278

接收时间：2025-04-15
首发时间：2026-10-21
出版时间：2025-10-20

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2025-04-15
修回日期：2025-04-29

基金

国家“十四五”重点研发计划(2022YFB3603300)

上海市2022年度科技创新行动计划国际科技合作项目(22520730500)

作者信息

^1．浙江大学材料科学与工程学院，杭州 310058

^2．中国建材国际工程集团有限公司，上海 200063

^3．玻璃新材料创新中心（安徽）有限公司，安徽蚌埠 233000

^4．浙江大学宁波国际科创中心，浙江宁波 315100

通讯作者:

刘涌（1979—），男，副教授。

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/gsyxb/CN/10.14062/j.issn.0454-5648.20250278

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT