Multiobjective optimization of dielectric, thermal, and mechanical properties of inorganic glasses utilizing explainable machine learning and genetic algorithm
Abstract To meet the demands of advanced electronic devices, inorganic glasses are required to have comprehensive dielectric, thermal, and mechanical properties. However, the complex composition–property relationship and vast compositional diversity hinder optimization. This study developed machine...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley-VCH
2025-06-01
|
| Series: | Materials Genome Engineering Advances |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/mgea.70005 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839630646519005184 |
|---|---|
| author | Jincheng Qin Faqiang Zhang Mingsheng Ma Yongxiang Li Zhifu Liu |
| author_facet | Jincheng Qin Faqiang Zhang Mingsheng Ma Yongxiang Li Zhifu Liu |
| author_sort | Jincheng Qin |
| collection | DOAJ |
| description | Abstract To meet the demands of advanced electronic devices, inorganic glasses are required to have comprehensive dielectric, thermal, and mechanical properties. However, the complex composition–property relationship and vast compositional diversity hinder optimization. This study developed machine learning models to predict permittivity, dielectric loss, thermal conductivity, coefficient of thermal expansion, and Young’s modulus based on the composition features of inorganic glasses. The optimal models achieve R2 values of 0.9614, 0.7411, 0.9454, 0.9684, and 0.8164, respectively. By integrating domain knowledge with model‐agnostic interpretation methods, feature contributions and interactions were analyzed. The mixed alkali effect is crucial for property regulation, especially Na‐K for dielectric loss and Na‐Li for thermal conductivity. Boron anomaly shifts the high‐λ region to a balanced composition of alkali metals with rising B%. The multiobjective optimization of properties was realized using a genetic algorithm framework. After 23 iterations, the optimal material in the MgO‐Al2O3‐B2O3‐SiO2 system exhibits εr = 4.78, tanδ = 0.00063, λ = 2.59 W/(m·K), α = 50.27×10−7K−1, and E = 82.41 GPa, outperforming all materials in the dataset. The computational effort was reduced to 1/19 of that required using exhaustive search methods. This study provides a model interpretation framework and an effective multiobjective optimization strategy for glass design. |
| format | Article |
| id | doaj-art-8dad96e1e1df4098a90e2f3bc8c6d16c |
| institution | Matheson Library |
| issn | 2940-9489 2940-9497 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Wiley-VCH |
| record_format | Article |
| series | Materials Genome Engineering Advances |
| spelling | doaj-art-8dad96e1e1df4098a90e2f3bc8c6d16c2025-07-13T15:31:09ZengWiley-VCHMaterials Genome Engineering Advances2940-94892940-94972025-06-0132n/an/a10.1002/mgea.70005Multiobjective optimization of dielectric, thermal, and mechanical properties of inorganic glasses utilizing explainable machine learning and genetic algorithmJincheng Qin0Faqiang Zhang1Mingsheng Ma2Yongxiang Li3Zhifu Liu4The State Key Laboratory of High Performance Ceramics and Superfine Structure Shanghai Institute of Ceramics Chinese Academy of Sciences Shanghai ChinaThe State Key Laboratory of High Performance Ceramics and Superfine Structure Shanghai Institute of Ceramics Chinese Academy of Sciences Shanghai ChinaThe State Key Laboratory of High Performance Ceramics and Superfine Structure Shanghai Institute of Ceramics Chinese Academy of Sciences Shanghai ChinaSchool of Engineering RMIT University Melbourne VIC AustraliaThe State Key Laboratory of High Performance Ceramics and Superfine Structure Shanghai Institute of Ceramics Chinese Academy of Sciences Shanghai ChinaAbstract To meet the demands of advanced electronic devices, inorganic glasses are required to have comprehensive dielectric, thermal, and mechanical properties. However, the complex composition–property relationship and vast compositional diversity hinder optimization. This study developed machine learning models to predict permittivity, dielectric loss, thermal conductivity, coefficient of thermal expansion, and Young’s modulus based on the composition features of inorganic glasses. The optimal models achieve R2 values of 0.9614, 0.7411, 0.9454, 0.9684, and 0.8164, respectively. By integrating domain knowledge with model‐agnostic interpretation methods, feature contributions and interactions were analyzed. The mixed alkali effect is crucial for property regulation, especially Na‐K for dielectric loss and Na‐Li for thermal conductivity. Boron anomaly shifts the high‐λ region to a balanced composition of alkali metals with rising B%. The multiobjective optimization of properties was realized using a genetic algorithm framework. After 23 iterations, the optimal material in the MgO‐Al2O3‐B2O3‐SiO2 system exhibits εr = 4.78, tanδ = 0.00063, λ = 2.59 W/(m·K), α = 50.27×10−7K−1, and E = 82.41 GPa, outperforming all materials in the dataset. The computational effort was reduced to 1/19 of that required using exhaustive search methods. This study provides a model interpretation framework and an effective multiobjective optimization strategy for glass design.https://doi.org/10.1002/mgea.70005genetic algorithminorganic glassmachine learningmodel‐agnostic interpretationmultiobjective optimization |
| spellingShingle | Jincheng Qin Faqiang Zhang Mingsheng Ma Yongxiang Li Zhifu Liu Multiobjective optimization of dielectric, thermal, and mechanical properties of inorganic glasses utilizing explainable machine learning and genetic algorithm Materials Genome Engineering Advances genetic algorithm inorganic glass machine learning model‐agnostic interpretation multiobjective optimization |
| title | Multiobjective optimization of dielectric, thermal, and mechanical properties of inorganic glasses utilizing explainable machine learning and genetic algorithm |
| title_full | Multiobjective optimization of dielectric, thermal, and mechanical properties of inorganic glasses utilizing explainable machine learning and genetic algorithm |
| title_fullStr | Multiobjective optimization of dielectric, thermal, and mechanical properties of inorganic glasses utilizing explainable machine learning and genetic algorithm |
| title_full_unstemmed | Multiobjective optimization of dielectric, thermal, and mechanical properties of inorganic glasses utilizing explainable machine learning and genetic algorithm |
| title_short | Multiobjective optimization of dielectric, thermal, and mechanical properties of inorganic glasses utilizing explainable machine learning and genetic algorithm |
| title_sort | multiobjective optimization of dielectric thermal and mechanical properties of inorganic glasses utilizing explainable machine learning and genetic algorithm |
| topic | genetic algorithm inorganic glass machine learning model‐agnostic interpretation multiobjective optimization |
| url | https://doi.org/10.1002/mgea.70005 |
| work_keys_str_mv | AT jinchengqin multiobjectiveoptimizationofdielectricthermalandmechanicalpropertiesofinorganicglassesutilizingexplainablemachinelearningandgeneticalgorithm AT faqiangzhang multiobjectiveoptimizationofdielectricthermalandmechanicalpropertiesofinorganicglassesutilizingexplainablemachinelearningandgeneticalgorithm AT mingshengma multiobjectiveoptimizationofdielectricthermalandmechanicalpropertiesofinorganicglassesutilizingexplainablemachinelearningandgeneticalgorithm AT yongxiangli multiobjectiveoptimizationofdielectricthermalandmechanicalpropertiesofinorganicglassesutilizingexplainablemachinelearningandgeneticalgorithm AT zhifuliu multiobjectiveoptimizationofdielectricthermalandmechanicalpropertiesofinorganicglassesutilizingexplainablemachinelearningandgeneticalgorithm |