Ming Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ming Huang has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
Fenglin Wang
College of Aerospace Science and Engineering National University of Defense Technology Changsha China
3 shared publicationsHaijun Mao
College of Aerospace Science and Engineering National University of Defense Technology Changsha China
3 shared publicationsWei Li
College of Aerospace Science and Engineering National University of Defense Technology Changsha China
3 shared publicationsWeijun Zhang
College of Aerospace Science and Engineering National University of Defense Technology Changsha China
3 shared publications- Wen Zhang
Science and Technology on Advanced Ceramic Fibers and Composites Laboratory College of Aerospace Science and Engineering National University of Defense Technology Changsha P.R. China
3 shared publications - Xiang Yang
Science and Technology on Advanced Ceramic Fibers and Composites Laboratory, College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China
3 shared publications
Latest Publications
- Open Access
- 25 February 2026
- Published by Wiley in Materials Genome Engineering Advances
- Vol. 4 (1)
A Dynamic‐Weighted Deep Transfer Learning Framework for Thermal Conductivity Prediction and Analysis
To overcome the limitations of small‐sample data in establishing microstructure–property linkages, this study introduces a deep transfer learning framework with a dynamic weighting mechanism. By transferring the perceptual capabilities of the ResNet‐18 model and adaptively fusing them with material domain knowledge, the model effectively captures complex features such as phase distribution. Using silicon nitride ceramics as the primary research object, the framework achieves an average cross‐validation prediction accuracy ( R 2 ) of 0.73, representing a 104.3% relative improvement compared to the traditional CNN framework, and the optimal model reaches an accuracy of R 2 = 0.89. Furthermore, this framework also demonstrates exceptional predictive accuracy on silicon carbide ceramics ( R 2 = 0.84) and sintered nano silver ( R 2 = 0.93), indicating its strong generalization capabilities. By employing multilevel gradient‐weighted class activation mapping (Grad‐CAM) and sliding occlusion analysis, the decision‐making process of the model is elucidated, thereby validating the logical soundness of its predictions. Additionally, symbolic regression is utilized to identify the influence of different microstructural features on thermal conductivity and to establish their quantitative relationships. This research holds broad application prospects in the rapid development and design of thermal management materials, analysis of material microstructure images, and the establishment of structure–performance relationships between microstructural features and macroscopic properties.
- 25 February 2026
- Published by Wiley in Materials Genome Engineering Advances
- Vol. 4 (1)
Open AccessA Dynamic‐Weighted Deep Transfer Learning Framework for Thermal Conductivity Prediction and Analysis
To overcome the limitations of small‐sample data in establishing microstructure–property linkages, this study introduces a deep transfer learning framework with a dynamic weighting mechanism. By transferring the perceptual capabilities of the ResNet‐18 model and adaptively fusing them with material domain knowledge, the model effectively captures complex features such as phase distribution. Using silicon nitride ceramics as the primary research object, the framework achieves an average cross‐validation prediction accuracy ( R 2 ) of 0.73, representing a 104.3% relative improvement compared to the traditional CNN framework, and the optimal model reaches an accuracy of R 2 = 0.89. Furthermore, this framework also demonstrates exceptional predictive accuracy on silicon carbide ceramics ( R 2 = 0.84) and sintered nano silver ( R 2 = 0.93), indicating its strong generalization capabilities. By employing multilevel gradient‐weighted class activation mapping (Grad‐CAM) and sliding occlusion analysis, the decision‐making process of the model is elucidated, thereby validating the logical soundness of its predictions. Additionally, symbolic regression is utilized to identify the influence of different microstructural features on thermal conductivity and to establish their quantitative relationships. This research holds broad application prospects in the rapid development and design of thermal management materials, analysis of material microstructure images, and the establishment of structure–performance relationships between microstructural features and macroscopic properties.
- 20 November 2025
- Published by Elsevier in Materials Today Physics
- Vol. 59
Thermal expansion prediction in oxide glasses via graph neural networks with temperature-encoded virtual nodes
- 20 November 2025
- Published by Elsevier in Materials Today Physics
- Vol. 59
Thermal expansion prediction in oxide glasses via graph neural networks with temperature-encoded virtual nodes
- Open Access
- 25 February 2025
- Published by Royal Society of Chemistry (RSC) in Journal of Materials Chemistry A
- Vol. 13 (12) , 8715-8725
Accelerating discovery of glass materials in electronic devices through topology-guided machine learning
The trial-and-error method, which is one of the most used methods in the glass industry, is extremely time-consuming and cost-intensive. In order to alleviate energy consumption and improve efficiency in glass development, a multi-tasking framework with topology-informed descriptors is proposed to obtain key properties, such as TEC, Tg, and Tm values, without conducting additional experiments. Herein, we disclosed that the casually generated findings on compositions are difficult to fabricate experimentally, and the predicted results largely deviate from the real values. To counter these issues, a confidence indicator was used to evaluate the composition's reliability, which embodied expert knowledge by classifying glass components into network formers, intermediates, and modifiers through the weighted Euclidean distance. Consequently, we were able to obtain real glass compositions with designed TEC values in the range of 3–12 ppm °C−1 within a short cycle. Achieving a matched sealing with Kovar alloy (∼5.0 ppm °C−1), five generated glasses exhibited TEC values closer to Kovar alloy and good wettability under 1000 °C. This work sheds light on developing efficient and cost-effective methods for the discovery of novel glasses in the field of electronic materials, such as GTMS, LTCC, and MLCC.
- 25 February 2025
- Published by Royal Society of Chemistry (RSC) in Journal of Materials Chemistry A
- Vol. 13 (12) , 8715-8725
Open AccessAccelerating discovery of glass materials in electronic devices through topology-guided machine learning
The trial-and-error method, which is one of the most used methods in the glass industry, is extremely time-consuming and cost-intensive. In order to alleviate energy consumption and improve efficiency in glass development, a multi-tasking framework with topology-informed descriptors is proposed to obtain key properties, such as TEC, Tg, and Tm values, without conducting additional experiments. Herein, we disclosed that the casually generated findings on compositions are difficult to fabricate experimentally, and the predicted results largely deviate from the real values. To counter these issues, a confidence indicator was used to evaluate the composition's reliability, which embodied expert knowledge by classifying glass components into network formers, intermediates, and modifiers through the weighted Euclidean distance. Consequently, we were able to obtain real glass compositions with designed TEC values in the range of 3–12 ppm °C−1 within a short cycle. Achieving a matched sealing with Kovar alloy (∼5.0 ppm °C−1), five generated glasses exhibited TEC values closer to Kovar alloy and good wettability under 1000 °C. This work sheds light on developing efficient and cost-effective methods for the discovery of novel glasses in the field of electronic materials, such as GTMS, LTCC, and MLCC.
- 1 November 2024
- Published by Elsevier in Journal of Power Sources
- Vol. 626
Thermal strain offset strategy for fabrication of glass-ceramic to metal seals with high-reliability
- 1 November 2024
- Published by Elsevier in Journal of Power Sources
- Vol. 626
Thermal strain offset strategy for fabrication of glass-ceramic to metal seals with high-reliability
- 21 January 2024
- Published by Elsevier in Ceramics International
- Vol. 50 (7) , 12006-12016
Enhancement of dielectric properties in MnTiNb2O8-Based microwave ceramic materials
- 21 January 2024
- Published by Elsevier in Ceramics International
- Vol. 50 (7) , 12006-12016
Enhancement of dielectric properties in MnTiNb2O8-Based microwave ceramic materials
- 18 October 2022
- Published by Elsevier in Ceramics International
- Vol. 49 (4) , 5700-5706
Preparation and mechanical properties of the 2.5D ASf/ZrO2 composites after high-temperature heat treatment
- 18 October 2022
- Published by Elsevier in Ceramics International
- Vol. 49 (4) , 5700-5706
Preparation and mechanical properties of the 2.5D ASf/ZrO2 composites after high-temperature heat treatment
- 30 September 2022
- Published by Wiley in Journal of the American Ceramic Society
- Vol. 106 (2) , 967-976
Influence of β‐Si 3 N 4 whiskers on sintering and crystallization of fused silica ceramics
Fused silica ceramics are widely applied for radome materials, crucibles, and vanes, but the mechanical properties were deteriorated due to the cristobalite crystallization. The fused silica ceramics added with by β‐Si 3 N 4 whiskers were prepared by a slip‐casting method to retard the cristobalite crystallization. The influences of the sintering environments and the β‐Si 3 N 4 whiskers on the microstructure and phase structure were investigated. The silanol (Si‐(OH) n ) and oxygen vacancies ( V O ) in the fused silica in formed in different conditions were studied by Fourier Transform Infra‐Red (FT‐IR) and X‐ray photoelectron spectroscopy (XPS), and the results indicated that the ball‐milled produced a large amount of the silanol groups onto the surface of the fused silica particles. The fused silica heated in the vacuum created the maximum oxygen vacancies (24.2%) on the surfaces. Silanol groups reacted with the β‐Si 3 N 4 whiskers, and the O atoms in the silanol groups were fixed into the bulk materials. And the crystallization kinetics and the activation energy of Si 3 N 4w /SiO 2 ceramics at the temperature ranging from 1200 to 1400°C were calculated based on the JMA(Johnson‐Mehl‐Avrami) model. The activation energy of the fused silica ceramics with the addition of the β‐Si 3 N 4 is 506.2 kJ/mol, increased by 23.6% than that of the pure fused silica ceramic.
- 30 September 2022
- Published by Wiley in Journal of the American Ceramic Society
- Vol. 106 (2) , 967-976
Influence of β‐Si 3 N 4 whiskers on sintering and crystallization of fused silica ceramics
Fused silica ceramics are widely applied for radome materials, crucibles, and vanes, but the mechanical properties were deteriorated due to the cristobalite crystallization. The fused silica ceramics added with by β‐Si 3 N 4 whiskers were prepared by a slip‐casting method to retard the cristobalite crystallization. The influences of the sintering environments and the β‐Si 3 N 4 whiskers on the microstructure and phase structure were investigated. The silanol (Si‐(OH) n ) and oxygen vacancies ( V O ) in the fused silica in formed in different conditions were studied by Fourier Transform Infra‐Red (FT‐IR) and X‐ray photoelectron spectroscopy (XPS), and the results indicated that the ball‐milled produced a large amount of the silanol groups onto the surface of the fused silica particles. The fused silica heated in the vacuum created the maximum oxygen vacancies (24.2%) on the surfaces. Silanol groups reacted with the β‐Si 3 N 4 whiskers, and the O atoms in the silanol groups were fixed into the bulk materials. And the crystallization kinetics and the activation energy of Si 3 N 4w /SiO 2 ceramics at the temperature ranging from 1200 to 1400°C were calculated based on the JMA(Johnson‐Mehl‐Avrami) model. The activation energy of the fused silica ceramics with the addition of the β‐Si 3 N 4 is 506.2 kJ/mol, increased by 23.6% than that of the pure fused silica ceramic.
- 6 May 2022
- Published by Wiley in International Journal of Applied Ceramic Technology
- Vol. 19 (5) , 2916-2924
Fabrication and characterization of Si 3 N 4 whisker‐reinforced SiO 2 ceramic for radome materials
- 6 May 2022
- Published by Wiley in International Journal of Applied Ceramic Technology
- Vol. 19 (5) , 2916-2924
Fabrication and characterization of Si 3 N 4 whisker‐reinforced SiO 2 ceramic for radome materials