Accelerated discovery of near-zero ablation ultra-high temperature ceramics via GAN-enhanced directionally constrained active learning
In materials science, a significant correlation often exists between material input parameters and their corresponding performance attributes. Nevertheless, the inherent challenges associated with small data obscure these statistical correlations, impeding machine learning models from effectively ca...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co. Ltd.
2025-06-01
|
| Series: | Advanced Powder Materials |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772834X25000235 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850201931813748736 |
|---|---|
| author | Wenjian Guo Fayuan Li Lingyu Wang Li'an Zhu Yicong Ye Zhen Wang Bin Yang Shifeng Zhang Shuxin Bai |
| author_facet | Wenjian Guo Fayuan Li Lingyu Wang Li'an Zhu Yicong Ye Zhen Wang Bin Yang Shifeng Zhang Shuxin Bai |
| author_sort | Wenjian Guo |
| collection | DOAJ |
| description | In materials science, a significant correlation often exists between material input parameters and their corresponding performance attributes. Nevertheless, the inherent challenges associated with small data obscure these statistical correlations, impeding machine learning models from effectively capturing the underlying patterns, thereby hampering efficient optimization of material properties. This work presents a novel active learning framework that integrates generative adversarial networks (GAN) with a directionally constrained expected absolute improvement (EAI) acquisition function to accelerate the discovery of ultra-high temperature ceramics (UHTCs) using small data. The framework employs GAN for data augmentation, symbolic regression for feature weight derivation, and a self-developed EAI function that incorporates input feature importance weighting to quantify bidirectional deviations from zero ablation rate. Through only two iterations, this framework successfully identified the optimal composition of HfB2-3.52SiC-5.23TaSi2, which exhibits robust near-zero ablation rates under plasma ablation at 2500 °C for 200 s, demonstrating superior sampling efficiency compared to conventional active learning approaches. Microstructural analysis reveals that the exceptional performance stems from the formation of a highly viscous HfO2-SiO2-Ta2O5-HfSiO4-Hf3(BO3)4 oxide layer, which provides effective oxygen barrier protection. This work demonstrates an efficient and universal approach for rapid materials discovery using small data. |
| format | Article |
| id | doaj-art-ebeb8eeac11a49d58ad2bba9ef1dc69b |
| institution | OA Journals |
| issn | 2772-834X |
| language | English |
| publishDate | 2025-06-01 |
| publisher | KeAi Communications Co. Ltd. |
| record_format | Article |
| series | Advanced Powder Materials |
| spelling | doaj-art-ebeb8eeac11a49d58ad2bba9ef1dc69b2025-08-20T02:11:54ZengKeAi Communications Co. Ltd.Advanced Powder Materials2772-834X2025-06-014310028710.1016/j.apmate.2025.100287Accelerated discovery of near-zero ablation ultra-high temperature ceramics via GAN-enhanced directionally constrained active learningWenjian Guo0Fayuan Li1Lingyu Wang2Li'an Zhu3Yicong Ye4Zhen Wang5Bin Yang6Shifeng Zhang7Shuxin Bai8College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China; College of Materials Science and Engineering, East China Jiao Tong University, Nanchang 330013, ChinaCollege of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaCollege of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaCollege of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China; Corresponding author.College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China; Corresponding author. College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China.College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China; Corresponding author. College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China.College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaCollege of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaCollege of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaIn materials science, a significant correlation often exists between material input parameters and their corresponding performance attributes. Nevertheless, the inherent challenges associated with small data obscure these statistical correlations, impeding machine learning models from effectively capturing the underlying patterns, thereby hampering efficient optimization of material properties. This work presents a novel active learning framework that integrates generative adversarial networks (GAN) with a directionally constrained expected absolute improvement (EAI) acquisition function to accelerate the discovery of ultra-high temperature ceramics (UHTCs) using small data. The framework employs GAN for data augmentation, symbolic regression for feature weight derivation, and a self-developed EAI function that incorporates input feature importance weighting to quantify bidirectional deviations from zero ablation rate. Through only two iterations, this framework successfully identified the optimal composition of HfB2-3.52SiC-5.23TaSi2, which exhibits robust near-zero ablation rates under plasma ablation at 2500 °C for 200 s, demonstrating superior sampling efficiency compared to conventional active learning approaches. Microstructural analysis reveals that the exceptional performance stems from the formation of a highly viscous HfO2-SiO2-Ta2O5-HfSiO4-Hf3(BO3)4 oxide layer, which provides effective oxygen barrier protection. This work demonstrates an efficient and universal approach for rapid materials discovery using small data.http://www.sciencedirect.com/science/article/pii/S2772834X25000235UHTCsAblation resistantGANActive learningMicrostructure |
| spellingShingle | Wenjian Guo Fayuan Li Lingyu Wang Li'an Zhu Yicong Ye Zhen Wang Bin Yang Shifeng Zhang Shuxin Bai Accelerated discovery of near-zero ablation ultra-high temperature ceramics via GAN-enhanced directionally constrained active learning Advanced Powder Materials UHTCs Ablation resistant GAN Active learning Microstructure |
| title | Accelerated discovery of near-zero ablation ultra-high temperature ceramics via GAN-enhanced directionally constrained active learning |
| title_full | Accelerated discovery of near-zero ablation ultra-high temperature ceramics via GAN-enhanced directionally constrained active learning |
| title_fullStr | Accelerated discovery of near-zero ablation ultra-high temperature ceramics via GAN-enhanced directionally constrained active learning |
| title_full_unstemmed | Accelerated discovery of near-zero ablation ultra-high temperature ceramics via GAN-enhanced directionally constrained active learning |
| title_short | Accelerated discovery of near-zero ablation ultra-high temperature ceramics via GAN-enhanced directionally constrained active learning |
| title_sort | accelerated discovery of near zero ablation ultra high temperature ceramics via gan enhanced directionally constrained active learning |
| topic | UHTCs Ablation resistant GAN Active learning Microstructure |
| url | http://www.sciencedirect.com/science/article/pii/S2772834X25000235 |
| work_keys_str_mv | AT wenjianguo accelerateddiscoveryofnearzeroablationultrahightemperatureceramicsviaganenhanceddirectionallyconstrainedactivelearning AT fayuanli accelerateddiscoveryofnearzeroablationultrahightemperatureceramicsviaganenhanceddirectionallyconstrainedactivelearning AT lingyuwang accelerateddiscoveryofnearzeroablationultrahightemperatureceramicsviaganenhanceddirectionallyconstrainedactivelearning AT lianzhu accelerateddiscoveryofnearzeroablationultrahightemperatureceramicsviaganenhanceddirectionallyconstrainedactivelearning AT yicongye accelerateddiscoveryofnearzeroablationultrahightemperatureceramicsviaganenhanceddirectionallyconstrainedactivelearning AT zhenwang accelerateddiscoveryofnearzeroablationultrahightemperatureceramicsviaganenhanceddirectionallyconstrainedactivelearning AT binyang accelerateddiscoveryofnearzeroablationultrahightemperatureceramicsviaganenhanceddirectionallyconstrainedactivelearning AT shifengzhang accelerateddiscoveryofnearzeroablationultrahightemperatureceramicsviaganenhanceddirectionallyconstrainedactivelearning AT shuxinbai accelerateddiscoveryofnearzeroablationultrahightemperatureceramicsviaganenhanceddirectionallyconstrainedactivelearning |