Wenjian Guo , Fayuan Li , Lingyu Wang , Li'an Zhu , Yicong Ye , Zhen Wang , Bin Yang , Shifeng Zhang , Shuxin Bai
{"title":"通过gan增强的定向约束主动学习加速发现近零烧蚀超高温陶瓷","authors":"Wenjian Guo , Fayuan Li , Lingyu Wang , Li'an Zhu , Yicong Ye , Zhen Wang , Bin Yang , Shifeng Zhang , Shuxin Bai","doi":"10.1016/j.apmate.2025.100287","DOIUrl":null,"url":null,"abstract":"<div><div>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 HfB<sub>2</sub>-3.52SiC-5.23TaSi<sub>2</sub>, 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 HfO<sub>2</sub>-SiO<sub>2</sub>-Ta<sub>2</sub>O<sub>5</sub>-HfSiO<sub>4</sub>-Hf<sub>3</sub>(BO<sub>3</sub>)<sub>4</sub> oxide layer, which provides effective oxygen barrier protection. This work demonstrates an efficient and universal approach for rapid materials discovery using small data.</div></div>","PeriodicalId":7283,"journal":{"name":"Advanced Powder Materials","volume":"4 3","pages":"Article 100287"},"PeriodicalIF":0.0000,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Accelerated discovery of near-zero ablation ultra-high temperature ceramics via GAN-enhanced directionally constrained active learning\",\"authors\":\"Wenjian Guo , Fayuan Li , Lingyu Wang , Li'an Zhu , Yicong Ye , Zhen Wang , Bin Yang , Shifeng Zhang , Shuxin Bai\",\"doi\":\"10.1016/j.apmate.2025.100287\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>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 HfB<sub>2</sub>-3.52SiC-5.23TaSi<sub>2</sub>, 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 HfO<sub>2</sub>-SiO<sub>2</sub>-Ta<sub>2</sub>O<sub>5</sub>-HfSiO<sub>4</sub>-Hf<sub>3</sub>(BO<sub>3</sub>)<sub>4</sub> oxide layer, which provides effective oxygen barrier protection. This work demonstrates an efficient and universal approach for rapid materials discovery using small data.</div></div>\",\"PeriodicalId\":7283,\"journal\":{\"name\":\"Advanced Powder Materials\",\"volume\":\"4 3\",\"pages\":\"Article 100287\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-03-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Advanced Powder Materials\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2772834X25000235\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advanced Powder Materials","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2772834X25000235","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
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 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.