Zirui Du, Chaokun Song, Kang Guan, Pinggen Rao, Xiaohui Yang, Longteng Bai, Shengbo Shi, Jing Wang, Yongsheng Liu, Qingfeng Zeng
{"title":"高抗烧蚀改性C/SiC复合材料:数据驱动的智能设计与实验验证","authors":"Zirui Du, Chaokun Song, Kang Guan, Pinggen Rao, Xiaohui Yang, Longteng Bai, Shengbo Shi, Jing Wang, Yongsheng Liu, Qingfeng Zeng","doi":"10.1111/jace.70209","DOIUrl":null,"url":null,"abstract":"<p>Improving the ablation resistance of carbon fiber-reinforced silicon carbide (C/SiC) composites is essential to meet the stringent demands of ultra-high-temperature applications, but traditional empirical design approaches are resource-intensive and time-consuming. This study presents a novel data-driven methodology integrating machine learning (ML) with experimental validation to optimize C/SiC composite ablation resistance. Through systematic data preprocessing and feature analysis of 102 experimental samples, an XGBoost regression model was developed, achieving satisfactory prediction accuracy (mean absolute error < ∼0.075, mean squared error < ∼0.015, and coefficient of determination [R<sup>2</sup>] > ∼0.75) for ablation rate. SHapley Additive exPlanations (SHAP) analysis revealed that modifier properties, particularly standard enthalpy and melting point, predominantly influence ablation resistance. The ML-guided design strategy, implemented through Bayesian optimization, led to the successful fabrication of ZrB<sub>2</sub>-modified C/SiC composites with exceptional ablation resistance. The optimized composite, containing approximately 20.0 vol.% ZrB<sub>2</sub>, achieved a linear ablation rate of 2.083 µm/s under oxyacetylene torch testing, representing a significant improvement over conventional compositions. Microstructural analysis confirmed the formation of a dense SiO<sub>2</sub>‒B<sub>2</sub>O<sub>3</sub> protective layer, validating the predicted mechanism of enhanced ablation resistance. This work establishes a robust framework for accelerated development of ultra-high-temperature ceramics and demonstrates the efficacy of ML-driven approaches in materials design optimization. An object-oriented software with interactive graphical user interface has been developed. These methodologies have been integrated into an interactive software, Modified C/SiC Ablation Rate intelligent design Software (MARS), creating an efficient tool for the accelerated design of C/SiC composites with tailored ablation performance.</p>","PeriodicalId":200,"journal":{"name":"Journal of the American Ceramic Society","volume":"108 12","pages":""},"PeriodicalIF":3.8000,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Modified C/SiC composites with high ablation resistance: Data-driven intelligent design and experimental validation\",\"authors\":\"Zirui Du, Chaokun Song, Kang Guan, Pinggen Rao, Xiaohui Yang, Longteng Bai, Shengbo Shi, Jing Wang, Yongsheng Liu, Qingfeng Zeng\",\"doi\":\"10.1111/jace.70209\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Improving the ablation resistance of carbon fiber-reinforced silicon carbide (C/SiC) composites is essential to meet the stringent demands of ultra-high-temperature applications, but traditional empirical design approaches are resource-intensive and time-consuming. This study presents a novel data-driven methodology integrating machine learning (ML) with experimental validation to optimize C/SiC composite ablation resistance. Through systematic data preprocessing and feature analysis of 102 experimental samples, an XGBoost regression model was developed, achieving satisfactory prediction accuracy (mean absolute error < ∼0.075, mean squared error < ∼0.015, and coefficient of determination [R<sup>2</sup>] > ∼0.75) for ablation rate. SHapley Additive exPlanations (SHAP) analysis revealed that modifier properties, particularly standard enthalpy and melting point, predominantly influence ablation resistance. The ML-guided design strategy, implemented through Bayesian optimization, led to the successful fabrication of ZrB<sub>2</sub>-modified C/SiC composites with exceptional ablation resistance. The optimized composite, containing approximately 20.0 vol.% ZrB<sub>2</sub>, achieved a linear ablation rate of 2.083 µm/s under oxyacetylene torch testing, representing a significant improvement over conventional compositions. Microstructural analysis confirmed the formation of a dense SiO<sub>2</sub>‒B<sub>2</sub>O<sub>3</sub> protective layer, validating the predicted mechanism of enhanced ablation resistance. This work establishes a robust framework for accelerated development of ultra-high-temperature ceramics and demonstrates the efficacy of ML-driven approaches in materials design optimization. An object-oriented software with interactive graphical user interface has been developed. These methodologies have been integrated into an interactive software, Modified C/SiC Ablation Rate intelligent design Software (MARS), creating an efficient tool for the accelerated design of C/SiC composites with tailored ablation performance.</p>\",\"PeriodicalId\":200,\"journal\":{\"name\":\"Journal of the American Ceramic Society\",\"volume\":\"108 12\",\"pages\":\"\"},\"PeriodicalIF\":3.8000,\"publicationDate\":\"2025-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of the American Ceramic Society\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://ceramics.onlinelibrary.wiley.com/doi/10.1111/jace.70209\",\"RegionNum\":3,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATERIALS SCIENCE, CERAMICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the American Ceramic Society","FirstCategoryId":"88","ListUrlMain":"https://ceramics.onlinelibrary.wiley.com/doi/10.1111/jace.70209","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, CERAMICS","Score":null,"Total":0}
Modified C/SiC composites with high ablation resistance: Data-driven intelligent design and experimental validation
Improving the ablation resistance of carbon fiber-reinforced silicon carbide (C/SiC) composites is essential to meet the stringent demands of ultra-high-temperature applications, but traditional empirical design approaches are resource-intensive and time-consuming. This study presents a novel data-driven methodology integrating machine learning (ML) with experimental validation to optimize C/SiC composite ablation resistance. Through systematic data preprocessing and feature analysis of 102 experimental samples, an XGBoost regression model was developed, achieving satisfactory prediction accuracy (mean absolute error < ∼0.075, mean squared error < ∼0.015, and coefficient of determination [R2] > ∼0.75) for ablation rate. SHapley Additive exPlanations (SHAP) analysis revealed that modifier properties, particularly standard enthalpy and melting point, predominantly influence ablation resistance. The ML-guided design strategy, implemented through Bayesian optimization, led to the successful fabrication of ZrB2-modified C/SiC composites with exceptional ablation resistance. The optimized composite, containing approximately 20.0 vol.% ZrB2, achieved a linear ablation rate of 2.083 µm/s under oxyacetylene torch testing, representing a significant improvement over conventional compositions. Microstructural analysis confirmed the formation of a dense SiO2‒B2O3 protective layer, validating the predicted mechanism of enhanced ablation resistance. This work establishes a robust framework for accelerated development of ultra-high-temperature ceramics and demonstrates the efficacy of ML-driven approaches in materials design optimization. An object-oriented software with interactive graphical user interface has been developed. These methodologies have been integrated into an interactive software, Modified C/SiC Ablation Rate intelligent design Software (MARS), creating an efficient tool for the accelerated design of C/SiC composites with tailored ablation performance.
期刊介绍:
The Journal of the American Ceramic Society contains records of original research that provide insight into or describe the science of ceramic and glass materials and composites based on ceramics and glasses. These papers include reports on discovery, characterization, and analysis of new inorganic, non-metallic materials; synthesis methods; phase relationships; processing approaches; microstructure-property relationships; and functionalities. Of great interest are works that support understanding founded on fundamental principles using experimental, theoretical, or computational methods or combinations of those approaches. All the published papers must be of enduring value and relevant to the science of ceramics and glasses or composites based on those materials.
Papers on fundamental ceramic and glass science are welcome including those in the following areas:
Enabling materials for grand challenges[...]
Materials design, selection, synthesis and processing methods[...]
Characterization of compositions, structures, defects, and properties along with new methods [...]
Mechanisms, Theory, Modeling, and Simulation[...]
JACerS accepts submissions of full-length Articles reporting original research, in-depth Feature Articles, Reviews of the state-of-the-art with compelling analysis, and Rapid Communications which are short papers with sufficient novelty or impact to justify swift publication.