Scholarlink

<p>This study investigates the mechanical properties and microstructural characteristics of aluminum/silicon nitride (Al/SiN) composites fabricated via the powder metallurgy process. Optimal processing conditions, including 7% silicon nitride content and sintering at 550&#xa0;°C for 120&#xa0;min, were identified, leading to significant improvements in both compressive and tensile strengths. Microstructural analysis using scanning electron microscopy revealed a uniform distribution of silicon nitride reinforcement within the aluminum matrix, accompanied by strong interfacial bonding. This effective reinforcement-matrix interaction is critical for efficient load transfer and the resulting enhancement of mechanical properties. To predict the mechanical behavior of the composites, various machine learning models were employed, with the Random Forest algorithm achieving the highest accuracy, as indicated by an R-squared value of 0.9616. This demonstrates the efficacy of machine learning in material science, particularly for optimizing composite design and manufacturing processes. The findings emphasize the value of integrating advanced modeling techniques with detailed microstructural analysis to deepen the understanding of material behavior. In summary, this research advances the development of high-performance composites tailored for specific industrial applications and highlights the potential of data-driven approaches for optimizing material properties, providing a foundation for future studies in this field.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

From fabrication to prediction: unraveling the tensile strength of Al/SiN composites through machine learning

  • 期刊论文

  • 发表日期：

    2025年3月17日

查看全文
  • Guttikonda Manohar,
  • Venkateswara Reddy,
  • Vaishali

摘要

This study investigates the mechanical properties and microstructural characteristics of aluminum/silicon nitride (Al/SiN) composites fabricated via the powder metallurgy process. Optimal processing conditions, including 7% silicon nitride content and sintering at 550 °C for 120 min, were identified, leading to significant improvements in both compressive and tensile strengths. Microstructural analysis using scanning electron microscopy revealed a uniform distribution of silicon nitride reinforcement within the aluminum matrix, accompanied by strong interfacial bonding. This effective reinforcement-matrix interaction is critical for efficient load transfer and the resulting enhancement of mechanical properties. To predict the mechanical behavior of the composites, various machine learning models were employed, with the Random Forest algorithm achieving the highest accuracy, as indicated by an R-squared value of 0.9616. This demonstrates the efficacy of machine learning in material science, particularly for optimizing composite design and manufacturing processes. The findings emphasize the value of integrating advanced modeling techniques with detailed microstructural analysis to deepen the understanding of material behavior. In summary, this research advances the development of high-performance composites tailored for specific industrial applications and highlights the potential of data-driven approaches for optimizing material properties, providing a foundation for future studies in this field.