Scholarlink

<p>Carbon fiber-reinforced polyamide is an exceptional material that can be broadly applied in industrial applications, including automotive industries. Its high strength and ability to withstand high-temperature atmospheres make it a desirable material for automotive applications. A wide range of factors, including material type, printing parameters like layer height, print speed, and design features, impacts the mechanical properties of additively manufactured specimens. Hence, it is important to determine the properties of such specimens to select the appropriate applications for the material. However, determining the mechanical properties of additively manufactured parts needs a costly setup and is a time-consuming process. To avoid such complications in unique materials, the properties can be projected using machine learning. In this examination, an effort is made to forecast the hardness of 3D-printed polyamide—carbon fiber parts using machine learning models. Machine learning algorithms are capable of modeling complex, nonlinear relationships between these variables more successfully than traditional analytical methods. They can explore large datasets to recognize patterns and relationships that may not be immediately apparent. The polyamide—carbon fiber samples are printed by altering the process parameters, including layer height, infill density, infill pattern, and raster orientation. A total of 81 samples were manufactured, and an effort was made to predict the hardness of the samples. The machine learning models were analyzed to find the most suitable model that could predict the hardness values closer to the measured values.</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

Impact of Process Parameters on Hardness of Melt Fabricated PA6 Carbon Fiber-Reinforced Composites and Prediction of Properties Using Machine Learning

  • 期刊论文

  • 发表日期：

    2025年5月13日

查看全文
  • Dhinakaran Veeman,
  • Murugan Vellaisamy,
  • Pradeep Castro Ponnusamy,
  • Dhushyanth Palanisamy Subathra,
  • Jitendra Kumar Katiyar

摘要

Carbon fiber-reinforced polyamide is an exceptional material that can be broadly applied in industrial applications, including automotive industries. Its high strength and ability to withstand high-temperature atmospheres make it a desirable material for automotive applications. A wide range of factors, including material type, printing parameters like layer height, print speed, and design features, impacts the mechanical properties of additively manufactured specimens. Hence, it is important to determine the properties of such specimens to select the appropriate applications for the material. However, determining the mechanical properties of additively manufactured parts needs a costly setup and is a time-consuming process. To avoid such complications in unique materials, the properties can be projected using machine learning. In this examination, an effort is made to forecast the hardness of 3D-printed polyamide—carbon fiber parts using machine learning models. Machine learning algorithms are capable of modeling complex, nonlinear relationships between these variables more successfully than traditional analytical methods. They can explore large datasets to recognize patterns and relationships that may not be immediately apparent. The polyamide—carbon fiber samples are printed by altering the process parameters, including layer height, infill density, infill pattern, and raster orientation. A total of 81 samples were manufactured, and an effort was made to predict the hardness of the samples. The machine learning models were analyzed to find the most suitable model that could predict the hardness values closer to the measured values.