Scholarlink

<p>To explore the mechanical properties of nickel-based alloys, it is imperative to consider a comprehensive set of factors, including intrinsic material properties, environmental influences, and manufacturing processes. However, due to the challenges of experimental testing and the growing demand for alloy performance, predicting the mechanical behavior of such alloys becomes crucial. Therefore, this study aims to establish a comprehensive interpretable machine learning workflow for predicting and analyzing the Young's modulus of the IN718 alloy. The results reveal a significant correlation between the Young's modulus and inherent characteristics of IN718 alloy, providing evidence for a robust coupling relationship among these attributes. Notably, it is found that the Young's modulus resonance frequency range for the IN718 alloy falls between 3800 and 4500&#xa0;Hz. Moreover, by comparing the disparities between traditional casting and additive manufacturing processes, it is found that the contribution values for the 0° manufacturing direction are entirely opposite to those of other directions. In additive manufacturing, low-temperature environments and a 90° manufacturing angle exert a strong positive influence on the Young's modulus. This observation is further validated through a dual machine learning approach, affirming a strong causal relationship between the manufacturing angle and the Young's modulus in additive manufacturing methods.<?oxy_comment_start comment="Kindly provide description for the symbol [#] presented in author Wenzhao Li."?><?oxy_comment_end??><?oxy_comment_start comment="Sorry, this is a mistake, please delete the symbol [#]."?><?oxy_comment_end??></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

Study on the Young's Modulus of Different Variants of IN718 Alloy in Additive Manufacturing and Traditional Manufacturing Using Interpretable Machine Learning Methods

  • 期刊论文

  • 发表日期：

    2025年6月23日

查看全文
  • Wenzhao Li,
  • Mingji Liu,
  • Wenping Wu,
  • Bingfei Liu

摘要

To explore the mechanical properties of nickel-based alloys, it is imperative to consider a comprehensive set of factors, including intrinsic material properties, environmental influences, and manufacturing processes. However, due to the challenges of experimental testing and the growing demand for alloy performance, predicting the mechanical behavior of such alloys becomes crucial. Therefore, this study aims to establish a comprehensive interpretable machine learning workflow for predicting and analyzing the Young's modulus of the IN718 alloy. The results reveal a significant correlation between the Young's modulus and inherent characteristics of IN718 alloy, providing evidence for a robust coupling relationship among these attributes. Notably, it is found that the Young's modulus resonance frequency range for the IN718 alloy falls between 3800 and 4500 Hz. Moreover, by comparing the disparities between traditional casting and additive manufacturing processes, it is found that the contribution values for the 0° manufacturing direction are entirely opposite to those of other directions. In additive manufacturing, low-temperature environments and a 90° manufacturing angle exert a strong positive influence on the Young's modulus. This observation is further validated through a dual machine learning approach, affirming a strong causal relationship between the manufacturing angle and the Young's modulus in additive manufacturing methods.