Scholarlink

<p>Magnesium–aluminium–silicon (Mg-Al-Si) alloy is commonly employed in advanced aerospace, defense, automotive, and thermal management sectors due to its structural and functional properties. Some of the features of this alloy include higher specific strength, higher specific stiffness, lower density, and exceptional damping properties. The majority of Mg-Al-Si alloys are produced through a stir casting method. The work’s goal is to optimize the input parameters, which include load, sliding distance, sliding time, and the % of aluminum and silicon (0, 1, 2%) during a dry slide. The wear test was performed using a pin-on-disk instrument with a constant velocity of 1&#xa0;m/s. The experimental setup was created using Taguchi’s technique, and all tests were conducted on the L27 orthogonal array. The optimal conditions for wear loss were identified using ANOVA and regression analysis, which suggest that the smaller approach is the best. The experimental results have been compared with ANOVA and artificial neural network (ANN). The study identified that load is the most significant influencing variable on wear loss, accounting for 50.13%. In comparison with the other variables, it was concluded that the ANN method excelled beyond the Taguchi technique in predicting wear loss.</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

Optimizing Tribological Characteristics in Magnesium–Aluminum–Silicon Alloys through the Application of the Taguchi Method and Artificial Neural Network

  • 期刊论文

  • 发表日期：

    2025年11月3日

查看全文
  • A. Nagaraj,
  • S. Gopalakrishnan,
  • D. Shivalingappa,
  • V. Jayaseelan

摘要

Magnesium–aluminium–silicon (Mg-Al-Si) alloy is commonly employed in advanced aerospace, defense, automotive, and thermal management sectors due to its structural and functional properties. Some of the features of this alloy include higher specific strength, higher specific stiffness, lower density, and exceptional damping properties. The majority of Mg-Al-Si alloys are produced through a stir casting method. The work’s goal is to optimize the input parameters, which include load, sliding distance, sliding time, and the % of aluminum and silicon (0, 1, 2%) during a dry slide. The wear test was performed using a pin-on-disk instrument with a constant velocity of 1 m/s. The experimental setup was created using Taguchi’s technique, and all tests were conducted on the L27 orthogonal array. The optimal conditions for wear loss were identified using ANOVA and regression analysis, which suggest that the smaller approach is the best. The experimental results have been compared with ANOVA and artificial neural network (ANN). The study identified that load is the most significant influencing variable on wear loss, accounting for 50.13%. In comparison with the other variables, it was concluded that the ANN method excelled beyond the Taguchi technique in predicting wear loss.