Scholarlink

<p>The aim of this study was to investigate the simultaneous influence of B<sub>4</sub>C, BN and SiC reinforcement and heat treatment on the mechanical and tribological behavior of Al 7075 composite materials produced through Inert Gas Assisted Stir Casting. The developed composites showed a significant reduction in material density of 0.96% and substantial enhancements in hardness and ultimate tensile strength of up to 154% and 24.1%, respectively. The analysis of wear rate (WR) indicates that load(<i>L</i>) is the predominant parameter on wear, followed by age hardening time (AT), sliding distance (D), and sliding speed(N) with optimal test parameters determined as ageing time of 10&#xa0;Hours (h), applied load of 15&#xa0;N, sliding speed of 400&#xa0;rpm and total sliding distance of 500&#xa0;m. Using the wear results acquired during the experimental testing, three different machine learning techniques such as Decision Tree (DT), Random Forest (RF), and Gradient Boost Regression (GBR) were used to predict the&#xa0;wear behaviour. Among the three machine learning techniques tested, the Gradient Boost Regression technique yielded the highest accuracy and best predictions with <i>R</i><sup>2</sup> values of 0.98451 for training and 0.92478 for testing. The integration of both experimental and predictive methodologies presented in this research study presents a viable method for determining optimal processing conditions for creating Al 7075 hybrid composites with improved mechanical and wear properties.</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

Experimental Investigation and Machine Learning Modeling on the Tribological Characteristics of Heat Treated AA7075/B4C/BN/SiC Hybrid Composites

  • 期刊论文

  • 发表日期：

    2026年5月11日

查看全文
  • Seelam Pichi Reddy,
  • Dhanunjay Kumar Ammisetti,
  • Simhadri Raju Juvvala,
  • Annapareddy V. N. Reddy

摘要

The aim of this study was to investigate the simultaneous influence of B4C, BN and SiC reinforcement and heat treatment on the mechanical and tribological behavior of Al 7075 composite materials produced through Inert Gas Assisted Stir Casting. The developed composites showed a significant reduction in material density of 0.96% and substantial enhancements in hardness and ultimate tensile strength of up to 154% and 24.1%, respectively. The analysis of wear rate (WR) indicates that load(L) is the predominant parameter on wear, followed by age hardening time (AT), sliding distance (D), and sliding speed(N) with optimal test parameters determined as ageing time of 10 Hours (h), applied load of 15 N, sliding speed of 400 rpm and total sliding distance of 500 m. Using the wear results acquired during the experimental testing, three different machine learning techniques such as Decision Tree (DT), Random Forest (RF), and Gradient Boost Regression (GBR) were used to predict the wear behaviour. Among the three machine learning techniques tested, the Gradient Boost Regression technique yielded the highest accuracy and best predictions with R2 values of 0.98451 for training and 0.92478 for testing. The integration of both experimental and predictive methodologies presented in this research study presents a viable method for determining optimal processing conditions for creating Al 7075 hybrid composites with improved mechanical and wear properties.