Scholarlink

<p>High-temperature solid particle erosion (HTSPE) limits the operational life of titanium alloys used in aerospace and power generation systems. This study develops a machine learning–driven predictive framework for the Ti–6Al–5Zr–0.5Mo–0.2Si alloy to estimate and optimize its erosion rate under high-velocity particle impact. Experimental datasets were generated by varying particle velocity, impingement angle, and specimen surface temperature. Three ensemble learning models: Random Forest, Gradient Boosting, and XGBoost were trained to capture nonlinear interactions among these parameters. The Gradient Boosting model achieved the best performance with an R<sup>2</sup> of 0.9425 and an RMSE of 0.00012. Model predictions identified an optimal condition corresponding to a velocity of ~ 33&#xa0;m/s, surface temperature of ~ 204&#xa0;°C, and impact angle of 70°, yielding a minimum material removal rate of 0.000530&#xa0;mg/g. The results demonstrate that data-driven modelling can effectively capture erosion trends within the investigated parameter range and provide useful predictive insights for identifying erosion-resistant operating conditions. This framework bridges data analytics and physical metallurgy, enabling predictive optimisation of titanium alloys subjected to combined thermal and mechanical loading.</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

Sustainable assessment of high-temperature solid particle erosion behaviour of Ti–6Al–5Zr–0.5Mo–0.2Si via experimental and data-driven approaches

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月8日

查看全文
  • S. Shashikumar,
  • Yogesh Bhikusing Jadhao,
  • Shrishail B. Sollapur,
  • Sandip B. Patil,
  • Ganesh Shridhar Raghtate,
  • Sameer Sayyad,
  • Abhijit Bhowmik,
  • Nagaraj Ashok

摘要

High-temperature solid particle erosion (HTSPE) limits the operational life of titanium alloys used in aerospace and power generation systems. This study develops a machine learning–driven predictive framework for the Ti–6Al–5Zr–0.5Mo–0.2Si alloy to estimate and optimize its erosion rate under high-velocity particle impact. Experimental datasets were generated by varying particle velocity, impingement angle, and specimen surface temperature. Three ensemble learning models: Random Forest, Gradient Boosting, and XGBoost were trained to capture nonlinear interactions among these parameters. The Gradient Boosting model achieved the best performance with an R2 of 0.9425 and an RMSE of 0.00012. Model predictions identified an optimal condition corresponding to a velocity of ~ 33 m/s, surface temperature of ~ 204 °C, and impact angle of 70°, yielding a minimum material removal rate of 0.000530 mg/g. The results demonstrate that data-driven modelling can effectively capture erosion trends within the investigated parameter range and provide useful predictive insights for identifying erosion-resistant operating conditions. This framework bridges data analytics and physical metallurgy, enabling predictive optimisation of titanium alloys subjected to combined thermal and mechanical loading.