Scholarlink

<p>High-density polyethylene (HDPE) is widely used in tribological components, yet the influence of surface texture orientation on its frictional and wear behaviour remains underexplored. This study examines the effect of grinding angles (0°, 30°, 45°, 60°, 90°) on the coefficient of friction (COF), wear depth, and debris morphology of HDPE under dry and lubricated sliding at a 30&#xa0;N load. Under dry conditions, the COF increases from 0.30 at 0° to 0.42–0.45 at 45°, while wear depth rises from ~ 25&#xa0;μm to over 100&#xa0;μm. Lubrication significantly reduces friction, with COF dropping to 0.18–0.20 at 0° and 0.28–0.32 at 45°, accompanied by more than a 50% reduction in wear depth. Debris analysis shows finer, spherical particles under lubrication (ECD 8–30&#xa0;μm) and elongated particles in dry sliding (AR 4–7), indicating distinct wear mechanisms. The novelty of this work lies in integrating experimental tribology with supervised machine learning models (Decision Tree, Random Forest) to predict COF and wear depth with high accuracy (R<sup>2</sup> &gt;&#xa0;0.90), and in using image-based ML classification to correlate debris morphology with grinding orientation. This combined framework offers a predictive pathway for optimizing HDPE-based tribo-component design.</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

Machine Learning-Enabled Analysis of Surface Texture Orientation Effects on Wear Debris Morphology and Tribological Performance of High-Density Polyethene (HDPE)

  • 期刊论文

  • 发表日期：

    2025年12月4日

查看全文
  • Rajeev Kumar Gupta,
  • M. Rajanish,
  • R. PremChand,
  • Mahadeva Prasad,
  • Rayappa S. Mahale,
  • Ravitej Yellampalli Prakash,
  • M. Madhusudan,
  • Jayatirtha M. Patil,
  • B. Nityanand,
  • Balachandra Halemani,
  • O. Abhilash,
  • Joy Mondal

摘要

High-density polyethylene (HDPE) is widely used in tribological components, yet the influence of surface texture orientation on its frictional and wear behaviour remains underexplored. This study examines the effect of grinding angles (0°, 30°, 45°, 60°, 90°) on the coefficient of friction (COF), wear depth, and debris morphology of HDPE under dry and lubricated sliding at a 30 N load. Under dry conditions, the COF increases from 0.30 at 0° to 0.42–0.45 at 45°, while wear depth rises from ~ 25 μm to over 100 μm. Lubrication significantly reduces friction, with COF dropping to 0.18–0.20 at 0° and 0.28–0.32 at 45°, accompanied by more than a 50% reduction in wear depth. Debris analysis shows finer, spherical particles under lubrication (ECD 8–30 μm) and elongated particles in dry sliding (AR 4–7), indicating distinct wear mechanisms. The novelty of this work lies in integrating experimental tribology with supervised machine learning models (Decision Tree, Random Forest) to predict COF and wear depth with high accuracy (R2 > 0.90), and in using image-based ML classification to correlate debris morphology with grinding orientation. This combined framework offers a predictive pathway for optimizing HDPE-based tribo-component design.