Scholarlink

<p>Machine learning models have been built for the prediction of the coefficient of friction and the friction torque in journal bearing that has been statically loaded. Three distinct regression algorithms—Decision Tree, XGBoost, and Random Forest have been implemented in order to predict the performance behaviours. Four distinct errors, namely Mean Absolute error, Mean Absolute Percentage Error, Mean Squared Error, and R Square Score have been calculated for every model. Performance analysis highlighted that for the prediction of friction torque, XGBoost surpassed the other two models. A similar outcome was observed for the prediction of the coefficient of friction with the XGBoost model yielding the most accurate results. Therefore, XGBoost proved to be the highest-performing model among the three models for this dataset.</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

Prediction of Performance Parameters of Journal Bearing Using Machine Learning Algorithms

  • 期刊论文

  • 发表日期：

    2025年7月5日

查看全文
  • Yashna Nagpal,
  • Arushi Gupta,
  • Tisha Satija,
  • Gauri Maheshwari,
  • Shipra Aggarwal

摘要

Machine learning models have been built for the prediction of the coefficient of friction and the friction torque in journal bearing that has been statically loaded. Three distinct regression algorithms—Decision Tree, XGBoost, and Random Forest have been implemented in order to predict the performance behaviours. Four distinct errors, namely Mean Absolute error, Mean Absolute Percentage Error, Mean Squared Error, and R Square Score have been calculated for every model. Performance analysis highlighted that for the prediction of friction torque, XGBoost surpassed the other two models. A similar outcome was observed for the prediction of the coefficient of friction with the XGBoost model yielding the most accurate results. Therefore, XGBoost proved to be the highest-performing model among the three models for this dataset.