Scholarlink

<p>The cylinder is the most expensive part of the Internal Combustion Engine in a cylinder-piston system. Friction along the cylinder liner results from the moving parts when the compression and intake strokes occur. Minimizing the abrasion on the cylinder wall is an ongoing research. The reduction of abrasion maintains the cylinder liner and expands its life span, which maintains the engine’s thermal efficiency and reduces emissions resulting from the abrasion. This research investigates how cylinder rotation affects cylinder-liner friction through regression analysis. Our goal is to evaluate the effectiveness of cylinder rotation in minimizing abrasion on the cylinder liner by predicting and comparing friction levels between conventional fixed cylinders and rotating cylinders. We employ machine learning tools to explore the optimal rotation angle for the rotating cylinder. Prediction of wear rate aids in scheduling preventive maintenance for rotating and fixed cylinders to maintain engine efficiency, vehicle fuel economy, and emission standards. Due to the experimental dataset’s limited size and data collection difficulties, we use augmentation and feature scaling techniques to address these challenges. The decision-tree regression model yields a predictive accuracy of <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(R^2\)</EquationSource> <EquationSource Format="MATHML"><math> <msup> <mi>R</mi> <mn>2</mn> </msup> </math></EquationSource> </InlineEquation> = 0.995 and a normalized root mean square error of 0.006, indicating high precision in its predictions. Our prediction model accurately determines the optimal rotation angle based on engine speed. Additionally, it assists in predicting maintenance needs for both fixed and rotating cylinder systems. The decision-tree prediction model offers compelling evidence that implementing a rotating cylinder can extend the cylinder’s lifespan four times compared to a conventional fixed cylinder system.</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-Based Analysis of the Impact of Cylinder-Liner Rotation on Wear Rate in Internal Combustion Engines

  • 期刊论文

  • 发表日期：

    2025年2月10日

查看全文
  • Dana Elrushaidat,
  • Habiba Farrukh,
  • Ammar Alrousan

摘要

The cylinder is the most expensive part of the Internal Combustion Engine in a cylinder-piston system. Friction along the cylinder liner results from the moving parts when the compression and intake strokes occur. Minimizing the abrasion on the cylinder wall is an ongoing research. The reduction of abrasion maintains the cylinder liner and expands its life span, which maintains the engine’s thermal efficiency and reduces emissions resulting from the abrasion. This research investigates how cylinder rotation affects cylinder-liner friction through regression analysis. Our goal is to evaluate the effectiveness of cylinder rotation in minimizing abrasion on the cylinder liner by predicting and comparing friction levels between conventional fixed cylinders and rotating cylinders. We employ machine learning tools to explore the optimal rotation angle for the rotating cylinder. Prediction of wear rate aids in scheduling preventive maintenance for rotating and fixed cylinders to maintain engine efficiency, vehicle fuel economy, and emission standards. Due to the experimental dataset’s limited size and data collection difficulties, we use augmentation and feature scaling techniques to address these challenges. The decision-tree regression model yields a predictive accuracy of \(R^2\) R 2 = 0.995 and a normalized root mean square error of 0.006, indicating high precision in its predictions. Our prediction model accurately determines the optimal rotation angle based on engine speed. Additionally, it assists in predicting maintenance needs for both fixed and rotating cylinder systems. The decision-tree prediction model offers compelling evidence that implementing a rotating cylinder can extend the cylinder’s lifespan four times compared to a conventional fixed cylinder system.