Scholarlink

<p>As fossil fuel reserves are being depleted at a rapid pace and their prices remain volatile, there is a growing impetus to investigate alternative fuels for diesel engines. Since, the diesel engines are widely utilised in many sector such as industrial, transportation, and energy sector. This study evaluates how operational parameters affect CRDI diesel engines using ternary blends of biodiesel (WCO + WPO), ethanol, and diesel at different ratios, considering variations in FIT, EGR, and engine load. A hybrid optimisation model ANN coupled with RSM was employed to predict and optimise output responses. Results demonstrate ANN models accurately predict engine performance/emissions (R-value = 0.92–0.97), with R<sup>2</sup> values of 87.31% (BTE), 93.84% (EGT), 86.39% (CO), 95.84% (HC), 94.71% (NOx), and 88.80% (smoke). The BBD based RSM model optimization achieved near-perfect predictability (R<sup>2</sup>-value = 98.36–99.35%). The RSM optimiser identified optimal values for blend% (19.6%), FIT (25<sup>o</sup>bTDC), EGR (6.5%), and load (23.23%), resulting in improved BTE (15.63%) and reduced EGT (432.9&#xa0;K), CO (0.2504 vol.%), HC (22.01&#xa0;ppm), NOx (242.04&#xa0;ppm), and smoke (9.36%) emissions. This study found that using RSM and ANN models with high precision confidence improves engine performance estimation.</p> Graphical Abstract <p></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

ANN–RSM Synergistic Optimization for CRDI Engine Performance and Emissions Using Novel Waste-Based Biodiesel–Ethanol–Diesel Ternary Blends

  • 期刊论文

  • 发表日期：

    2025年9月16日

查看全文
  • Manish Kumar,
  • Naushad Ahmad Ansari,
  • Raghvendra Gautam

摘要

As fossil fuel reserves are being depleted at a rapid pace and their prices remain volatile, there is a growing impetus to investigate alternative fuels for diesel engines. Since, the diesel engines are widely utilised in many sector such as industrial, transportation, and energy sector. This study evaluates how operational parameters affect CRDI diesel engines using ternary blends of biodiesel (WCO + WPO), ethanol, and diesel at different ratios, considering variations in FIT, EGR, and engine load. A hybrid optimisation model ANN coupled with RSM was employed to predict and optimise output responses. Results demonstrate ANN models accurately predict engine performance/emissions (R-value = 0.92–0.97), with R2 values of 87.31% (BTE), 93.84% (EGT), 86.39% (CO), 95.84% (HC), 94.71% (NOx), and 88.80% (smoke). The BBD based RSM model optimization achieved near-perfect predictability (R2-value = 98.36–99.35%). The RSM optimiser identified optimal values for blend% (19.6%), FIT (25obTDC), EGR (6.5%), and load (23.23%), resulting in improved BTE (15.63%) and reduced EGT (432.9 K), CO (0.2504 vol.%), HC (22.01 ppm), NOx (242.04 ppm), and smoke (9.36%) emissions. This study found that using RSM and ANN models with high precision confidence improves engine performance estimation.

Graphical Abstract