Scholarlink

<p>The primary objective of this study is to develop a hybrid modeling-optimization framework for improving the performance and emission characteristics of a dual-fuel diesel engine. The work focuses on the effect of engine operating parameters and exhaust gas recirculation (EGR) rates when using bio-hydrogen (HHO) and magnesium oxide (MgO) nanoparticle-enhanced aloe vera biodiesel/diesel blends. A Central Composite Design (CCD) was used to generate an L<sub>30</sub> array, including four factors at five levels. Experiments were carried out using a fixed B20MgO90 (20% biodiesel, 80% diesel, And 90 ppm magnesium oxide) pilot fuel blend while varying engine load, compression ratio, HHO flow rate, and EGR rate. An ANN model was developed using the experimental data to predict key engine response parameters (BTE, BSFC, CO, HC, and NO<sub>x</sub>). The developed ANN model established high predictive accuracy, attaining an overall correlation coefficient (R) of 0.9963 and a mean squared error (MSE) of 0.0139. Multi-Output Response Surface Methodology was utilized for optimization, showing that An engine load of 77.26%, CR of 18:1, bio-hydrogen flow rate of 3.61&#xa0;L/min, And An EGR rate of 10.42% are the optimal operating conditions. Under these conditions, the predicted optimal responses for BTE, BSFC, CO, HC, And NOx were found to be 34.07%, 0.4448&#xa0;kg/kWh, 0.619% vol., 38.88 ppm, And 707.99 ppm, respectively. Experimental validation showed a maximum error of 6.61%, confirming the model’s reliability. This study shows that the combined ANN-RSM approach is an effective hybrid method for modeling, predicting, and optimizing the performance of dual-fuel engines.</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

Exploring the usability of biohydrogen and biodiesel in internal combustion engines with exhaust gas recirculation: RSM-ANN-Based prediction and optimization

  • 期刊论文

  • 发表日期：

    2025年10月9日

查看全文
  • Aqueel Ahmad,
  • Ashok Kumar Yadav,
  • Shifa Hasan

摘要

The primary objective of this study is to develop a hybrid modeling-optimization framework for improving the performance and emission characteristics of a dual-fuel diesel engine. The work focuses on the effect of engine operating parameters and exhaust gas recirculation (EGR) rates when using bio-hydrogen (HHO) and magnesium oxide (MgO) nanoparticle-enhanced aloe vera biodiesel/diesel blends. A Central Composite Design (CCD) was used to generate an L30 array, including four factors at five levels. Experiments were carried out using a fixed B20MgO90 (20% biodiesel, 80% diesel, And 90 ppm magnesium oxide) pilot fuel blend while varying engine load, compression ratio, HHO flow rate, and EGR rate. An ANN model was developed using the experimental data to predict key engine response parameters (BTE, BSFC, CO, HC, and NOx). The developed ANN model established high predictive accuracy, attaining an overall correlation coefficient (R) of 0.9963 and a mean squared error (MSE) of 0.0139. Multi-Output Response Surface Methodology was utilized for optimization, showing that An engine load of 77.26%, CR of 18:1, bio-hydrogen flow rate of 3.61 L/min, And An EGR rate of 10.42% are the optimal operating conditions. Under these conditions, the predicted optimal responses for BTE, BSFC, CO, HC, And NOx were found to be 34.07%, 0.4448 kg/kWh, 0.619% vol., 38.88 ppm, And 707.99 ppm, respectively. Experimental validation showed a maximum error of 6.61%, confirming the model’s reliability. This study shows that the combined ANN-RSM approach is an effective hybrid method for modeling, predicting, and optimizing the performance of dual-fuel engines.