Impact of synthesized boron quantum dots on the performance and emission characteristics of a hydrogen-enriched CI engine: Hybrid metaheuristic-optimized ANN prediction
Energy, cilt.361, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 361
- Basım Tarihi: 2026
- Doi Numarası: 10.1016/j.energy.2026.141969
- Dergi Adı: Energy
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Applied Science & Technology Source, Compendex, Environment Index, Geobase, INSPEC, Public Affairs Index, Academic Search Ultimate (EBSCO), Engineering Source (EBSCO)
- Anahtar Kelimeler: Boron quantum dots (BQDs), Engine performance, Exhaust emissions, Hydrogen enrichment, Metaheuristic-driven ANNs
- İstanbul Ticaret Üniversitesi Adresli: Hayır
Özet
In this study, the combined effects of different amounts of synthesized boron quantum dots (BQDs) and hydrogen gas on a diesel-biodiesel binary fuel blend were discussed on a three-cylinder, water-cooled engine. The test engine was operated at a constant speed of 2000 rpm under variable engine loads (15, 30, 45, and 60 Nm). Incorporating sunflower biodiesel into diesel fuel at a 20% ratio (B20) resulted in a 5.12% increase in brake specific fuel consumption (BSFC) and a 0.89% decrease in brake thermal efficiency (BTE). However, the presence of hydrogen gas and BQDs in the combustion chamber created a synergistic influence. For test fuels containing 0.25 g and 0.50 g BQD+10 Lpm hydrogen, BSFC values recovered and decreased by 5.87% and 8.34%, while BTE improved by 6.94% and 9.81%, respectively. On the other hand, HC and NOx emissions, which increased with B20 fuel, significantly decreased with the presence of BQDs and hydrogen compared to B20 fuel. To predict engine performance and emission characteristics, hybrid metaheuristic-driven artificial neural network models (NOA-ANN, CCO-ANN, and dFDB-LSHADE-ANN) were developed. The forecasting performance of all models was categorized as “excellent” regarding rRMSE and showed “high prediction accuracy” in terms of MAPE. Notably, the dFDB-LSHADE-ANN outperformed the others, standing out as the most robust tool for predicting the performance and emission characteristics of the engine. In conclusion, the findings of this study suggest that quantum dots have significant potential as novel fuel additives for internal combustion engines, and the changes in engine characteristics caused by quantum dots can be predicted with high accuracy.