Waste to energy: Mitigation of engine performance penalties through nano-agents and oxy-hydrogen gas enrichment, and prediction of engine behaviours with metaheuristic algorithms coupled with ANN
International Journal of Hydrogen Energy, cilt.277, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 277
- Basım Tarihi: 2026
- Doi Numarası: 10.1016/j.ijhydene.2026.157589
- Dergi Adı: International Journal of Hydrogen Energy
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Artic & Antarctic Regions, Chemical Abstracts Core, Chimica, Compendex, Environment Index, INSPEC, Academic Search Ultimate (EBSCO), Engineering Source (EBSCO)
- Anahtar Kelimeler: Engine behaviours, Metaheuristic-driven artificial neural networks, Nanofuels, Oxy-hydrogen gas, Waste tire pyrolysis oil
- İstanbul Ticaret Üniversitesi Adresli: Evet
Özet
After waste tires were transformed into pyrolysis oil, 20% of oil was blended with diesel-fuel (T20). Then CNT- and Al2O3-nanoparticles were added to T20 at 50 and 100 ppm, and Oxyhydrogen (HHO) was supplied at 0.5 L/min. The incorporation of HHO into nanoparticle-enhanced T20 blends reduced CO concentrations. Thermal efficiency increased by 14.10% and 22.54% for T20A50 + HHO and T20C100 + HHO, respectively, relative to T20. NOx emissions decreased by 25% and 31%, respectively, relative to T20. CO reductions for T20A100 + HHO and T20C100 + HHO were 16.24% and 22.59%. Smoke decreased by 29.1% and 34.63% for T20A100 + HHO and T20C100 + HHO, respectively, but HC decreased by 30% and 36% compared with T20. Artificial Neural Networks (ANNs) are integrated with Starfish Optimization Algorithm (SFOA), Arctic Puffin Optimization (APO), and Spider Wasp Optimizer (SWO). MAPE ≤ 10% and R2 between 0.9126 and 0.9980 were attained using SFOA-ANN, APO-ANN, and SWO-ANN. In conclusion, the use of HHO and nanoparticles improved engine performance and decreased emissions.