In this study, machine learning techniques, namely artificial neural network (ANN), support vector machine (SVM), and extreme gradient boosting (XGBoost), were used to comprehensively evaluate engine performance and exhaust emissions for different fuel blends. To obtain valuable insights on optimizing engine performance and emissions for alternative fuel blends and thus contribute to the advancement of knowledge in this field, we focused on iso-pentanol ratios while maintaining the biodiesel ratios constant. The maximum brake thermal efficiency (BTE) values for the diesel (30.13 %), D₈₅B₁₀P₅ (29.92 %), D₈₀B₁₀P₁₀ (29.89 %), and D₇₀B₁₀P₂₀ (29.79 %) blends were achieved at 1600 rpm. At 1600 rpm, the brake-specific fuel consumption (BSFC) values for the diesel, D8₅B₁₀P₅, D₈₀B₁₀P₁₀, and D₇₀B₁₀P₂₀ blends were 189.93, 200.93, 202.93, and 203.95 g kWh⁻¹, respectively. In engine performance prediction, the ANN model exhibited superior performance, yielding regression coefficient (R²), root mean square error, and mean absolute error values of 0.984, 0.411 %, and 0.112 %, respectively, in BTE prediction, and 0.958 %, 6.9 %, and 2.95 %, respectively, in BSFC prediction. In exhaust gas temperature prediction, the SVM model exhibited the best performance, yielding an R² value of 0.981. Although all models successfully predicted NOx emissions, the ANN model exhibited the best performance, achieving an R² value of 0.959. In CO₂ and hydrocarbon estimation, the XGBoost model exhibited the best performance, yielding R² values of 0.956 and 0.973, respectively. Therefore, the ANN model can be used to accurately predict engine performance, and the XGBoost model can be used to accurately predict emission parameters.

This study was primarily conducted to investigate the potential use of pumpkin seed oil in biodiesel production. Initially, the fatty acid composition of oils extracted from discarded pumpkin seeds was determined. Then, biodiesel produced from discarded pumpkin seed oil was tested in an engine test setup. The performance and emission values of a four-cylinder diesel engine fueled with diesel (D100), biodiesel (PB100), and blended fuels (PB2D98, PB5D95, and PB20D80) were determined. Furthermore, three distinctive machine learning algorithms (artificial neural networks, XGBoost, and random forest) were employed to model engine performance and emission parameters. Models were generated based on the data from the PB100, PB2D98, and PB5D95 fuels, and model performance was assessed through the R², RMSE, and MAPE metrics. The highest torque value (333.15 Nm) was obtained from 1200 rpm of D100 fuel. PB2D98 (2% biodiesel–98% diesel) had the lowest specific fuel consumption (194.33 g HPh⁻¹) at 1600 rpm. The highest BTE (break thermal efficiency) value (30.92%) was obtained from diesel fuel at 1400 rpm. Regarding the blended fuels, PB2D98 exhibited the most fuel-efficient performance. Overall, in terms of engine performance and emission values, PB2M98 showed the closest results to diesel fuel. A comparison of machine learning algorithms revealed that artificial neural networks (ANNs) generally performed the best. However, the XGBoost algorithm proved to be more successful than other algorithms at predicting the performance and emissions of PB20D80 fuel. The present findings demonstrated that the XGBoost algorithm could be a more reliable option for predicting engine performance and emissions, especially for data-deficient fuels such as PB20D80.

In this study, linseed oil was obtained with the aid of screw presses and linseed oil biodiesel (B100) (linseed oil methyl ester) production was performed by transesterification method. Linseed biodiesel was blended with regular diesel fuel at different ratios as B2 (98% diesel + 2% biodiesel), B5 (95% diesel + 5% biodiesel), B20 (80% diesel + 20% biodiesel), B50 (50% diesel + 50% biodiesel). Fuel properties tests were performed on all fuels. Results revealed that engine performance values of linseed biodiesel and fuel blends were similar with the standard diesel fuel. With regard to maximum torque, while the highest value was obtained as about 59.6 Nm at 1000 rpm with diesel fuel, the value was observed as about 53.8 Nm at 1200 1/min with B100 fuels. The highest maximum power output was recorded as approximately 10.96 kW at 2100 rpm with diesel fuel and as approximately 10.23 kW at 2000 rpm with B100 fuels. With regard to minimum specific fuel consumption, while the lowest value was measured as about 231.36 g/kWh at 1000 rpm with diesel fuel, the value was measured as about 296.73 g/kWh at 1200 rpm with B100 fuels. Exhaust emissions are generally improved by the addition of linseed biodiesel to diesel fuel.

Usage of biodiesel produced with conventional transesterification methods decreases the conversion of biodiesel from vegetable oil. Microwave-assisted production enables higher reaction efficiency, providing better conversion of vegetable oils. It also causes to obtain poorer characteristics of biodiesel, such as higher viscosity and density. It was aimed to improving the properties of biodiesel with microwave-assisted production and mixing it with nanoparticles to investigate the performance, combustion and emission characteristics. The influences of nanoparticle addition (carbon quantum dot) on engine performance, combustion and emissions have been analyzed in a direct injection CI engine. A single cylinder water cooled CI engine was used in the experiments. Experiments were performed at 4.12, 9.61, 15.10, 20.60 Nm and 2200 rpm. Canola biodiesel was obtained via the microwave-assisted transesterification method and mixed with diesel at the ratio of 20% (B20). 50, 100 and 150 ppm nanoparticle were added to the obtained B20 and tested in a CI engine. Specific Fuel Consumption (SFC) raised by 2.03%, 4.83%, 4.40% and 1.69% with B20, B20CQD 50 ppm, B20CQD 100 ppm and B20CQD 150 ppm respectively compared that diesel at 15.10 Nm. Remarkable reduction was found on CO, HC with B20CQD 50 ppm, B20CQD 100 ppm and B20CQD 150 ppm according to B20. In addition, an impressive reduction was realized on soot emissions with the usage of nanoprticle addition. But, NO_x increased using fuel blends. As a result, the usage of quantum dot nanoparticle improved the poor properties of canola oil biodiesel and test fuels were used easily without modification in a diesel engine.

Enerji ihtiyacının maliyetini minimum indirmek tarımsal işletmelerin kar payının arttırmasına katkı sağlayacaktır. Çiftliklerimiz enerji tüketimi fazla olan tarımsal üretim işlemlerini yerine getirebilmek için yenilenebilir enerji kaynakları olan biyoyakıt, güneş ve rüzgar enerjisinden yararlanmaktadır. Tarımsal üretimde özellikle de hayvan yetiştiriciliğinde daha kaliteli ve yüksek verime ulaşabilmek makineleşme ile orantılıdır. Makineleşmeye bağlı olarak enerji tüketimi de artış göstermektedir. Günümüzde enerji maliyetinin yükselmesi, çiftçilerimizin gelirlerinin önemli bir bölümünü elektrik faturalarına ayırmasına sebep olmaktadır. Bu çalışmada, artan bu elektrik ihtiyacımızı karşılamak için Konya’da, bir hayvan çiftliğinde güneş enerjisinin uygulanabilirliği ve işletmeye ekonomik getirisinin hesaplanması amaçlanmıştır. İşletmenin çatısına kurulan güneş enerji sisteminin üretileceği elektrik hesaplamaları iki farklı yönteme göre yapılmıştır. Güneş panellerinden anlık ölçümler ve aylık güneşlenme süreleri dikkate alınarak yapılan hesaplama ile photovoltaic geographical information system hesaplamaları karşılaştırılmıştır. Yöntemler arasında %3,7’lik bir fark bulunmuştur. İşletmenin çatısına kurulan güneş enerji sisteminin toplam maliyet 1.884.600 TL hesaplanmıştır. İşletmenin aylık elektriksel yükü 35.746 kWh olarak belirlenmiştir. İşletmenin aylık ortalama olarak elektrik tüketimi 27.881 TL, yıllık ise 334.582 TL hesaplanmıştır. Güneş enerji sisteminin aylık elektrik üretim miktarı 21.280 TL, yıllık ise 255.368 TL’dir. Sistemin kendini amorti etme süresi yaklaşık 7,2 yıl hesaplanmıştır. Güneş enerji sisteminin yaklaşık 25 yıl ömrü olduğunu hesaba katarsak geriye kalan 17,8 yıl sonunda işletmenin maliyetlerinde yaklaşık olarak 4,5 milyon TL azalmanın olacağı tahmin edilmektedir. Ayrıca işletmenin güneş enerji sistemi ile temiz enerji üretimi sayesinde, yıllık elektrik tüketim değerine eşdeğer 670.340 kg CO2 salınımı engellenmiş olacaktır. Bu işletme için güneş enerji sisteminin ekonomik bir yatırım olmasının yanı sıra elektrik üretimi bakımından CO2 salınımına sebep olmaması büyük bir avantajdır.