A Comparative Study of Machine Learning Techniques in Prediction of Exhaust Emissions and Performance of a Diesel Engine Fuelled with Biodiesel Blends

Hung, Quang; Lo, Shih-Kuei; Chen, Jeng-Fung

doi:10.46488/nept.2021.v20i02.049

Cited by 4 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prediction performances (R 2 ) of the artificial neural network (ANN), XGBoost, and random forest (RF) models for specific fuel consumption (SFC) were 0.97, 0.9, and 0.96, respectively (Figure 4e). Regarding the error metrics, the root mean square error Do, et al [53] demonstrated that in predicting torque for B0 and B20 fuels, the artificial neural network (ANN) outperformed other algorithms. In a distinct study, Sanjeevannavar, et al [54] emphasized the efficacy of the XGBoost machine learning algorithm as a swift and cost-efficient method for predicting engine performance and emission characteristics.…”

Section: Model Performancesmentioning

confidence: 99%

Comparison of Engine Performance and Emission Values of Biodiesel Obtained from Waste Pumpkin Seeds with Machine Learning

Şahin,

Torun

2024

Agriculture

View full text Add to dashboard Cite

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.

show abstract

Section: Model Performancesmentioning

confidence: 99%

Comparison of Engine Performance and Emission Values of Biodiesel Obtained from Waste Pumpkin Seeds with Machine Learning

Şahin,

Torun

2024

Agriculture

View full text Add to dashboard Cite

show abstract

“…To meet the strict emission standards and attain cleaner creation of mingling fluidized bed units, it is essential to build a dynamic model of pollutants emission for creating an economical and environmentally friendly pollutant removal operation mode [42]. The main theme is to explore the fitness of several machine learning (ML) techniques including artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), general regression neural network (GRNN), radial basis function (RBFN), and support vector regression (SVR) for predicting performance and exhaust emissions of the diesel engine fueled with biodiesel blends [43]. The aim is to approximate diverse airfuel ratio motor shaft speed and fuel flow rates under the performance limits contingent on the indices of ignition efficiency and exhaust emission of the engine, a turboprop multilayer feed forward artificial neural network model [44].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Prediction and Optimization of Performance and Emissions Characteristics of IC Engine

Sanjeevannavar,

Banapurmath,

Kumar

et al. 2023

Sustainability

View full text Add to dashboard Cite

In this work, a study was conducted to investigate the effects of different biodiesel blends with hydrogen peroxide additive on the performance and emissions of an internal combustion engine under various operating parameters. A CI engine was operated with diesel, four dissimilar biodiesels, and H2O2 at various proportions. The biodiesel blends used were Jatropha (D60JB30A10, D60JB34A6, D60JB38A2, D60JB40), Honge (D60HB30A10, D60HB34A6, D60HB38A2, D60HB40), Simarouba (D60SB30A10, D60SB34A6, D60SB38A2, D60SB40), and Neem (D60NB30A10, D60NB34A6, D60NB38A2, D60NB40). The engine was tested at different injection operating pressures (200, 205, and 210 bar), a speed of 1500 rpm, and a CR of 17.5:1. From the experiments conducted, it was highlighted that, under specific conditions, i.e., with an injection pressure of 205 bar, 80% load, a compression ratio of 17.5, an injection timing set at 230 before top dead center, and an engine speed of 1500 rpm, the biodiesel blends D60JB30A10, D60HB30A10, D60SB30A10, and D60NB30A10 achieved the highest brake thermal efficiencies of 24%, 23.9675%, 23.935%, and 23.9025%, respectively. Notably, the blend D60JB30A10 stood out with the highest brake thermal efficiency of 24% among these tested blends. Similarly, when evaluating emissions under the same operational conditions, the D60JB30A10 blend exhibited the lowest emissions levels: CO (0.16% Vol), CO2 (7.8% Vol), HC (59 PPM), and Smoke (60 HSU), while NOx (720 PPM) emissions showed a relative increase with higher concentrations of the hydrogen-based additive. The D60HB30A10, D60SB30A10, and D60NB30A10 blends showed higher emissions in comparison. Additionally, the study suggests that machine learning techniques can be employed to predict engine performance and emission characteristics, thereby cutting down on time and costs associated with traditional engine trials. Specifically, machine learning methods, like XG Boost, random forest regressor, decision tree regressor, and linear regression, were utilized for prediction purposes. Among these techniques, the XG Boost model demonstrated highly accurate predictions, followed by the random forest regressor, decision tree regressor, and linear regression models. The accuracy of the predictions for XG Boost model was assessed through evaluation metrics such as R2-Score (0.999), Root Mean Squared Error (0.540), Mean Squared Error (0.248), and Mean Absolute Error (0.292), which allowed for a thorough analysis of the algorithm’s performance compared to actual values.

show abstract

Tiered prediction models for port vessel emissions inventories

Cammin

Voß

2022

Flex Serv Manuf J

View full text Add to dashboard Cite

Albeit its importance, a large number of port authorities do not provide continuous or publicly available air emissions inventories (EIs) and thereby obscure the emissions contribution of ports. This is caused by, e.g., the economic effort generated by obtaining data. Therefore, the performance of abatement measures is not monitored and projected, which is specifically disadvantageous concerning top contributors such as container ships. To mitigate this issue, in this paper we propose port vessel EI prediction models by exploring the combination of different machine-learning algorithms, data from the one-off application of an activity-based bottom-up methodology and vessel-characteristics data. The results for this specific case show that prediction models enable acceptable trade-offs between the prediction performance and data requirements, promoting the creation of EIs.

show abstract

A Comparative Study of Machine Learning Techniques in Prediction of Exhaust Emissions and Performance of a Diesel Engine Fuelled with Biodiesel Blends

Cited by 4 publications

References 0 publications

Comparison of Engine Performance and Emission Values of Biodiesel Obtained from Waste Pumpkin Seeds with Machine Learning

Comparison of Engine Performance and Emission Values of Biodiesel Obtained from Waste Pumpkin Seeds with Machine Learning

Machine Learning Prediction and Optimization of Performance and Emissions Characteristics of IC Engine

Tiered prediction models for port vessel emissions inventories

Contact Info

Product

Resources

About