Biodiesel has evolved as a sustainable alternative to fossil diesel because it is renewable and yields lower exhaust emissions. The composition and properties of biodiesel vary significantly depending on the feedstock. Consequently, the engine’s behavioral response to biodiesel is closely linked to the specific feedstock source. The complex interdependence between biodiesel feedstock and engine characteristics demands careful selection of suitable feedstock to achieve better engine performance and lower exhaust emissions. The novelty of the current investigation lies in addressing this challenge by selecting optimal feedstocks using a machine-learning framework to produce biodiesel fuel with improved engine characteristics. The proposed framework involves predictive analysis, in which models to estimate engine characteristics are developed using engine load and biodiesel composition as inputs. The engine characteristics of interest include brake-specific fuel consumption (BSFC), oxides of nitrogen (NOx), unburned hydrocarbons (HC), and carbon monoxide (CO) emissions. The predictive analysis confirms the applicability of artificial neural network (ANN) regression, Gaussian process regression (GPR), support vector machine regression (SVM), and random forest (RF) for building reliable models to estimate engine characteristics, with errors under 5%. Biodiesel has limited applications due to higher BSFC and NOx emissions than diesel; hence, the optimization target simultaneously minimizes BSFC and HC, CO, and NOx emissions. The optimized biodiesel markedly improves fuel economy, with BSFC 26% higher than diesel, while coconut biodiesel exhibits a 41% higher BSFC. NOx levels from mustard biodiesel are 97% higher than diesel, while the proposed biodiesel yields only a 35% increase in NOx. A blend of olive, coconut, and canola oils in volume proportions of 85%, 10%, and 5% (±1%) yields a biodiesel nearly identical to the proposed composition. Thus, an optimal feedstock for producing biodiesel with minimal BSFC and NOx emission penalty was determined using the machine-learning approach employed in this study.
ShirizadehBAilleretACartryC, et al. Climate neutrality in European heavy-duty road transport: how to decarbonise trucks and buses in less than 30 years?Energy Convers Manag2024; 309: 118438. https://doi.org/10.1016/j.enconman.2024.118438
2.
CalamASolmazHYılmazE, et al. Investigation of effect of compression ratio on combustion and exhaust emissions in A HCCI engine. Energy2019; 168: 1208–1216. https://doi.org/10.1016/j.energy.2018.12.023
3.
SoudagarMEMShelareSMarghadeD, et al. Optimizing IC engine efficiency: a comprehensive review on biodiesel, nanofluid, and the role of artificial intelligence and machine learning. Energy Convers Manag2024; 307: 118337. https://doi.org/10.1016/j.enconman.2024.118337
4.
KaramiRRasulMGKhanMMK, et al. Experimental and computational analysis of combustion characteristics of a diesel engine fueled with diesel-tomato seed oil biodiesel blends. Fuel2021; 285: 119243. https://doi.org/10.1016/j.fuel.2020.119243
5.
JungSShettiNPReddyKR, et al. Synthesis of different biofuels from livestock waste materials and their potential as sustainable feedstocks – a review. Energy Convers Manag2021; 236: 114038. https://doi.org/10.1016/j.enconman.2021.114038
6.
PereiraFMVelásquezJARiechiJL, et al. Impact of pure biodiesel fuel on the service life of engine-lubricant: a case study. Fuel2020; 261: 116418. https://doi.org/10.1016/j.fuel.2019.116418
7.
Govt. of India Ministry of Petroleum and Natural Gas. National policy on biofuels 2018. Gaz India, 2018, pp.1–23.
8.
FarobieOHartulistiyosoE. Palm oil biodiesel as a renewable energy resource in Indonesia: current status and challenges. Bioenerg Res2022; 15: 93–111. https://doi.org/10.1007/s12155-021-10344-7
9.
SantosBSCaparedaSC. A comparative study on the engine performance and exhaust emissions of biodiesel from various vegetable oils and animal fat. J Sustain Bioenergy Syst2015; 05: 89–103. https://doi.org/10.4236/jsbs.2015.53009
HoangAT. Prediction of the density and viscosity of biodiesel and the influence of biodiesel properties on a diesel engine fuel supply system. J Mar Eng Technol2021; 20: 299–311. https://doi.org/10.1080/20464177.2018.1532734
WuFWangJChenW, et al. A study on emission performance of a diesel engine fueled with five typical methyl ester biodiesels. Atmos Environ2009; 43: 1481–1485. https://doi.org/10.1016/j.atmosenv.2008.12.007
14.
RajakUVermaTN. Effect of emission from ethylic biodiesel of edible and non-edible vegetable oil, animal fats, waste oil and alcohol in CI engine. Energy Convers Manag2018; 166: 704–718. https://doi.org/10.1016/j.enconman.2018.04.070
15.
KhalifeETabatabaeiMDemirbasA, et al. Impacts of additives on performance and emission characteristics of diesel engines during steady state operation. Prog Energy Combust Sci2017; 59: 32–78. https://doi.org/10.1016/j.pecs.2016.10.001
16.
Hosseinzadeh-BandbafhaHTabatabaeiMAghbashloM, et al. A comprehensive review on the environmental impacts of diesel/biodiesel additives. Energy Convers Manag2018; 174: 579–614. https://doi.org/10.1016/j.enconman.2018.08.050
17.
SharmaASahooPKTripathiRK, et al. Artificial neural network-based prediction of performance and emission characteristics of CI engine using polanga as a biodiesel. Int J Ambient Energy2016; 37: 559–570. https://doi.org/10.1080/01430750.2015.1023466
18.
BhaskarGargADiwanPSaxenaM. Artificial Neural Networks for internal combustion engine performance and emission analysis. Int J Comput Appl2014; 87: 23–27. https://doi.org/10.5120/15212-3705
19.
SilitongaASMasjukiHHOngHC, et al. Engine performance, emission and combustion in common rail turbocharged diesel engine from Jatropha Curcas using artificial neural network. SAE Technical Paper2015.
20.
Shivakumar Srinivasa PaiPShrinivasa RaoBR. Artificial neural network based prediction of performance and emission characteristics of a variable compression ratio CI engine using WCO as a biodiesel at different injection timings. Appl Energy2011; 88: 2344–2354. https://doi.org/10.1016/j.apenergy.2010.12.030
21.
MenonPRKrishnasamyA. A composition-based model to predict and optimize biodiesel-fuelled engine characteristics using artificial neural networks and genetic algorithms. Energy Fuels2018; 32: 11607–11618. https://doi.org/10.1021/acs.energyfuels.8b02846
22.
HoangATChenW-HParamasivamP, et al. Comprehensive investigation on performance and emission of dual-fuel diesel engine fuelled with biodiesel and hydrogen using D-optimal design and desirability-based multi-attribute optimization. Int J Hydrogen Energy2025; 146: 150005. https://doi.org/10.1016/j.ijhydene.2025.06.195
23.
HoangATNižetićSOngHC, et al. A review on application of artificial neural network (ANN) for performance and emission characteristics of diesel engine fueled with biodiesel-based fuels. Sustain Energy Technol Assess2021; 47: 101416. https://doi.org/10.1016/j.seta.2021.101416
SakthivelG. Prediction of CI engine performance, emission and combustion characteristics using fish oil as a biodiesel at different injection timing using fuzzy logic. Fuel2016; 183: 214–229. https://doi.org/10.1016/j.fuel.2016.06.063
26.
CanakciMOzsezenANArcakliogluE, et al. Prediction of performance and exhaust emissions of a diesel engine fueled with biodiesel produced from waste frying palm oil. Expert Syst Appl2009; 36: 9268–9280. https://doi.org/10.1016/j.eswa.2008.12.005
27.
BukkarapuKRKrishnasamyA. Fourier Transform infrared spectroscopy models to predict cetane number of different biodiesels and their blends. 2020. https://doi.org/10.4271/2020-01-0617
28.
SinghAKPundirBPSinghA. Fuel system for dual-fuel operation of an automotive diesel. In: IV international symposium on alcohol fuels technology, Sao Paulo, Brazil, 5 October 1980, pp. 507–511.
29.
GiwaSOTaziwaRTSharifpurM. Dependence of composition-based approaches on hybrid biodiesel fuel properties prediction using artificial neural network and random tree algorithms. Renew Energy2023; 218: 119324. https://doi.org/10.1016/j.renene.2023.119324
30.
SultanaNHossainSMZAbusaadM, et al. Prediction of biodiesel production from microalgal oil using Bayesian optimization algorithm-based machine learning approaches. Fuel2022; 309: 122184. https://doi.org/10.1016/j.fuel.2021.122184
31.
GharehghaniAAbbasiHRAlizadehP. Application of machine learning tools for constrained multi-objective optimization of an HCCI engine. Energy2021; 233: 121106. https://doi.org/10.1016/j.energy.2021.121106
32.
WangH-PChuX-LChenP, et al. Moving window correlation coefficient differences partial least squares (MWCC-DPLS) quantitative calibration method based on spectral differences between calibration samples: application to the fast determination of gasoline octane number with near-infrared spectroscopy. Fuel Process Technol2023; 240: 107583. https://doi.org/10.1016/j.fuproc.2022.107583
33.
BukkarapuKRKrishnasamyA. Support vector regression approach to optimize the biodiesel composition for improved engine performance and lower exhaust emissions. Fuel2023; 348: 128604. https://doi.org/10.1016/j.fuel.2023.128604
34.
BatoolSNaberJDShahbakhtiM. Machine learning approaches for identification of heat release shapes in a low temperature combustion engine for control applications. Control Eng Pract2024; 144: 105838. https://doi.org/10.1016/j.conengprac.2023.105838
35.
BukkarapuKRKrishnasamyA. Investigations on the applicability of machine learning algorithms to optimize biodiesel composition for improved engine fuel properties. Int J Engine Res2024; 25: 1299–1314. https://doi.org/10.1177/14680874241227540
36.
WangBAlruyemiI. Comprehensive modeling in predicting biodiesel density using Gaussian process regression approach. Biomed Res Int2021; 2021(1): 13. https://doi.org/10.1155/2021/6069010
37.
PustokhinaISerajAHafsanH, et al. Developing a robust model based on the Gaussian process regression approach to predict biodiesel properties. Int J Chem Eng2021; 2021: 1–12. https://doi.org/10.1155/2021/5650499
38.
HoangATMurugesanPPvE, et al. Strategic combination of waste plastic/tire pyrolysis oil with biodiesel for natural gas-enriched HCCI engine: Experimental analysis and machine learning model. Energy2023; 280: 128233. https://doi.org/10.1016/j.energy.2023.128233
39.
CunhaCLTorresARLunaAS. Multivariate regression models obtained from near-infrared spectroscopy data for prediction of the physical properties of biodiesel and its blends. Fuel2020; 261: 116344. https://doi.org/10.1016/j.fuel.2019.116344
40.
BukkarapuKRKrishnasamyA. Fourier-Transform-Infrared-Spectroscopy-based approach to predict engine fuel properties of biodiesel. Energy Fuels2021; 35: 7993–8005. https://doi.org/10.1021/acs.energyfuels.0c03927
41.
ChiesaMMaioliGColomboGI, et al. GARS: genetic algorithm for the identification of a robust subset of features in high-dimensional datasets. BMC Bioinformatics2020; 21: 54. https://doi.org/10.1186/s12859-020-3400-6
42.
MurataTIshibuchiH. MOGA: multi-objective genetic algorithms. In: Proceedings of 1995 IEEE international conference on evolutionary computation, Perth, Australia, 1995, pp.289–294.
