Machine Learning Approach to Predict the Performability and Emissions of Diesel Engine Fueled with Doped Biodiesel Blend

Year : 2025 | Volume : 03 | Issue : 01 | Page : 1 12
    By

    Kiran Dinkar Chaudhari,

  • Kailas Dhanraj Deore,

  • Kshamta Mathur,

  1. Student, Department of Data Science, Shri Vile Parle Kelavani Mandal’s Narsee Monjee Institute of Management Studies (SVKM’s NMIMS), Mukesh Patel School of Technology Management and Engineering, Mumbai, Maharashtra, India
  2. Student, Department of Data Science, Shri Vile Parle Kelavani Mandal’s Narsee Monjee Institute of Management Studies (SVKM’s NMIMS), Mukesh Patel School of Technology Management and Engineering, Mumbai, Maharashtra, India
  3. Assistant Professor, Department of Data Science, Shri Vile Parle Kelavani Mandal’s Narsee Monjee Institute of Management Studies (SVKM’s NMIMS), Mukesh Patel School of Technology Management and Engineering, Mumbai, Maharashtra, India

Abstract

Enhancing the performability and emission characteristics of diesel engines has been a difficult task in light of growing concerns about global warming and other negative effects, as diesel accounts for 70% of global energy demand. In this study, engine performance and exhaust emissions for various fuel blends were thoroughly evaluated using machine learning techniques to predict engine emission and performance behavior. We focused on biodiesel blend and nanoparticle additive concentration to gain valuable insights into optimizing engine performance and emissions for alternative fuel blends, advancing knowledge in this field. Four machine learning algorithms—decision tree, random forest, linear regression, and XGBoost—were employed to predict engine performance (brake-specific fuel consumption (BSFC), brake thermal efficiency (BTE), exhaust gas temperature (EGT)) and emission parameters (CO, CO2, HC, NOx, smoke) using data from experiments with various biodiesel blends (B10, B20, B30) derived from waste cooking oil and diesel, incorporating different calcium oxide nanoparticle concentrations. The models were trained and tested using a 70/30 split of a dataset comprising engine load, additive concentration, and biodiesel blend ratio as input variables. Model performance was evaluated using R², mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). With regression coefficient (R2), MSE, MAE, MAPE, and RMSE values of 0.845, 255.7, 5.66, 0.1645, and 7.49 percent, respectively, in overall prediction, the XGBoost model performed better in engine performance prediction. This study demonstrates the effectiveness of XGBoost in optimizing biodiesel blends and nanoparticle additives for enhanced engine performance and reduced emissions, offering a more efficient alternative to traditional experimental methods. Future research could explore more advanced machine learning techniques and validate the model with a larger dataset.

Keywords: Biodiesel, emission, engine performance, machine learning, nanoparticles

[This article belongs to International Journal of Mechanical Dynamics and Systems Analysis ]

How to cite this article:
Kiran Dinkar Chaudhari, Kailas Dhanraj Deore, Kshamta Mathur. Machine Learning Approach to Predict the Performability and Emissions of Diesel Engine Fueled with Doped Biodiesel Blend. International Journal of Mechanical Dynamics and Systems Analysis. 2025; 03(01):1-12.
How to cite this URL:
Kiran Dinkar Chaudhari, Kailas Dhanraj Deore, Kshamta Mathur. Machine Learning Approach to Predict the Performability and Emissions of Diesel Engine Fueled with Doped Biodiesel Blend. International Journal of Mechanical Dynamics and Systems Analysis. 2025; 03(01):1-12. Available from: https://journals.stmjournals.com/ijmdsa/article=2025/view=216730


References

  1. Aydın M, Uslu S, Bahattin Çelik MB. Performance and emission prediction of a compression ignition engine fueled with biodiesel-diesel blends: A combined application of ANN and RSM based optimization. Fuel. 2020;269:117472. doi:10.1016/j.fuel.2020.117472.
  2. Ağbulut Ü, Gürel AE, Sarıdemir S. Experimental investigation and prediction of performance and emission responses of a CI engine fuelled with different metal-oxide based nanoparticles–diesel blends using different machine learning algorithms. Energy. 2021;215:119076. doi:10.1016/j.
    2020.119076.
  3. Uslu S, Celik MB. Combustion and emission characteristics of isoamyl alcohol-gasoline blends in spark ignition engine. Fuel. 2020;262:116496. doi:10.1016/j.fuel.2019.116496.
  4. Salvi BL, Subramanian KA, Panwar NL. Alternative fuels for transportation vehicles: A technical review. Renew Sustain Energy Rev. 2013;25:404–19. doi:10.1016/j.rser.2013.04.017.
  5. Karikalan L, Jacob S, Baskar S, Venugopal S. Analyzing the influence of varied fuel injection pressure on diesel engine fueled with Karanja biodiesel. Mater Today Proc. 2020;21:291–4. doi:10.1016/j.matpr.2019.05.439.
  6. Simsek S. Effects of biodiesel obtained from Canola, safflower oils and waste oils on the engine performance and exhaust emissions. Fuel. 2020;265:117026. doi:10.1016/j.fuel.2020.117026.
  7. Elkelawy M, Alm-Eldin Bastawissi H, Esmaeil KK, Radwan AM, Panchal H, Sadasivuni KK, et al. Experimental studies on the biodiesel production parameters optimization of sunflower and soybean oil mixture and DI engine combustion, performance, and emission analysis fueled with diesel/biodiesel blends. Fuel. 2019;255:115791. doi:10.1016/j.fuel.2019.115791.
  8. Gozmen Şanli B, Uludamar E, Özcanli M. Evaluation of energetic-exergetic and sustainability parameters of biodiesel fuels produced from palm oil and opium poppy oil as alternative fuels in diesel engines. Fuel. 2019;258:116116. doi:10.1016/j.fuel.2019.116116.
  9. Holechek JL, Geli HME, Sawalhah MN, Valdez R. A global assessment: Can renewable energy replace fossil fuels by 2050? Sustainability. 2022;14:4792. doi:10.3390/su14084792.
  10. Hoang AT, Nižetić S, Olcer AI, Ong HC, Chen WH, Chong CT, et al. Impacts of COVID-19 pandemic on the global energy system and the shift progress to renewable energy: Opportunities, challenges, and policy implications. Energy Policy. 2021;154:112322. doi:10.1016/j.enpol.2021.
    PMID: 34566236.
  11. Ahmad S, Jafry AT, Haq M, Abbas N, Ajab H, Hussain A, et al. Performance and emission characteristics of second-generation biodiesel with oxygenated additives. Energies. 2023;16. doi:10.3390/en16135153.
  12. Ağbulut Ü, Karagöz M, Sarıdemir S, Öztürk A. Impact of various metal-oxide based nanoparticles and biodiesel blends on the combustion, performance, emission, vibration and noise characteristics of a CI engine. Fuel. 2020;270:117521. doi:10.1016/j.fuel.2020.117521.
  13. Altammar KA. A review on nanoparticles: Characteristics, synthesis, applications, and challenges. Front Microbiol. 2023;14:1155622. doi:10.3389/fmicb.2023.1155622. PMID: 37180257.
  14. Abdallah AM, Abdel-Rahman AA, Elwardany AE. Analysis of the impact of different nanoparticle metal oxides as fuel additives in compression ignition engine performance. Energy Rep. 2020;6:99–105. doi:10.1016/j.egyr.2020.12.016.
  15. Montgomery DC. Design and Analysis of Experiments. New York: John Wiley & Sons; 2017.
  16. Pattnaik P, Sharma A, Choudhary M, Singh V, Agarwal P, Kukshal V. Role of machine learning in the field of fiber reinforced polymer composites: A preliminary discussion. Mater Today Proc. 2021;44:4703–8. doi:10.1016/j.matpr.2020.11.026.
  17. El-Seesy AI, Waly MS, He Z, El-Batsh HM, Nasser A, El-Zoheiry RM. Influence of quaternary combinations of biodiesel/methanol/n-octanol/diethyl ether from waste cooking oil on combustion, emission, and stability aspects of a diesel engine. Energy Convers Manag. 2021;240:114268. doi:10.1016/j.enconman.2021.114268.
  18. Roy S, Banerjee R, Bose PK. Performance and exhaust emissions prediction of a CRDI assisted single cylinder diesel engine coupled with EGR using artificial neural network. Appl Energy. 2014;119:330–40. doi:10.1016/j.apenergy.2014.01.044.
  19. Yıldırım S, Tosun E, Çalık A, Uluocak İ, Avşar E. Artificial intelligence techniques for the vibration, noise, and emission characteristics of a hydrogen-enriched diesel engine. Energy Sources Part A. 2019;41:2194–206. doi:10.1080/15567036.2018.1550540.
  20. Namar MM, Jahanian O, Koten H. The start of combustion prediction for methane-fueled HCCI engines: Traditional vs. machine learning methods. Math Probl Eng. 2022;2022:1–11. doi:10.1155/2022/4589160.
  21. Dhahad HA, Hasan AM, Chaichan MT, Kazem HA. Prognostic of diesel engine emissions and performance based on an intelligent technique for nanoparticle additives. Energy. 2022;238:121855. doi:10.1016/j.energy.2021.121855.
  22. Wang H, Zhao W. ARIMA model estimated by particle swarm optimization algorithm for consumer price index forecasting. In: Deng H, Wang L, Wang FL, Lei J, editors. Artif Intell Comput Intell. Berlin: Springer; 2009. p. 48–58. doi:10.1007/978-3-642-05253-8_6.
  23. Agrawal T, Gautam R, Agrawal S, Singh V, Kumar M, Kumar S. Optimization of engine performance parameters and exhaust emissions in compression ignition engine fueled with biodiesel-alcohol blends using Taguchi method, multiple regression and artificial neural network. Sustain Futures. 2020;2:100039. doi:10.1016/j.sftr.2020.100039.
  24. Zivkovic M, Jovanovic L, Ivanovic M, Bacanin N, Strumberger I, Joseph PM. XGBoost hyperparameters tuning by fitness-dependent optimizer for network intrusion detection. In: Sharma H, Shrivastava V, Kumari Bharti K, Wang L, editors. Communication and Intelligent Systems. Singapore: Springer; 2022. (Lecture Notes in Networks and Systems; vol. 461). doi:10.1007/978-981-19-2130-8_74.
Regular Issue Subscription Original Research
Volume 03
Issue 01
Received 20/05/2025
Accepted 07/06/2025
Published 17/06/2025
Publication Time 28 Days
129

Login


My IP

PlumX Metrics