Cerium Oxide Blended Biodiesel: Machine Learning and Response Surface Methodology for Prediction of Responses

Abstract

Because of the rising demand for diesel, researchers are looking into finding a new alternative fuel. Biodiesel is an excellent alternative to neat diesel due to its renewable, biodegradable, and non-toxic nature. However, its response characteristics, such as brake thermal efficiency (BTE) and brake-specific fuel consumption (BSFC) should be predicted correctly. Thus, the present work includes the production of biodiesel from cottonseed oil with two-step transesterification and the investigation of response characteristics for a single-cylinder diesel engine fueled with Cerium oxide, i.e. nanoparticle additive (NA), which is blended cottonseed oil biodiesel. Compression ratio (CR) and NA levels have varied from 16 to 18 and 50 to 100 ppm, respectively. Input parameters, namely CR and NA levels are considered for the present investigation. The present study presents a novel method that uses deep learning-based surrogate modelling, a machine learning (ML) technique to forecast the responses. The optimum operating conditions are a CR of 18 and an NA level of 83.877 ppm. The study results demonstrate that the deep learning model provides a convincing substitute for classical regression models such as Random Forest, Decision Tree, Support Vector Machines, Gradient Boosting, and K-Nearest Neighbor Regressor. Further, multi-objective optimization of input parameters is performed using the desirability function approach. The optimized parameters were attained at a composite desirability of 0.847. Lastly, confirmation experiments are performed to validate the results of non-linear regression models and found satisfactory with an error percentage of less than five.

Keywords

• Cottonseed oil
• Nanoparticle additive
• Brake Thermal Efficiency
• Brake Specific Fuel Consumption
• Deep Learning
• Surrogate modelling

References

1. [1] Anggono W, Noor MM, Suprianto FD, Lesmana LA, Gotama GJ, Setiyawan A. Effect of Cerbera Manghas Biodiesel on Diesel Engine Performance. International Journal of Automotive and Mechanical Engineering. 2018 Oct 5;15(3):5667–82. https://doi.org/10.15282/ijame.15.3.2018.20.0435
2. [2] Can Ö, Öztürk E, Solmaz H, Aksoy F, Çinar C, Yücesu HS. Combined effects of soybean biodiesel fuel addition and EGR application on the combustion and exhaust emissions in a diesel engine. Appl Therm Eng. 2016 Feb;95:115–24. https://doi.org/10.1016/j.applthermaleng.2015.11.056
3. [3] Kaushik S, Sati V, Kanojia N, Mehra KS, Malkani H, Pant H, et al. Biodiesel a Substitution for Conventional Diesel Fuel: A Comprehensive Review. In Advances in Mechanical Engineering. Lecture Notes in Mechanical Engineering. Springer, Singapore, 2021. p. 113–22. https://doi.org/10.1007/978-981-16-0942-8_10
4. [4] Nayak SK, Pattanaik BP. Experimental Investigation on Performance and Emission Characteristics of a Diesel Engine Fuelled with Mahua Biodiesel Using Additive. Energy Procedia. 2014;54:569–79. https://doi.org/10.1016/j.egypro.2014.07.298
5. [5] Ramana P, RamanathReddy P, Balaram C, Sharath kumar A. Experimental Study on CI Engine Performance Using Bio Diesel Blends. International Research Journal of Engineering and Technology. 2015;2(2):1107–16.
6. [6] Doğan B, Özer S, Vural E, Haciyusufoğlu AF. Energy, exergy and sustainability analyses of nanoparticles added to fuels to reduce carbon footprint. Case Studies in Thermal Engineering. 2024 Apr; 56:104252. http://doi.org/10.1016/j.csite.2024.104252
7. [7] Arumugam S, Sriram G, Ellappan R. Bio-lubricant-biodiesel combination of rapeseed oil: An experimental investigation on engine oil tribology, performance, and emissions of variable compression engine. Energy. 2014 Aug;72:618–27. https://doi.org/10.1016/j.energy.2014.05.087
8. [8] Arul Mozhi Selvan V, Anand RB, Udayakumar M. Effect of Cerium Oxide Nanoparticles and Carbon Nanotubes as fuel-borne additives in Diesterol blends on the performance, combustion and emission characteristics of a variable compression ratio engine. Fuel. 2014 Aug;130:160–7. https://doi.org/10.1016/j.fuel.2014.04.034

9. [9] Bridjesh P, Prabhu Kishore N, Mallikarjuna M V., Alekhya N. Performance Analysis of Variable Compression Ratio Diesel Engine using Calophyllum inophyllum Biodiesel. Indian J Sci Technol. 2016 Sep 28;9(35). https://dx.doi.org/10.17485/ijst/2016/v9i35/95577
10. [10] Suresh M, Jawahar CP, Richard A. A review on biodiesel production, combustion, performance, and emission characteristics of non-edible oils in variable compression ratio diesel engine using biodiesel and its blends. Renewable and Sustainable Energy Reviews. 2018 Sep;92:38–49. https://doi.org/10.1016/j.rser.2018.04.048
11. [11] Murugapoopathi S, Vasudevan D. Energy and exergy analysis on variable compression ratio multi-fuel engine. J Therm Anal Calorim. 2019 Apr 3;136(1):255–66. https://doi.org/10.1007/s10973-018-7761-2
12. [12] Khatri D, Goyal R, Darad A, Jain A, Rawat S, Khan A, et al. Investigations for the optimal combination of zinc oxide nanoparticle-diesel fuel with optimal compression ratio for improving performance and reducing the emission features of variable compression ratio diesel engine. Clean Technol Environ Policy. 2019 Sep 14;21(7):1485–98. https://doi.org/10.1007/s10098-019-01719-8
13. [13] Hussain F, Soudagar MEM, Afzal A, Mujtaba MA, Fattah IMR, Naik B, et al. Enhancement in Combustion, Performance, and Emission Characteristics of a Diesel Engine Fueled with Ce-ZnO Nanoparticle Additive Added to Soybean Biodiesel Blends. Energies (Basel). 2020 Sep 3;13(17):4578. https://doi.org/10.3390/en13174578
14. [14] Subramani K, Karuppusamy M. Performance, combustion and emission characteristics of variable compression ratio engine using waste cooking oil biodiesel with added nanoparticles and diesel blends. Environmental Science and Pollution Research. 2021 Dec 24;28(45):63706–22. https://doi.org/10.1007/s11356-021-14768-8
15. [15] Rajak U, Panchal M, Veza I, Ağbulut Ü, Nath Verma T, Sarıdemir S, et al. Experimental investigation of performance, combustion and emission characteristics of a variable compression ratio engine using low-density plastic pyrolyzed oil and diesel fuel blends. Fuel. 2022 Jul;319:123720. https://doi.org/10.1016/j.fuel.2022.123720
16. [16] Hussain Vali R, Hoang AT, Marouf Wani M, Pali HS, Balasubramanian D, Arıcı M, et al. Optimization of variable compression ratio diesel engine fueled with Zinc oxide nanoparticles and biodiesel emulsion using response surface methodology. Fuel. 2022 Sep;323:124290. https://doi.org/10.1016/j.fuel.2022.124290
17. [17] Shelare SD, Belkhode PN, Nikam KC, Jathar LD, Shahapurkar K, Soudagar MEM, et al. Biofuels for a sustainable future: Examining the role of nano-additives, economics, policy, internet of things, artificial intelligence and machine learning technology in biodiesel production. Energy. 2023 Nov;282:128874. https://doi.org/10.1016/j.energy.2023.128874
18. [18] Aghbashlo M, Peng W, Tabatabaei M, Kalogirou SA, Soltanian S, Hosseinzadeh-Bandbafha H, et al. Machine learning technology in biodiesel research: A review. Prog Energy Combust Sci. 2021 Jul;85:100904. https://doi.org/10.1016/j.pecs.2021.100904
19. [19] Veza I, Afzal A, Mujtaba MA, Tuan Hoang A, Balasubramanian D, Sekar M, et al. Review of artificial neural networks for gasoline, diesel and homogeneous charge compression ignition engine. Alexandria Engineering Journal. 2022 Nov;61(11):8363–91. https://doi.org/10.1016/j.aej.2022.01.072
20. [20] Li J, Zhong W, Zhang J, Zhao Z, Hu J. The combustion and emission improvements for diesel–biodiesel hybrid engines based on response surface methodology. Front Energy Res. 2023 May 30;11. https://doi.org/10.3389/fenrg.2023.1201815
21. [21] Dharmalingam B, Annamalai S, Areeya S, Rattanaporn K, Katam K, Show PL, et al. Bayesian Regularization Neural Network-Based Machine Learning Approach on Optimization of CRDI-Split Injection with Waste Cooking Oil Biodiesel to Improve Diesel Engine Performance. Energies (Basel). 2023 Mar 17;16(6):2805. https://doi.org/10.3390/en16062805
22. [22] Elkelawy M, El Shenawy EA, Alm-Eldin Bastawissi H, Shams MM, Panchal H. A comprehensive review on the effects of diesel/biofuel blends with nanofluid additives on compression ignition engine by response surface methodology. Energy Conversion and Management: X. 2022 May;14:100177. https://doi.org/10.1016/j.ecmx.2021.100177
23. [23] Gupta KK, Kalita K, Ghadai RK, Ramachandran M, Gao XZ. Machine Learning-Based Predictive Modelling of Biodiesel Production—A Comparative Perspective. Energies (Basel). 2021 Feb 20;14(4):1122. https://doi.org/10.3390/en14041122
24. [24] M S, R S, S P. Cerium Zirconium blended biodiesel. Gedrag & Organisatie Review. 2020 Jun 21;33(02).
25. [25] Murugapoopathi S, Vasudevan D, Karthikeyan S. Prediction of performance and emission characteristics of biodiesel blends-Response surface methodology approach. In 2019. p. 020014. https://doi.org/10.1063/1.5127605
26. [26] Koçyiğit S, Özer S, Çelebi S, Demir U. Bio-based solutions for diesel engines: Investigating the effects of propolis additive and ethanol on performance and emissions. Thermal Science and Engineering Progress. 2024 Feb;48:102421. https://ui.adsabs.harvard.edu/link_gateway/2024TSEP...4802421K/doi:10.1016/j.tsep.2024.102421
27. [27] ÖZEL S, VURAL E, BİNİCİ M. Taguchi method for investigation of the effect of TBC coatings on NiCr bond-coated diesel engine on exhaust gas emissions. International Advanced Researches and Engineering Journal. 2020 Apr 15;4(1):14–20. https://doi.org/10.35860/iarej.686459
28. [28] Özel S, Vural E, Binici M. Optimization of the effect of thermal barrier coating (TBC) on diesel engine performance by Taguchi method. Fuel. 2020 Mar;263:116537. https://doi.org/10.1016/j.fuel.2019.116537
29. [29] Vural E, Özer S, Özel S, Binici M. Analyzing the effects of hexane and water blended diesel fuels on emissions and performance in a ceramic-coated diesel engine by Taguchi optimization method. Fuel. 2023 Jul;344:128105. https://doi.org/10.1016/j.fuel.2023.128105
30. [30] Pali HS, Kumar N. Combustion, performance and emissions of Shorea robusta methyl ester blends in a diesel engine. Biofuels. 2016 Sep 2;7(5):447–56. https://doi.org/10.1080/17597269.2016.1153363
31. [31] Syu JY, Chang YY, Tseng CH, Yan YL, Chang YM, Chen CC, et al. Effects of water-emulsified fuel on a diesel engine generator’s thermal efficiency and exhaust. J Air Waste Manage Assoc. 2014 Aug 3;64(8):970–8. https://doi.org/10.1080/10962247.2014.905508
32. [32] Elumalai PV, Nambiraj M, Parthasarathy M, Balasubramanian D, Hariharan V, Jayakar J. Experimental investigation to reduce environmental pollutants using biofuel nano-water emulsion in thermal barrier coated engine. Fuel. 2021 Feb;285:119200. https://doi.org/10.1016/j.fuel.2020.119200
33. [33] El-Seesy AI, Attia AMA, El-Batsh HM. The effect of Aluminum oxide nanoparticles addition with Jojoba methyl ester-diesel fuel blend on a diesel engine performance, combustion and emission characteristics. Fuel. 2018 Jul;224:147–66. https://doi.org/10.1016/j.fuel.2018.03.076
34. [34] Donahue J, Hendricks LA, Guadarrama S, Rohrbach M, Venugopalan S, Darrell T, et al. Long-term recurrent convolutional networks for visual recognition and description. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE; 2015. p. 2625–34. https://doi.org/10.1109/CVPR.2015.7298878
35. [35] Lai S, Xu L, Liu K, Zhao J. Recurrent Convolutional Neural Networks for Text Classification. Proceedings of the AAAI Conference on Artificial Intelligence. 2015 Feb 19;29(1). https://doi.org/10.1609/aaai.v29i1.9513
36. [36] Shin HC, Roth HR, Gao M, Lu L, Xu Z, Nogues I, et al. Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning. IEEE Trans Med Imaging. 2016 May;35(5):1285–98. https://doi.org/10.1109/TMI.2016.2528162
37. [37] Hanif AM, Beqiri S, Keane PA, Campbell JP. Applications of interpretability in deep learning models for ophthalmology. Curr Opin Ophthalmol. 2021 Sep;32(5):452–8. https://doi.org/10.1097/icu.0000000000000780