Machine learning optimisation of CI engine characteristics with WSA algorithm and prosopis juliflora biofuel
DOI:
https://doi.org/10.24425/ather.2025.156842Abstract
Machine learning, a division of artificial intelligence (AI), empowers systems to gain knowledge from information and refine their capabilities over time. It uses algorithms to identify patterns and make prophecies or decisions. Prosopis juliflora is becoming gradually notorious as an optimistic substitute in biofuel inquiry. The mixing of Prosopis juliflora with diesel for use in combustion engines has been the subject of growing study in recent years. However, limited research has explored the impact of Prosopis juliflora on the compression ignition (CI) engine exhaust employing data-driven optimisation highlighting the need for new inquiries to address this shortfall. We aim to explore the cutting-edge and proficient machine learning driven weighted superposition attraction algorithm to optimise the efficiency and exhaust of CI engines powered with Prosopis juliflora biodiesel – diesel blends. Regression modelling is employed to define the relationships between factors such as the blend percentage and brake mean effective pressure (bar), and responses like the brake thermal efficiency (%), brake specific fuel consumption (g/kWh), smoke opacity (%), NOx (g/kWh), CO (g/kWh), and HC (g/kWh). The datadriven weighted superposition attraction algorithm is subsequently employed to determine the best factor levels. Validation of the results demonstrates that the brake thermal efficiency is enhanced, while the other response variables are effectively reduced, showcasing the effectiveness of this methodology.References
[1] Stančin, H., Mikulčić, H., Wang, X., & Duić, N. (2020). A review on alternative fuels in future energy system. Renewable and Sustainable Energy Reviews, 128, 109927. doi:10.1016/j.rser.2020.109927
[2] Zhang, Z., Wang, S., Pan, M., Lv, J., Lu, K., Ye, Y., & Tan, D. (2024). Utilization of hydrogen-diesel blends for the improvements of a dual-fuel engine based on the improved Taguchi methodology. Energy, 292, 130474. doi:10.1016/j.energy.2024.130474
[3] Debella, H. A., Ancha, V. R., Atnaw, S. M., & Zeleke, D. S. (2024). Experimental study on performance and emissions from Prosopis juliflora biodiesel blends with diethyl ether additives. Energy Conversion and Management: X, 22, 100581. doi:10.1016/j.ecmx.2024.100581
[4] Jaiganesh, J., Prakash, R., & Krishnan, M. G. (2024). Exploring the synergistic potential of Prosopis juliflora and waste plastic oil biodiesel through investigation of performance, combustion, and emission in a CRDI engine: A shift towards sustainable fuel. Process Safety and Environmental Protection, 184, 720–735. doi:10.1016/j.psep.2024.02.036
[5] Kukana, R., & Jakhar, O. P. (2021). Synthesis of biodiesel from Prosopis juliflora and using MCDM analytical hierarchy process technique for evaluating with different biodiesel. Cogent Engineering, 8(1). doi:10.1080/23311916.2021.1957291
[6] Sasikumar, R., Sankaranarayanan, G., & Karthikeyan, R. (2022). Investigation characteristics of Prosopis juliflora biodiesel blended with diesel fuel in a DI diesel engine. Australian Journal of Mechanical Engineering, 20(3), 692–697. doi:10.1080/14484846.2020.1740021
[7] Kumar, S., Ningegowda, B. A., & Raju, V. D. (2022). The combined influence of injection pressure and exhaust gas recirculation on the characteristics of the diesel engine fuelled with Juliflora Biodiesel. International Journal of Ambient Energy, 43(1), 7952–7961. doi:10.1080/01430750.2022.2075929
[8] Selvan, P. T., & Goteti, G. S. (2020). Experimental analysis of VCR engine operated with Prosopis juliflora biodiesel blends. International Journal of Renewable Energy Research, 10(2). doi:10.20508/ijrer.v10i2.10776.g7965
[9] Abbas, A. M., Alomran, M. M., Alharbi, N. K., & Novak, S. J. (2023). Suppression of Seedling Survival and Recruitment of the Invasive Tree Prosopis juliflora in Saudi Arabia through Its Own Leaf Litter: Greenhouse and Field Assessments. Plants, 12(4). doi:10.3390/plants12040959
[10] Vinodraj, S., Arularasan, R., Karthikeyan, D., Sethuraman, N., & Suryavarman, K. (2023). Impact of non-edible biodiesel (Juliflora oil seed) on CI engine – combustion, performance and emission features. Materials Today: Proceedings. doi:10.1016/j.matpr.2023.05.306
[11] Musthafa, B., Saravanan, B., Vaibhav, B., Muhammad, P., Sam, F., & Asokan, M. A. (2023). Performance and emission analysis of a diesel engine fuelled with Juliflora Biodiesel: A simulation and experimental study. Australian Journal of Mechanical Engineering, 23(1), 220–234. doi:10.1080/14484846.2023.2274999
[12] Musthafa, B., & Asokan, M. A. (2024). Numerical and experimental investigation of performance and emission characteristics of hydrogen enrichment with Prosopis juliflora biodiesel in CI engine using RSM and ANN optimization. International Journal of Hydrogen Energy, 66, 326–336. doi:10.1016/j.ijhydene.2024.04.083
[13] Duraisamy, B., Velmurugan, K., & Venkatachalapathy, V. S. (2022). Analysis of Prosopis juliflora methyl ester as a fuel in the CI engine. International Journal of Research and Review, 9(7), 112–118. doi:10.52403/ijrr.20220713
[14] Mason, R. L., Gunst, R. F., & Hess, J. L. (2003). Statistical Design and Analysis of Experiments: With Applications to Engineering and Science (2nd ed.). John Wiley & Sons.
[15] Simsek, D., Ozyurek, D., Ileri, E., Akpinar, S., & Karaoglan, A. D. (2022). Optimizing of Wear Performance on Elevated Temperature of ZrO2 Reinforced AMCs Using Weighted Superposition Attraction Algorithm. Journal of Scientific & Industrial Research, 81, 462–474. doi:10.56042/jsir.v81i05.47027
[16] Baykasoğlu, A., & Akpinar, S. (2015). Weighted Superposition Attraction (WSA): A Swarm Intelligence Algorithm for Optimization Problems – Part 2: Constrained Optimization. Applied Soft Computing, 37, 396–415. doi:10.1016/j.asoc.2015.08.052
