Enhancing Random Forest Model Accuracy using GridSearchCV Optimization for Predicting Multi-Cylinder Engine Performance with Hydrogen-Enriched Natural Gas Blends
Downloads
Diesel generators (gensets) are essential in India for industries, construction, agriculture, and as backup power for hospitals and data centres. Common fuels include diesel, petrol, natural gas, and, increasingly, solar energy, with hybrid systems gaining popularity for improved efficiency and reduced emissions. Diesel gensets remain reliable and cost-effective, especially in remote areas, but growing environmental concerns are driving adoption of cleaner alternatives like compressed natural gas (CNG), bio-CNG, and dual-fuel systems. HCNG (hydrogen-enriched compressed natural gas) gensets are more efficient and environmentally friendly, though they require greater initial investment. Adding hydrogen enhances combustion and reduces emissions. In this study, various HCNG blends were tested on a multi-cylinder, single-speed gas engine. Experimental evaluation of combustion and performance characteristics is typically time and resource-intensive, so Machine Learning (ML) was applied to streamline the process, thereby minimizing the number of required experiments. The engine performance is assessed using the engine dynamometer, whereas the combustion characteristics are obtained from the High-Speed Data Acquisition (HSDA) system. A Random Forest (RF) regression model was developed to predict performance and combustion characteristics for higher HCNG blends from lower-blend data, with hyperparameter optimization used to improve accuracy and minimize overfitting. Predicted values were validated against experimental results, showing strong correlations. Key parameters like Brake-Specific Fuel Consumption (BSFC), Brake Mean Effective Pressure (BMEP), Exhaust Temperature, Maximum In-Cylinder Combustion Pressure (Pmax), Indicated Mean Effective Pressure (IMEP) and Combustion Duration were predicted, with evaluations showing strong correlations between predicted values and actual results.
Airamadan, A. S., Al Ibrahim, Z., Mohan, B., & Badra, J. (2022). Machine Learning Model for Spark-Assisted Gasoline Compression Ignition Engine. SAE Technical Papers. https://doi.org/10.4271/2022-01-0459
Bandyopadhyay, D., Sutar, P., Sonawane, S., Rairikar, S., Thipse, Dr. S., & Sale, O. (2025). Raw Emissions Determination and Calculations for Blended Fuel – HCNG. ARAI Journal of Mobility Technology, 5(1), 1490–1501. https://doi.org/10.37285/ajmt.5.1.10
Cheng, M., Zhao, X., Dhimish, M., Qiu, W., & Niu, S. (2024). A Review of Data-Driven Surrogate Models for Design Optimization of Electric Motors. IEEE Transactions on Transportation Electrification, 10(4), 8413–8431. https://doi.org/10.1109/TTE.2024.3366417
Choi, Y., Park, C.-W., Won, S.-Y., & Kim, C.-G. (2011). A Study on the Optimization of Combustion and Emission Performance in a Heavy-duty HCNG Engine. Journal of the Korean Institute of Gas, 15(2), 15–20. https://doi.org/10.7842/kigas.2011.15.2.015
De Simio, L., Gambino, M., & Iannaccone, S. (2011). Effect of natural gas/hydrogen blends on spark ignition stoichiometric engine efficiency. SAE Technical Papers. https://doi.org/10.4271/2011-24-0121
Deng, J., Ma, F., Li, S., He, Y., Wang, M., Jiang, L., & Zhao, S. (2011). Experimental study on combustion and emission characteristics of a hydrogen-enriched compressed natural gas engine under idling condition. International Journal of Hydrogen Energy, 36(20), 13150–13157. https://doi.org/10.1016/j.ijhydene.2011.07.036
Duan, H., Yin, X., Kou, H., Wang, J., Zeng, K., & Ma, F. (2023). Regression prediction of hydrogen enriched compressed natural gas (HCNG) engine performance based on improved particle swarm optimization back propagation neural network method (IMPSO-BPNN). Fuel, 331, 125872. https://doi.org/10.1016/j.fuel.2022.125872
Fact.MR. (2024). P-Phenylenediamine Market Size & Industry Analysis to 2032. https://www.factmr.com/report/p-phenylenediamine-market
Farhan, M., Chen, T., Rao, A., Shahid, M. I., Liu, Y., & Ma, F. (2024). Comparative knock analysis of HCNG fueled spark ignition engine using different heat transfer models and prediction of knock intensity by artificial neural network fitting tool. Energy, 304, 132135. https://doi.org/10.1016/j.energy.2024.132135
Ghareeb, A., Abdulkarim, A. H., Salman, A. S., Kakei, A., Canli, E., Chiasson, A., Choi, J.-K., & Dalkilic, A. S. (2024). Prediction of the operational performance of a vehicle seat thermal management system using statistical and machine learning techniques. Case Studies in Thermal Engineering, 60, 104626. https://doi.org/10.1016/j.csite.2024.104626
Gong, C., Li, D., Li, Z., & Liu, F. (2016). Numerical study on combustion and emission in a DISI methanol engine with hydrogen addition. International Journal of Hydrogen Energy, 41(1), 647–655. https://doi.org/10.1016/j.ijhydene.2015.11.062
Hao, D., Mehra, R. K., Luo, S., Nie, Z., Ren, X., & Fanhua, M. (2020). Experimental study of hydrogen enriched compressed natural gas (HCNG) engine and application of support vector machine (SVM) on prediction of engine performance at specific condition. International Journal of Hydrogen Energy, 45(8), 5309–5325. https://doi.org/10.1016/j.ijhydene.2019.04.039
Hora, T. S., & Agarwal, A. K. (2016). Effect of varying compression ratio on combustion, performance, and emissions of a hydrogen enriched compressed natural gas fuelled engine. Journal of Natural Gas Science and Engineering, 31, 819–828. https://doi.org/10.1016/j.jngse.2016.03.041
Hou, Y., Zhang, Z., Liu, P., Song, C., & Wang, Z. (2021). Research on a novel data-driven aging estimation method for battery systems in real-world electric vehicles. Advances in Mechanical Engineering, 13(7). https://doi.org/10.1177/16878140211027735
Ishaq, H., & Dincer, I. (2020). Performance investigation of adding clean hydrogen to natural gas for better sustainability. Journal of Natural Gas Science and Engineering, 78, 103236. https://doi.org/10.1016/j.jngse.2020.103236
Kim, D.-K., Ryu, D., Lee, Y., & Choi, D.-H. (2024). Generative models for tabular data: A review. Journal of Mechanical Science and Technology, 38(9), 4989–5005. https://doi.org/10.1007/s12206-024-0835-0
Kou, L., Qin, Y., Zhao, X., & Fu, Y. (2019). Integrating synthetic minority oversampling and gradient boosting decision tree for bogie fault diagnosis in rail vehicles. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 233(3), 312–325. https://doi.org/10.1177/0954409718795089
Lather, R. S., & Das, L. M. (2019). Performance and emission assessment of a multi-cylinder S.I engine using CNG & HCNG as fuels. International Journal of Hydrogen Energy, 44(38), 21181–21192. https://doi.org/10.1016/j.ijhydene.2019.03.137
Lee, J., & Kwon, D. (2025). Reduction in electronic package design processes through AI-based surrogate models. JMST Advances, 7, 125–130. https://doi.org/10.1007/s42791-025-00106-3
Liu, J., Duan, X., Yuan, Z., Liu, Q., & Tang, Q. (2017). Experimental study on the performance, combustion and emission characteristics of a high compression ratio heavy-duty spark-ignition engine fuelled with liquefied methane gas and hydrogen blend. Applied Thermal Engineering, 124, 585–594. https://doi.org/10.1016/j.applthermaleng.2017.06.067
M., G. N., Banapurmath, N. R., & Tewari, P. G. (2016). Performance, Combustion and Emission characteristics of a Manifold Injected HCNG-Biodiesel Dual Fuel Operation / Bir Manifolda Enjekte Edilen HCNG-Biyodizelin Çift Yakıtlı Çalışmasının Performans, Yanma ve Emisyon Karakteristikleri. International Journal of Automotive Engineering and Technologies, 4(4), 201.
Mehra, R. K., Duan, H., Luo, S., Rao, A., & Ma, F. (2018). Experimental and artificial neural network (ANN) study of hydrogen enriched compressed natural gas (HCNG) engine under various ignition timings and excess air ratios. Applied Energy. https://doi.org/10.1016/j.apenergy.2018.06.085
Michikawauchi, R., Tanno, S., Ito, Y., Kanda, M., & Kawauchi, M. (2011). Combustion improvement of CNG engines by hydrogen addition. SAE Technical Papers. https://doi.org/10.4271/2011-01-1996
Mustafi, N. N., & Agarwal, A. K. (2019). Combustion and Emission Characteristics, and Emission Control of CNG Fueled Vehicles. In A. P. Singh, Y. C. Sharma, N. N. Mustafi, & A. K. Agarwal (Eds.), Alternative Fuels and Their Utilization Strategies in Internal Combustion Engines (pp. 201–228). Springer Singapore. https://doi.org/10.1007/978-981-15-0418-1_12
Pandey, V., Guluwadi, S., & Tafesse, G. H. (2022). Performance and emission study of low HCNG fuel blend in SI engine with fixed ignition timing. Cogent Engineering, 9(1). https://doi.org/10.1080/23311916.2021.2010925
Papaioannou, N., Fang, X., Leach, F., Lewis, A., Akehurst, S., & Turner, J. (2021). A Random Forest Algorithmic Approach to Predicting Particulate Emissions from a Highly Boosted GDI Engine. SAE Technical Papers. https://doi.org/10.4271/2021-24-0076
Park, C., Kim, C., Choi, Y., Won, S., & Moriyoshi, Y. (2011). The influences of hydrogen on the performance and emission characteristics of a heavy duty natural gas engine. International Journal of Hydrogen Energy, 36(5), 3739–3745. https://doi.org/10.1016/j.ijhydene.2010.12.021
Pathak, M., Kuttippurath, J., & Kumar, R. (2024). Long-term changes in black carbon aerosols and their health effects in rural India during the past two decades (2000–2019). Journal of Hazardous Materials Advances, 16, 100519. https://doi.org/10.1016/j.hazadv.2024.100519
Prasad Rao, G. A., & Karthikeya Sharma, T. (2020). Engine Emission Control Technologies: Design Modifications and Pollution Mitigation Techniques (1st ed.). Apple Academic Press. https://doi.org/10.1201/9780429322228
Rao, A., Chen, T., Liu, Y., & Ma, F. (2023). Computational analysis of performances for a hydrogen enriched compressed natural gas engine’ by advanced machine learning algorithms. Fuel, 347, 128244. https://doi.org/10.1016/j.fuel.2023.128244
Sahoo, S., Kumar, V. N. S. P., & Srivastava, D. K. (2022). Quantitative analysis of engine parameters of a variable compression ratio CNG engine using machine learning. Fuel, 311, 122587. https://doi.org/10.1016/j.fuel.2021.122587
Shah, N., Zhao, P., Delvescovo, D., & Ge, H. (2019). Prediction of autoignition and flame properties for multicomponent fuels using machine learning techniques. SAE Technical Papers. https://doi.org/10.4271/2019-01-1049
Singh, S., Mishra, S., Mathai, R., Sehgal, A. K., & Suresh, R. (2016). Comparative Study of Unregulated Emissions on a Heavy Duty CNG Engine using CNG & Hydrogen Blended CNG as Fuels. SAE International Journal of Engines, 9(4), 2292–2300.
Sofianopoulos, A., Assanis, D. N., & Mamalis, S. (2016). Effects of Hydrogen Addition on Automotive Lean-Burn Natural Gas Engines: Critical Review. Journal of Energy Engineering, 142(2), E4015010. https://doi.org/10.1061/(ASCE)EY.1943-7897.0000319
Sonawane, S., Sekhar, R., Warke, A., Thipse, S., & Varma, C. (2023a). Forecasting of Engine Performance for Gasoline-Ethanol Blends using Machine Learning. Journal of Engineering and Technological Sciences, 55(3), 340–355. https://doi.org/10.5614/j.eng.technol.sci.2023.55.3.10
Verma, G., Prasad, R. K., Agarwal, R. A., Jain, S., & Agarwal, A. K. (2016). Experimental investigations of combustion, performance and emission characteristics of a hydrogen enriched natural gas fuelled prototype spark ignition engine. Fuel, 178, 209–217. https://doi.org/10.1016/j.fuel.2016.03.022
Yang, R., Yan, Y., Sijia, R., Liu, Z., Zhang, Y., & Fu, J. (2022). Modeling Performance and Emissions of a Spark Ignition Engine with Machine Learning Approaches. SAE Technical Papers. https://doi.org/10.4271/2022-01-0380
Yang, R., Yan, Y., Sun, X., Wang, Q., Zhang, Y., Fu, J., & Liu, Z. (2022). An Artificial Neural Network Moel to Predict Efficiency and Emissions of a Gasoline Engine. Processes, 10(2), 204. https://doi.org/10.3390/pr10020204
Zareei, J., Haseeb, M., Ghadamkheir, K., Farkhondeh, S. A., Yazdani, A., & Ershov, K. (2020). The effect of hydrogen addition to compressed natural gas on performance and emissions of a DI diesel engine by a numerical study. International Journal of Hydrogen Energy, 45(58), 34241–34253. https://doi.org/10.1016/j.ijhydene.2020.09.027
Copyright (c) 2025 Journal of Engineering and Technological Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
