A comparative analysis of regression modelling and artificial neural networks for diesel engine performance prediction

Muhammad Asad; Umer Iftikhar; Daniyal Abbasi; Muhammad Bilal Jamil

doi:10.15282/ijame.23.1.2026.13.1011

Authors

Muhammad Asad Mechanical Engineering Department, University of Engineering and Technology, G.T. Road, Lahore 54890, Pakistan
Umer Iftikhar Mechanical Engineering Department, University of Engineering and Technology, G.T. Road, Lahore 54890, Pakistan
Daniyal Abbasi Mining Engineering Department, University of Engineering and Technology, G.T. Road, Lahore 54890, Pakistan
Muhammad Bilal Jamil Mining Engineering Department, University of Engineering and Technology, G.T. Road, Lahore 54890, Pakistan

DOI:

https://doi.org/10.15282/ijame.23.1.2026.13.1011

Keywords:

Regression, Artificial Neural Network, 4-Stroke Diesel Engine, RPM Variation, Throttle Position, Comparative Analysis

Abstract

Diesel engines are inherently difficult to analyze due to the complex and nonlinear interactions among engine speed, throttle position, and load. This study investigates the key factors affecting the performance of a four-stroke diesel engine. It compares the predictive capabilities of multiple linear regression and Artificial Neural Networks (ANN) in modeling five critical performance indicators: power (kW), torque (Nm), Brake Thermal Efficiency (BTE, %), Brake Specific Fuel Consumption (BSFC, kg/kWh), and Air-to-Fuel (A/F) ratio. Experimental data were collected from a TD23 diesel engine tested on an engine dynamometer across a range of operating conditions, with engine speeds from 1100 to 1600 RPM, throttle positions from 10% to 40%, and varying loads, yielding a dataset of 24 observations. Regression models were developed using Minitab, while ANN models were implemented in MATLAB. Results show that engine speed and load exert the strongest influence on performance, whereas throttle position has a relatively minor effect. Although regression achieves slightly lower Root Mean Square Error (RMSE) for power (0.1406 kW vs. 0.3561 kW) and torque (1.0937 Nm vs. 1.4698 Nm), likely due to the small dataset favoring simpler linear fits, the ANN consistently demonstrates superior coefficient of determination (R²) values for nonlinear responses. It improves R² by 44.38% for BSFC (0.9143 vs. 0.4705), 35.26% for BTE (0.8186 vs. 0.4660), 19.31% for torque (0.8136 vs. 0.6205), and 2.63% for A/F ratio (0.8589 vs. 0.8326). Notably, BSFC exhibits extremely small RMSE values due to its unit scale (kg/kWh) and low data variability, underscoring the importance of clear unit reporting. Overall, the ANN proves more effective at capturing the complex, nonlinear behaviour of diesel engine performance, particularly when sufficient data diversity is present, while regression remains competitive for near-linear outputs in data-limited scenarios.

References

[1] K.M. Akkoli, N.R. Banapurmath, M.M. Shivashimpi, M.E.M. Soudagar, I.A. Badruddin, M.A. Alazwari, et al., "Effect of injection parameters and producer gas derived from redgram stalk on the performance and emission characteristics of a diesel engine," Alexandria Engineering Journal, vol. 60, no. 3, pp. 3133-3142, 2021.

[2] A. Syta, J. Czarnigowski, P. Jakliński, "Detection of cylinder misfire in an aircraft engine using linear and nonlinear signal analysis," Measurement, vol. 174, p. 108982, 2021.

[3] B. Mehlig, "Machine learning with neural networks: an introduction for scientists and engineers," UK: Cambridge University Press, 2021.

[4] G. Sakthivel, "Prediction of CI engine performance, emission, and combustion characteristics using fish oil as a biodiesel at different injection timing using fuzzy logic," Fuel, vol. 183: pp. 214-229, 2016.

[5] D. Hao, R.K. Mehra, S. Luo, Z. Nie, X. Ren, M. Fanhua, "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, vol. 45, no. 8, pp. 5309-5325, 2020.

[6] R. Dancila, R. Botez, "New flight trajectory optimisation method using genetic algorithms," The Aeronautical Journal, vol. 125, no. 1286, pp. 618-671, 2021.

[7] A. Norouzi, M. Aliramezani, C.R. Koch, "A correlation-based model order reduction approach for a diesel engine NOx and brake mean effective pressure dynamic model using machine learning," International Journal of Engine Research, vol. 22, no. 8, pp. 2654-2672, 2021.

[8] Z. Zhang, J. Li, J. Tian, G. Xie, D. Tan, B. Qin, et al., "Effects of different diesel-ethanol dual fuel ratio on performance and emission characteristics of diesel engine," Processes, vol. 9, no. 7, p. 1135, 2021.

[9] D.O. Onukwuli, C. Esonye, A.U. Ofoefule, R. Eyisi, "Comparative analysis of the application of artificial neural network-genetic algorithm and response surface methods-desirability function for predicting the optimal conditions for biodiesel synthesis from chrysophyllum albidum seed oil," Journal of the Taiwan Institute of Chemical Engineers, vol. 125, pp. 153-167, 2021.

[10] N. Gammoudi, M. Mabrouk, T. Bouhemda, K. Nagaz, A. Ferchichi, "Modeling and optimization of capsaicin extraction from Capsicum annuum L. using response surface methodology (RSM), artificial neural network (ANN), and Simulink simulation," Industrial Crops and Products, vol. 171, p. 113869, 2021.

[11] A.T. Hoang, S. Nižetić, H.C. Ong, W. Tarelko, V.V. Pham, T.H. Le,, et al., "A review on application of artificial neural network (ANN) for performance and emission characteristics of diesel engine fueled with biodiesel-based fuels," Sustainable Energy Technologies and Assessments, vol. 47, p. 101416, 2021.

[12] A.V. Prabhu, A. Alagumalai, A. Jodat, "Artificial neural networks to predict the performance and emission parameters of a compression ignition engine fuelled with diesel and preheated biogas–air mixture," Journal of Thermal Analysis and Calorimetry, vol. 145, pp. 1935-1948, 2021.

[13] M.I.L. Galdo, J.T. Miranda, J.M.R. Lorenzo, C.G. Caccia, "Internal modifications to optimize pollution and emissions of internal combustion engines through multiple-criteria decision-making and artificial neural networks," International Journal of Environmental Research and Public Health, vol. 18, no. 23, p. 12823, 2021.

[14] A.N. Bhatt, N. Shrivastava, "Application of artificial neural network for internal combustion engines: a state of the art review," Archives of Computational Methods in Engineering, vol. 29, no. 2, p. 897-919, 2022.

[15] X.H. Fang, N. Papaioannou, F. Leach, M.H. Davy, "On the application of artificial neural networks for the prediction of NOx emissions from a high-speed direct injection diesel engine," International Journal of Engine Research, vol. 22, no. 6, p. 1808-1824, 2021.

[16] M. Aliramezani, C.R. Koch, M. Shahbakhti, "Modeling, diagnostics, optimization, and control of internal combustion engines via modern machine learning techniques: A review and future directions," Progress in Energy and Combustion Science,vol. 88, p. 100967, 2022.

[17] W. Yu, F. Zhao, "Predictive study of ultra-low emissions from dual-fuel engine using artificial neural networks combined with genetic algorithm," International Journal of Green Energy, vol. 16, no. 12, p. 938-946, 2019.

[18] I. Veza, M.F. Muhamad Said, Z. Abdul Latiff, M.A. Abas, "Application of Elman and Cascade neural network (ENN and CNN) in comparison with adaptive neuro fuzzy inference system (ANFIS) to predict key fuel properties of ABE-diesel blends," International Journal of Green Energy, vol. 18, no. 14, p. 1510-1522, 2021.

[19] M.K.D. Kiani, B. Ghobadian, T. Tavakoli, A.M. Nikbakht, G. Najafi, "Application of artificial neural networks for the prediction of performance and exhaust emissions in SI engine using ethanol-gasoline blends," Energy, vol. 35, no. 1, p. 65-69, 2010.

[20] S. Roy, R. Banerjee, P.K. Bose, "Performance and exhaust emissions prediction of a CRDI-assisted single cylinder diesel engine coupled with EGR using artificial neural network," Applied Energy, vol. 119, p. 330-340, 2014.

[21] S. Arumugam, G. Sriram, P.S. Subramanian, "Application of artificial intelligence to predict the performance and exhaust emissions of diesel engine using rapeseed oil methyl ester," Procedia engineering, vol. 38, p. 853-860, 2012.

[22] A.T. Hoang, S. Nižetić, H.C. Ong, W. Tarelko, V.V. Pham, T.H. Le, et al., "A review on application of artificial neural network (ANN) for performance and emission characteristics of diesel engine fueled with biodiesel-based fuels," Sustainable Energy Technologies and Assessments, vol. 47, p. 101416, 2021.

[23] Y. Kurtgoz, M. Karagoz, E. Deniz, "Biogas engine performance estimation using ANN," Engineering Science and Technology, An International Journal, vol. 20, 6, p. 1563-1570, 2017.

[24] K.M. Akkoli, N.R. Banapurmath, M.M. Shivashimpi, M.E.M. Soudagar, I.A. Badruddin, M.A. Alazwari, et al., "Effect of injection parameters and producer gas derived from redgram stalk on the performance and emission characteristics of a diesel engine," Alexandria Engineering Journal, vol. 60, no. 3, p. 3133-3142, 2021.

[25] M. Zare, "Compare neural network and linear regression when there exist outliers or sensitive data: Advantages and disadvantages. 2024.

[26] R.N. Prasad, P.N. Devi "A comparative analysis of machine learning algorithms for big data applications in predictive analytics," International Journal of Scientific Research and Management, vol. 12, no. 10, pp. 1608-30 2024.

[27] M. Grebovic, L. Filipovic, I. Katnic, M. Vukotic, T. Popovic, "Overcoming limitations of statistical methods with artificial neural networks," in 2022 International Arab Conference on Information Technology, IEEE, 2022.

[28] Y. Li, Y. Wang, Z. Lin, H. Xie, "An efficient approach to regression problems with tensor neural networks". arXiv preprint arXiv:2406.09694, 2024.

[29] P. Belany, P. Hrabovsky, S. Sedivy, N. Cajova Kantova, Z. Florkova, "A comparative analysis of polynomial regression and artificial neural networks for prediction of lighting consumption," Buildings, vol. 14, no. 6, p. 1712, 2024.

[30] M, Rahman, M. Asadujjaman, "Implementation of artificial neural network on regression analysis," In 2021 5th Annual Systems Modelling Conference, IEEE, 2021.

]31] H. Oğuz, I. Sarıtas, H.E. Baydan, "Prediction of diesel engine performance using biofuels with artificial neural network," Expert Systems with Applications, vol. 37, no. 9, p. 6579-6586, 2010.

[32] Y. Wang, J. Li, G. Wang, G. Chen, S. He, "Prediction of diesel particulate filter regeneration conditions and diesel engine performance under regeneration mode using AMSO-BPNN and combined with XGBoost," Applied Energy, vol. 377, p. 124341, 2025.

[33] H. Dave, V. Vakharia, H. Panchal, M.I.H. Siddiqui, D. Dobrotă, "ANN and multilayer-ELM based prediction of combustion, performance and emission characteristics of a diesel engine fuelled with Diesel-DTBP blends," Case Studies in Thermal Engineering, vol. 72, p. 106323, 2025.

[34] O. Odufuwa, L. Tartibu, K. Kusakana, "Artificial neural network modelling for predicting efficiency and emissions in mini-diesel engines: Key performance indicators and environmental impact analysis," Fuel, vol. 387, p. 134294, 2025.

[35] N.K. Pallicheruvu, S. Gnanasekaran, "ANN-driven prediction of optimal machine learning models for engine performance in a dual-fuel mode powered by biogas and fish oil biodiesel," Energy Conversion and Management, vol. 25, p. 100827, 2025.

[36] R. Khujamberdiev, H.M. Cho, "Artificial intelligence in automotives: ANNs’ impact on biodiesel engine performance and emissions," Energies, vol. 18, no. 2, p. 438, 2025.

[37] P. Paramasivam, K. Alnamasi, A.M.A. Alsharif, P.K. Kanti, "Performance and emission analysis of a dual-fuel engine using biogas and algal biodiesel: Machine learning prediction and response surface optimization," Case Studies in Thermal Engineering, p. 107227, 2025

[38] A. Dong, H. Cui, C. Zhao, Y. Guan, "Neural network prediction based on dung beetle optimization algorithm and engine performance emission optimization using multi-objective rime optimization algorithm," Energy, p. 137553, 2025

[39] A.A.M. Mohammedali, A. Albadwi, A.A.M. Omara, K. Ali, M.I.H. Ali, "Machine learning prediction and evolutionary multi-objective optimization on performance and emissions of a syngas-diesel dual-fuel engine," International Journal of Hydrogen Energy, vol. 162, p. 150781, 2025.

[40] H. Kawakami, A. Zukeran, K. Yasumoto, M. Kubojima, Y. Ehara, T. Yamamoto, et al., "Effect of AC electrostatic precipitator on removal diesel exhaust particles," IEEJ Transactions on Fundamentals and Materials, vol. 131, no. 3, p. 192-198, 2011.