Integrating experimental data and neural computation for emission forecasting in automotive systems

• Autorzy: Zimakowska-Laskowska Magdalena , Orynycz Olga , Kulesza Ewa , Matijošius Jonas , Tucki Karol , Świć Antoni

Identyfikatory

DOI

10.12913/22998624/208172

• Języki publikacji: EN

Abstrakty

EN

This work presents an integrated approach combining experimental testing and mathematical modeling to analyze fuel consumption and pollutant emissions in a spark-ignition engine vehicle. Experimental data were obtained from chassis dynamometer tests under the WLTP driving cycle, including time series of vehicle speed, energy consumption, and CO₂, CO, THC, and other compounds emissions. Two classes of artificial neural networks were implemented to capture the complex, nonlinear relationships between driving dynamics and emission profiles: Multi-Layer Perceptrons (MLP) and Self-Associative Neural Networks (SANN). These models were trained on real-world time series data to predict vehicle speed and energy consumption as functions of emission parameters and vice versa. The models demonstrated high accuracy, especially in the validation phase, confirming their potential for forecasting and environmental performance assessment. The neural network models underwent training, validation, and testing processes, allowing for the assessment of their effectiveness in predicting energy consumption under various system operating scenarios. The results demonstrated high prediction accuracy, confirming the usefulness of ANN as a tool for analyzing complex relationships between emissions and energy efficiency. The study developed models identifying the relationships between emission parameters and energy consumption characteristics, enabling precise modeling of combustion processes. The input data included key emission indicators such as carbon monoxide (CO), carbon dioxide (CO₂), and hydrocarbons (HC, NMHC and CH4), as well as operational parameters of energy systems. Additionally, the observed patterns in energy use were interpreted through a physical lens, considering the thermodynamics and chemical kinetics of combustion processes under different driving conditions. This hybrid methodology – combining data-driven AI with domain-specific physical insight – provides a robust framework for predicting the environmental impacts of internal combustion engines and optimizing their operation. The proposed approach applies to broader engineering contexts, including emission control strategy design, digital twin development for powertrains, and intelligent vehicle energy management systems. The proposed approach represents a significant step toward leveraging modern artificial intelligence methods to improve energy efficiency and develop emission reduction strategies through combustion condition optimization. The obtained results can serve as a foundation for further refining industrial processes in the context of sustainable development and environmental protection.

Słowa kluczowe

EN

emission modeling; energy efficiency; combustion process optimization; sustainable development; energy consumption prediction; artificial neural networks

• Wydawca: Lublin University of Technology ; Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin
• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2025
• Tom: Vol. 19, no. 9
• Strony: 452--468
• Opis fizyczny: Bibligr. 33 poz., fig., tab.

Twórcy

autor

Zimakowska-Laskowska Magdalena

• Environment Protection Centre, Motor Transport Institute, Poland

• https://orcid.org/0000-0001-9193-1473

autor

Orynycz Olga

• Faculty of Engineering Management, Department of Production Management, Bialystok University of Technology, ul. Wiejska 45A, 15-351 Bialystok, Poland

autor

Kulesza Ewa

• Faculty of Mechanical Engineering, Department of Mechanics and Applied Computer Science, Bialystok University of Technology, ul. Wiejska 45A, 15-351 Bialystok, Poland

• https://orcid.org/0000-0001-6585-8647

autor

Matijošius Jonas

• Mechanical Science Institute, Vilnius Gediminas Technical University, Plytinės Str. 25, LT-10105 Vilnius, Lithuania

autor

Tucki Karol

• Institute of Mechanical Engineering, Department of Production Engineering, Warsaw University of Life Sciences, ul. Nowoursynowska 164, 02-787 Warsaw, Poland

autor

Świć Antoni

• Department of Production Computerisation and Robotisation, Faculty of Mechanical Engineering, Lublin University of Technology, ul. Nadbystrzycka 36, 2018 Lublin, Poland

Bibliografia

• 1. Lejri D, Can A, Schiper N, Leclercq L. Accounting for traffic speed dynamics when calculating COPERT and PHEM pollutant emissions at the urban scale. Transportation Research Part D: Transport and Environment 2018;63:588–603. https://doi.org/10.1016/j.trd.2018.06.023.
• 2. Samaras C, Tsokolis D, Toffolo S, Magra G, Ntziachristos L, Samaras Z. Enhancing average speed emission models to account for congestion impacts in traffic network link-based simulations. Transportation Research Part D: Transport and Environment 2019;75:197–210. https://doi.org/10.1016/j.trd.2019.08.029.
• 3. Kulisz M, Kujawska J, Cioch M, Cel W. Modeling energy access challenges in Europe: a neural network approach to predicting household heating inadequacy using macro-energy indicators. Energies 2024;17:6104. https://doi.org/10.3390/en17236104.
• 4. Surblys V, Kozłowski E, Matijošius J, Gołda P, Laskowska A, Kilikevičius A. Accelerometer-based pavement classification for vehicle dynamics analysis using neural networks. Applied Sciences 2024;14:10027. https://doi.org/10.3390/app142110027.
• 5. Haykin S. Neural networks: a comprehensive foundation. Prentice Hall PTR. 1994.
• 6. Goodfellow I. Deep learning. n.d.
• 7. Zimakowska-Laskowska M, Laskowski P, Wojs MK, Orliński P. Prediction of pollutant emissions in various cases in road transport. Applied Sciences 2022;12:11975. https://doi.org/10.3390/app122311975.
• 8. Zimakowska-Laskowska M, Kozłowski E, Laskowski P, Wiśniowski P, Świderski A, Orynycz O. Vehicle exhaust emissions in the light of modern research tools: synergy of chassis dynamometers and computational models. Combustion Engines 2025;200:145–54. https://doi.org/10.19206/CE-201224.
• 9. Seo J, Lim Y, Han J, Park S. Machine learning-based estimation of gaseous and particulate emissions using internally observable vehicle operating parameters. Urban Climate 2023;52:101734. https://doi.org/10.1016/j.uclim.2023.101734.
• 10. Fu J, Yang R, Li X, Sun X, Li Y, Liu Z, et al. Application of artificial neural network to forecast engine performance and emissions of a spark ignition engine. Applied Thermal Engineering 2022;201:117749. https://doi.org/10.1016/j.applthermaleng.2021.117749.
• 11. Hashemi N, Clark NN. Artificial neural network as a predictive tool for emissions from heavy-duty diesel vehicles in Southern California. International Journal of Engine Research 2007;8:321–36. https://doi.org/10.1243/14680874JER00807.
• 12. Valeika G, Matijošius J, Orynycz O, Rimkus A, Kilikevičius A, Tucki K. Compression ignition internal combustion engine’s energy parameter research using variable (HVO) biodiesel and biobutanol fuel blends. Energies 2024;17:262. https://doi.org/10.3390/en17010262.
• 13. Kong X, Chen Z, Liu W, Ning K, Zhang L, Muhammad Marier S, et al. Deep learning for time series forecasting: a survey. Int J Mach Learn & Cyber 2025. https://doi.org/10.1007/s13042-025-02560-w.
• 14. Shin S, Lee Y, Kim M, Park J, Lee S, Min K. Deep neural network model with Bayesian hyperparameter optimization for prediction of NO x at transient conditions in a diesel engine. Engineering Applications of Artificial Intelligence 2020;94:103761. https://doi.org/10.1016/j.engappai.2020.103761.
• 15. Tucki K, Orynycz OA, Świć A, Wasiak A, Mruk R, Gola A. Analysis of the possibility of using neural networks to monitor the technical efficiency of diesel engines during operation. Adv Sci Technol Res J 2023;17:1–15. https://doi.org/10.12913/22998624/172003.
• 16. Sun P, Cheng X, Yang S, Ruan E, Zhao H, Liu Y, et al. Artificial neural network models for forecasting the combustion and emission characteristics of ethanol/gasoline DFSI engines with combined injection strategy. Case Studies in Thermal Engineering 2024;54:104007. https://doi.org/10.1016/j.csite.2024.104007.
• 17. Sathishkumar S, Ibrahim MM. Evaluation of machine learning algorithms on hydrogen boosted homogeneous charge compression ignition engine operation for performance and emission prediction. Process Safety and Environmental Protection 2025;195:106756. https://doi.org/10.1016/j.psep.2025.01.010.
• 18. Tasdemir S, Saritas I, Ciniviz M, Allahverdi N. Artificial neural network and fuzzy expert system comparison for prediction of performance and emission parameters on a gasoline engine. Expert Systems with Applications 2011:S0957417411007251. https://doi.org/10.1016/j.eswa.2011.04.198.
• 19. Yang R, Yan Y, Sun X, Wang Q, Zhang Y, Fu J, et al. An artificial neural network model to predict efficiency and emissions of a gasoline engine. Processes 2022;10:204. https://doi.org/10.3390/pr10020204.
• 20. Azeez OS, Pradhan B, Shafri HZM, Shukla N, Lee C-W, Rizeei HM. Modeling of CO emissions from traffic vehicles using artificial neural networks. Applied Sciences 2019;9:313. https://doi.org/10.3390/app9020313.
• 21. Alazemi F, Alazmi A, Alrumaidhi M, Molden N. Predicting fuel consumption and emissions using GPS-Based machine learning models for gasoline and diesel vehicles. Sustainability 2025;17:2395. https://doi.org/10.3390/su17062395.
• 22. Cortes C, Vapnik V. Support-vector networks. Mach Learn 1995;20:273–97. https://doi.org/10.1007/BF00994018.
• 23. Dini P, Basso G, Saponara S, Romano C. Real‐time monitoring and ageing detection algorithm design with application on SiC‐based automotive power drive system. IET Power Electronics 2024;17:690–710. https://doi.org/10.1049/pel2.12679.
• 24. Tlelo-Cuautle E, Rangel-Magdaleno JDJ, De La Fraga LG. Artificial Neural Networks for Time Series Prediction. Engineering Applications of FPGAs, Cham: Springer International Publishing; 2016, p. 117–50. https://doi.org/10.1007/978-3-319-34115-6_5.
• 25. Gierz Ł, Al-Sammarraie MAJ, Özbek O, Markowski P. The use of image analysis to study the effect of moisture content on the physical properties of grains. Sci Rep 2024;14. https://doi.org/10.1038/s41598-024-60852-7.
• 26. Al-Sammarraie MAJ, Gierz ŁA, Özbek O, Kırılmaz H. Power predicting for power take-off shaft of a disc maize silage harvester using machine learning. Adv Sci Technol Res J 2024;18:1–9. https://doi.org/10.12913/22998624/188666.
• 27. Hussain I, Ching KB, Uttraphan C, Tay KG, Noor A. Evaluating machine learning algorithms for energy consumption prediction in electric vehicles: A comparative study. Sci Rep 2025;15:16124. https://doi.org/10.1038/s41598-025-94946-7.
• 28. Zhao D, Li H, Hou J, Gong P, Zhong Y, He W, et al. A review of the data-driven prediction method of vehicle fuel consumption. Energies 2023;16:5258. https://doi.org/10.3390/en16145258.
• 29. Seo J, Yun B, Park J, Park J, Shin M, Park S. Prediction of instantaneous real-world emissions from diesel light-duty vehicles based on an integrated artificial neural network and vehicle dynamics model. Science of The Total Environment 2021;786:147359. https://doi.org/10.1016/j.scitotenv.2021.147359.
• 30. Fang L, He B. A deep learning framework using multi-feature fusion recurrent neural networks for energy consumption forecasting. Applied Energy 2023;348:121563. https://doi.org/10.1016/j.apenergy.2023.121563.
• 31. Orynycz O, Zimakowska-Laskowska M, Kulesza E. CO2 Emission and Energy Consumption Estimates in the COPERT Model—Conclusions from Chassis Dynamometer Tests and SANN Artificial Neural Network Models and Their Meaning for Transport Management. Energies 2025;18:3457. https://doi.org/10.3390/en18133457.
• 32. Qiao Q, Eskandari H, Saadatmand H, Sahraei MA. An interpretable multi-stage forecasting framework for energy consumption and CO2 emissions for the transportation sector. Energy 2024;286:129499. https://doi.org/10.1016/j.energy.2023.129499.
• 33. Tomiło P. Classification of the condition of pavement with the use of machine learning methods. Transport and Telecommunication Journal 2023;24:158–66. https://doi.org/10.2478/ttj-2023-0014.