Estimation of emissions from failures in Otto engines using convolutional neuronal networks
Article Sidebar
Main Article Content
Abstract
This study applies a machine learning technique, specifically Convolutional Neural Networks (CNNs), to predict pollutant emissions resulting from failures in actuators and components of Otto engines. The work addresses the current lack of non-intrusive methods that exploit signals already available in the vehicle to estimate, with high accuracy, emissions associated with failures in the injection, ignition, and air intake systems. Concentrations of CO (% carbon monoxide), CO2 (% carbon dioxide), HC (unburned hydrocarbons, ppm), and O2 (% oxygen) are quantified by analyzing the Manifold Absolute Pressure (MAP) sensor signal under a rigorous sampling and signal-processing protocol. Optimal features are extracted from the MAP signal based on their informational relevance and discriminative capacity. These features are obtained through spectrographic transformation, enabling the construction of a robust database. The resulting dataset serves as an effective input for CNN training, achieving emission prediction errors below 1%.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The Universidad Politécnica Salesiana of Ecuador preserves the copyrights of the published works and will favor the reuse of the works. The works are published in the electronic edition of the journal under a Creative Commons Attribution/Noncommercial-No Derivative Works 4.0 Ecuador license: they can be copied, used, disseminated, transmitted and publicly displayed.
The undersigned author partially transfers the copyrights of this work to the Universidad Politécnica Salesiana of Ecuador for printed editions.
It is also stated that they have respected the ethical principles of research and are free from any conflict of interest. The author(s) certify that this work has not been published, nor is it under consideration for publication in any other journal or editorial work.
The author (s) are responsible for their content and have contributed to the conception, design and completion of the work, analysis and interpretation of data, and to have participated in the writing of the text and its revisions, as well as in the approval of the version which is finally referred to as an attachment.
References
[1] W. R. Contreras Urgilés, R. S. León Japa, and J. L. Maldonado Ortega, “Predicción de emisiones de CO y HC en motores Otto mediante redes neuronales,” Ingenius, no. 23, pp. 30–39, Dec. 2019. [Online]. Available: https://doi.org/10.17163/ings.n23.2020.03
[2] F. Narváez, F. E. Sierra Vargas, and M. A. Montenegro Mier, “Modelo basado en redes neuronales para predecir las emisiones en un motor diésel que opera con mezclas de biodiésel de higuerilla,” Informador Técnico, vol. 76, p. 46, Dec. 2012. [Online]. Available: https://doi.org/10.23850/22565035.28
[3] R. S. Chauhan and N. Shrivastava, “Neuro fuzzy-grey wolf optimization-based modelling and analysis of diesel engine using tire oil with different proportions of 2-EHN,” Fuel, vol. 384, p. 133849, Mar. 2025. [Online]. Available: https://doi.org/10.1016/j.fuel.2024.133849
[4] F. Sapio, F. Aglietti, P. Ferreri, and A. Savuca, “Neural-network-based modeling of SCR systems for emission simulation: A comprehensive approach,” SAE International Journal of Advances and Current Practices in Mobility, vol. 07, no. 3, pp. 1437–1452, Sep. 2024. [Online]. Available: https://doi.org/10.4271/2024-24-0042
[5] H. H. Imtiaz, P. Schaffer, Y. Liu, P. Hesse, A. Bergmann, and M. Kupper, “Qualitative and quantitative analyses of automotive exhaust plumes for remote emission sensing application using gas schlieren imaging sensor system,” Atmosphere, vol. 15, no. 9, p. 1023, Aug. 2024. [Online]. Available: https://doi.org/10.3390/atmos15091023
[6] W. Torres Guin, J. Sánchez Aquino, S. Bustos Gaibor, and M. Coronel Suárez, “Arquitectura de IoT para el monitoreo de emisiones de gases contaminantes de vehículos y su validación a través de machine learning,” Ingenius, no. 32, pp. 9–17, Oct. 2024. [Online]. Available: https://doi.org/10.17163/ings.n32.2024.01
[7] R. S. Jawad and H. Abid, “HVDC fault detection and classification with artificial neural network based on ACO-DWT method,” Energies, vol. 16, no. 3, p. 1064, Jan. 2023. [Online]. Available: https://doi.org/10.3390/en16031064
[8] F. Ricci, M. Avana, and F. Mariani, “Enhancing lambda measurement in hydrogen-fueled SI engines through virtual sensor implementation,” Energies, vol. 17, no. 16, p. 3932, Aug. 2024. [Online]. Available: https://doi.org/10.3390/en17163932
[9] D. Tian, Q. Li, F. Liu, J. Khan, M. Q. Abbas, and Z. Du, “VOC data-driven evaluation of vehicle cabin odor: from ANN to CNN-BiLSTM,” Environmental Science and Pollution Research, vol. 31, no. 22, pp. 32 826–32 841, Apr. 2024. [Online]. Available: https://doi.org/10.1007/s11356-024-33293-y
[10] I. Cesur and F. Uysal, “Experimental investigation and artificial neural network-based modelling of thermal barrier engine performance and exhaust emissions for methanol-gasoline blends,” Energy, vol. 291, p. 130393, Mar. 2024. [Online]. Available: https://doi.org/10.1016/j.energy.2024.130393
[11] A. K and P. Rithishbrahma, “Prediction of vehicle carbon emission using machine learning,” in 2024 5th International Conference on Electronics and Sustainable Communication Systems (ICESC). IEEE, Aug. 2024, pp. 1814–1818. [Online]. Available: https://doi.org/10.1109/ICESC60852.2024.10690134
[12] M. A. Rahim, M. M. Rahman, M. S. Islam, A. J. M. Muzahid, M. A. Rahman, and D. Ramasamy, “Deep learning-based vehicular engine health monitoring system utilising a hybrid convolutional neural network/bidirectional gated recurrent unit,” Expert Systems with Applications, vol. 257, p. 125080, Dec. 2024. [Online]. Available: https://doi.org/10.1016/j.eswa.2024.125080
[13] H. Sun and P. Chen, “Application of neural networks in automotive engine misfire,” in 2024 IEEE 4th International Conference on Electronic Communications, Internet of Things and Big Data (ICEIB). IEEE, Apr. 2024, pp. 261–264. [Online]. Available: https://doi.org/10.1109/ICEIB61477.2024.10602668
[14] M. Abboush, D. Bamal, C. Knieke, and A. Rausch, “Intelligent fault detection and classification based on hybrid deep learning methods for hardware-in-the-loop test of automotive software systems,” Sensors, vol. 22, no. 11, p. 4066, May 2022. [Online]. Available: https://doi.org/10.3390/s22114066
[15] S.-C. Lin, S.-F. Su, and Y. Huang, “A time-frequency signal-based convolutional neural network algorithm for fault diagnosis of gasoline engine fuel control system,” in 2019 International Conference on System Science and Engineering (ICSSE). IEEE, Jul. 2019, pp. 81–87. [Online]. Available: https://doi.org/10.1109/ICSSE.2019.8823285
[16] A. Maged and M. Nour, “Prediction of combustion pressure with deep learning using flame images,” Fuel, vol. 380, p. 133203, Jan. 2025. [Online]. Available: https://doi.org/10.1016/j.fuel.2024.133203
[17] Z. Li, Z. Qin, W. Luo, and X. Ling, “Gasoline engine misfire fault diagnosis method based on improved YOLOv8,” Electronics, vol. 13, no. 14, p. 2688, Jul. 2024. [Online]. Available: https://doi.org/10.3390/electronics13142688
[18] Y. Liu, J. Kang, L. Wen, Y. Bai, and C. Guo, “Health status assessment of diesel engine valve clearance based on BFA-BOAVMD adaptive noise reduction and multichannel information fusion,” Sensors, vol. 22, no. 21, p. 8129, Oct. 2022. [Online]. Available: https://doi.org/10.3390/s22218129
[19] W. R. Contreras Urgilés, J. Maldonado Ortega, and R. León Japa, “Aplicación de una red neuronal feed-forward backpropagation para el diagnóstico de fallas mecánicas en motores de encendido provocado,” Ingenius, no. 21, pp. 32–40, Dec. 2018. [Online]. Available: https://doi.org/10.17163/ings.n21.2019.03
[20] MathWorks. (2025) Redes neuronales convolucionales. The MathWorks, Inc. [Online]. Available: https://upsalesiana.ec/ing35ar7r20