Noise and Oil Viscosity Characterization and Modelling for Petrol-Gas-Converted Generator
Abstract
The modification of petrol generators to operate on dual-fuel systems such as petrol-gas offers advantages in fuel efficiency and emission reduction, but it also introduces new challenges in maintenance, particularly in noise behavior and oil degradation. This study presents a comprehensive characterization and modelling of noise levels and oil viscosity in a petrol-gas-converted generator under various load conditions and operational durations. Experimental data were collected using a digital sound level meter and a Brookfield viscometer at intervals over a 60-hour runtime. An Artificial Neural Network (ANN) model was developed in MATLAB using a feedforward backpropagation architecture with a 70:15:15 training-validation-testing split. The ANN model achieved high predictive accuracy, with R² values of 0.9 for prediction of for oil viscosity based on noise level. The results demonstrate that ANN-based modelling provides a reliable approach for forecasting the operational variables on petrol-gen-converted generators. These findings offer a valuable tool for predictive maintenance and performance optimization in hybrid-fuel power systems.
References
Abdallah, T. (2017). Sustainable Initiatives for Public Bus Networks. Sustainable Mass Transit, 79–93. https://doi.org/10.1016/B978-0-12-811299-1.00006-X
Bertinatto, R., Friedrich, L., Bariccatti, R., Souza, S., Gurgacz, F., & Pazuch, F. (2017). Analysis of lubricant oil contamination and degradation and wear of a biogas-fed otto cycle engine. Acta Scientiarum. Technology, 39, 409. https://doi.org/10.4025/actascitechnol.v39i4.29458
Emagbetere, E., Uwatse, S. & Okoidigun, O. G., 2025. Artificial Neural Network for the Clustering of Vibration Signals for Condition Monitoring of Rotating Machines. ABUAD Journal of Engineering Research and Development, 8(1), pp. 1-13.
Ershad, M. (2025). Literature Review and Prospects for Grey-Box Models and PINN in Powertrain Technology. https://doi.org/10.13140/RG.2.2.34632.64008
Garcia Tobar, M., Pinta Pesantez, K., Jimenez Romero, P., & Contreras Urgiles, R. W. (2025). The Impact of Oil Viscosity and Fuel Quality on Internal Combustion Engine Performance and Emissions: An Experimental Approach. In Lubricants (Vol. 13, Issue 4). https://doi.org/10.3390/lubricants13040188
Islam Sazzad, M. R., Rahman, M. M., Hassan, T., Al Rifat, A., Al Mamun, A., Adib, A. R., Meraz, R. M., & Ahmed, M. (2024). Advancing sustainable lubricating oil management: Re-refining techniques, market insights, innovative enhancements, and conversion to fuel. Heliyon, 10(20), e39248. https://doi.org/10.1016/J.HELIYON.2024.E39248
Katopodis, T., & Sfetsos, T. (2019). A Review of Climate Change Impacts to Oil Sector Critical Services and Suggested Recommendations for Industry Uptake. Infrastructures, 4, 74. https://doi.org/10.3390/infrastructures4040074
Kpang, M., & Chukwudi, D. (2021). Monitoring noise level in cities: A step towards urban environmental quality management in Nigeria. World Journal of Advanced Research and Reviews, 10, 348–357. https://doi.org/10.30574/wjarr.2021.10.3.0194
Laguado-Ramírez, R., Hernandez-Villamizar, F., & Duarte-Forero, J. (2024). Comparative assessment of emissions, performance, and economics parameters for a dual-fuel diesel generator operating with rice bran biodiesel and hydrogen. Heliyon, 10(11), e32109. https://doi.org/10.1016/j.heliyon.2024.e32109
Loutas, T., Roulias, D., Pauly, E., & Kostopoulos, V. (2011). The combined use of vibration, acoustic emission and oil debris on-line monitoring towards a more effective condition monitoring of rotating machinery. Mechanical Systems and Signal Processing, 25, 1339–1352. https://doi.org/10.1016/j.ymssp.2010.11.007
Madhiarasan, M. & Louzazni, M., 2022. Analysis of Artificial Neural Network: Architecture, Types, and Forecasting Applications. Journal of Electrical and Computer Engineering, 2022(416722), pp. 1-23.
Mateen, S., Haque, A., Khan, M. A., & Ebel, T. (2025). Unveiling cutting-edge innovations toward green vehicle technology. Energy Reports, 13, 3402–3417. https://doi.org/https://doi.org/10.1016/j.egyr.2025.02.038
Mehrnoosh, D., Asghar, H. A., & Asghar, M. A. (2012). Thermodynamic model for prediction of performance and emission characteristics of SI engine fuelled by gasoline and natural gas with experimental verification. Journal of Mechanical Science and Technology, 26, 2213–2225. https://api.semanticscholar.org/CorpusID:255538573
Nwabueze, O. D., Chijioke, O. V., & Blessed, N. S. (2024). Assessment of Noise Pollution from Petrol Generators in Nigeria: An Analysis of Distance, Capacity and Age Variables. Journal of Engineering Research and Reports, 26(12 SE-Original Research Article), 1–10. https://doi.org/10.9734/jerr/2024/v26i121335
Odufuwa, O. Y., Tartibu, L. K., & Kusakana, K. (2025). Artificial neural network modelling for predicting efficiency and emissions in mini-diesel engines: Key performance indicators and environmental impact analysis. Fuel, 387, 134294. https://doi.org/10.1016/J.FUEL.2025.134294
Feenita, S, P., C., Goel, U., T, M., Duraisamy, B., Subramanian, B., Ganeshan, K., Josephin, F., Albeshr, M., Pugazhendhi, A., & Varuvel, E. (2024). Comparative analysis of regression models to predict the performance of the dual fuel engine operating on diesel and hydrogen gas. International Journal of Hydrogen Energy. https://doi.org/10.1016/j.ijhydene.2024.12.238
Wan Osman, W. N. A., Rosli, M. H., Mazli, W. N. A., & Samsuri, S. (2024). Comparative review of biodiesel production and purification. Carbon Capture Science & Technology, 13, 100264. https://doi.org/https://doi.org/10.1016/j.ccst.2024.100264
Yang, R., Yan, Y., Sun, X., Wang, Q., Zhang, Y., Jiahong, F., & Liu, Z. (2022). An Artificial Neural Network Model to Predict Efficiency and Emissions of a Gasoline Engine. Processes, 10, 204. https://doi.org/10.3390/pr10020204
Zhu, S., Cheng, J., Qiao, Z., & Yang, J. (2019). High temperature solid-lubricating materials: A review. Tribology International, 133, 206–223. https://doi.org/10.1016/j.triboint.2018.12.037
