Prediction of air pollution from power generation using machine learning
-
Published:2024-01-31
Issue:1
Volume:
Page:27-35
-
ISSN:2461-4262
-
Container-title:EUREKA: Physics and Engineering
-
language:
-
Short-container-title:Eureka: PE
Author:
Photsathian ThongchaiORCID, Suttikul ThitipornORCID, Tangsrirat WorapongORCID
Abstract
Electrical energy is now widely recognized as an essential part of life for humans, as it powers many daily amenities and devices that people cannot function without. Examples of these include traffic signals, medical equipment in hospitals, electrical appliances used in homes and offices, and public transportation. The process that generates electricity can pollute the air. Even though natural gas used in power plants is derived from fossil fuels, it can nevertheless produce air pollutants involving particulate matter (PM), nitrogen oxides (NOx), and carbon monoxide (CO), which affect human health and cause environmental problems. Numerous researchers have devoted significant efforts to developing methods that not only facilitate the monitoring of current air quality but also possess the capability to predict the impacts of this increasing rise. The primary cause of air pollution issues associated with electricity generation is the combustion of fossil fuels. The objective of this study was to create three multiple linear regression models using artificial intelligence (AI) technology and data collected from sensors positioned around the energy generator. The objective was to precisely predict the amount of air pollution that electricity generation would produce. The highly accurate forecasted data proved valuable in determining operational parameters that resulted in minimal air pollution emissions. The predicted values were accurate with the mean squared error (MSE) of 0.008, the mean absolute error (MAE) of 0.071, and the mean absolute percentage error (MAPE) of 0.006 for the turbine energy yield (TEY). For the CO, the MSE was 2.029, the MAE was 0.791, and the MAPE was 0.934. For the NOx, the MSE was 69.479, the MAE was 6.148, and the MAPE was 0.096. The results demonstrate that the models developed have a high level of accuracy in identifying operational conditions that result in minimal air pollution emissions, with the exception of NOx. The accuracy of the NOx model is relatively lower, but it may still be used to estimate the pattern of NOx emissions
Publisher
OU Scientific Route
Subject
General Physics and Astronomy,General Engineering
Reference15 articles.
1. Lamarque, J.-F., Bond, T. C., Eyring, V., Granier, C., Heil, A., Klimont, Z. et al. (2010). Historical (1850–2000) gridded anthropogenic and biomass burning emissions of reactive gases and aerosols: methodology and application. Atmospheric Chemistry and Physics, 10 (15), 7017–7039. https://doi.org/10.5194/acp-10-7017-2010 2. Amann, M., Kiesewetter, G., Schöpp, W., Klimont, Z., Winiwarter, W., Cofala, J. et al. (2020). Reducing global air pollution: the scope for further policy interventions. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 378 (2183), 20190331. https://doi.org/10.1098/rsta.2019.0331 3. Balali-Mood, M., Ghorani-Azam, A., Riahi-Zanjani, B. (2016). Effects of air pollution on human health and practical measures for prevention in Iran. Journal of Research in Medical Sciences, 21 (1), 65. https://doi.org/10.4103/1735-1995.189646 4. Larki, I., Zahedi, A., Asadi, M., Forootan, M. M., Farajollahi, M., Ahmadi, R., Ahmadi, A. (2023). Mitigation approaches and techniques for combustion power plants flue gas emissions: A comprehensive review. Science of The Total Environment, 903, 166108. https://doi.org/10.1016/j.scitotenv.2023.166108 5. Okafor, E. C., Somarathne, K. D. K. A., Ratthanan, R., Hayakawa, A., Kudo, T., Kurata, O. et al. (2020). Control of NOx and other emissions in micro gas turbine combustors fuelled with mixtures of methane and ammonia. Combustion and Flame, 211, 406–416. https://doi.org/10.1016/j.combustflame.2019.10.012
|
|