AI-based data mining approach to control the environmental impact of conventional energy technologies
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27650%2F24%3A10255342" target="_blank" >RIV/61989100:27650/24:10255342 - isvavai.cz</a>
Result on the web
<a href="https://www.sciencedirect.com/science/article/pii/S0959652624029226" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0959652624029226</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/j.jclepro.2024.143473" target="_blank" >10.1016/j.jclepro.2024.143473</a>
Alternative languages
Result language
angličtina
Original language name
AI-based data mining approach to control the environmental impact of conventional energy technologies
Original language description
Environmental pollution remains one of the foremost existential threats to human well-being, despite the concerted efforts and implementation of various programmes aimed at fostering cleaner air. The contemporary global economic and energy landscape, characterised by multifaceted challenges, has undeniably hindered the efficacy of efforts to kerb air pollutant emissions. Solid fuels persist as primary sources of energy production in numerous countries, serving both the residential and industrial sectors. However, combustion of such fuels, particularly within domestic heating units (DHUs), engenders the release of a diverse array of organic compounds characterised by intricate structures and potent mutagenic and environmentally hazardous properties. However, the combustion process, if properly regulated, can be carried out in an environmentally sustainable manner. The intricate interplay of myriad factors that influence the composition and quality of chimney flue gases underscores the complexity inherent in controlling the combustion process. Artificial intelligence (AI) has emerged as a versatile tool with applications that span various domains, including environmental monitoring systems. In this study, we posit the utilisation of artificial neural networks (ANNs) as a sophisticated data mining technique to control the emission of flue gases contingent on the specific boiler and fuel utilised. Feed forward predictive models with back propagation were utilized for AI-based data mining aiming at the prediction of the concentration of flue gas components. The highest coefficients of model fit goodness were obtained for CO2, NOx and SO2 with R2 equal to 0.99, 0.98 and 0.99, respectively. The study demonstrated the feasibility and effectiveness of using AI-based data mining to predict emissions from conventional energy technologies. By leveraging the predictive capabilities of ANNs, it is possible to significantly reduce the environmental impact of solid fuel combustion, contributing to cleaner air and improved public health.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
20704 - Energy and fuels
Result continuities
Project
<a href="/en/project/EF18_069%2F0010049" target="_blank" >EF18_069/0010049: Research on the identification of combustion of unsuitable fuels and systems of self-diagnostics of boilers combusting solid fuels for domestic heating</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Journal of Cleaner Production
ISSN
0959-6526
e-ISSN
1879-1786
Volume of the periodical
472
Issue of the periodical within the volume
Neuveden
Country of publishing house
GB - UNITED KINGDOM
Number of pages
10
Pages from-to
"nestrankovano"
UT code for WoS article
001304104700001
EID of the result in the Scopus database
2-s2.0-85202353150