Random forest model for determination of the lower heating value of TPP “Kolubara A” coal
Authorized Users Only
2023
Authors
Milićević, AleksandarBelošević, Srđan
Erić, Milić
Marković, Zoran
Tomanović, Ivan
Crnomarković, Nenad
Stojanović, Andrijana
Conference object (Published version)
Metadata
Show full item recordAbstract
Heating value is an important indicator for assessment of the coal quality. Machine learning models are powerful computational tools that allow for the analysis of various heat and mass transfer phenomena in energy systems. In this paper, Random forest model for determining the lower heating values of coal from the thermal power plant “Kolubara A” is developed based on proximate and ultimate fuel analysis. A database of the proximate and ultimate fuel analysis values and lower heating value of coal was created by experimental measurements in the accredited test laboratory of the Department of Thermal Engineering and Energy (“VINČA” Institute of Nuclear Sciences). The developed Random forest models, applied to a relatively small database, showed acceptable predictions for the lower heating value based on both the proximate analysis (RMSE = 0.22 MJ/kg and MAPE = 2.26%) and the ultimate analysis (RMSE = 0.64 MJ/kg and MAPE = 6.12%), with better accuracy achieved by the model whose input d...ata consisted of the values of technical fuel analysis.
Keywords:
machine learning / Random forest / coal / heating value / thermal power plantSource:
International Conference Power Plants 2023 : Proceedings, 2023, 748-752Publisher:
- Belgrade : Society of Thermal Engineers of Serbia
Funding / projects:
- Ministry of Science, Technological Development and Innovation of the Republic of Serbia, institutional funding - 200017 (University of Belgrade, Institute of Nuclear Sciences 'Vinča', Belgrade-Vinča) (RS-MESTD-inst-2020-200017)
- United Nations Development Programme [Ref.: 00123168/01-04]
Note:
- Power Plants 2023 : Elektrane 2023; November 8-10, 2023, Zlatibor, Serbia
Collections
Institution/Community
VinčaTY - CONF AU - Milićević, Aleksandar AU - Belošević, Srđan AU - Erić, Milić AU - Marković, Zoran AU - Tomanović, Ivan AU - Crnomarković, Nenad AU - Stojanović, Andrijana PY - 2023 UR - https://vinar.vin.bg.ac.rs/handle/123456789/12766 AB - Heating value is an important indicator for assessment of the coal quality. Machine learning models are powerful computational tools that allow for the analysis of various heat and mass transfer phenomena in energy systems. In this paper, Random forest model for determining the lower heating values of coal from the thermal power plant “Kolubara A” is developed based on proximate and ultimate fuel analysis. A database of the proximate and ultimate fuel analysis values and lower heating value of coal was created by experimental measurements in the accredited test laboratory of the Department of Thermal Engineering and Energy (“VINČA” Institute of Nuclear Sciences). The developed Random forest models, applied to a relatively small database, showed acceptable predictions for the lower heating value based on both the proximate analysis (RMSE = 0.22 MJ/kg and MAPE = 2.26%) and the ultimate analysis (RMSE = 0.64 MJ/kg and MAPE = 6.12%), with better accuracy achieved by the model whose input data consisted of the values of technical fuel analysis. PB - Belgrade : Society of Thermal Engineers of Serbia C3 - International Conference Power Plants 2023 : Proceedings T1 - Random forest model for determination of the lower heating value of TPP “Kolubara A” coal SP - 748 EP - 752 UR - https://hdl.handle.net/21.15107/rcub_vinar_12766 ER -
@conference{ author = "Milićević, Aleksandar and Belošević, Srđan and Erić, Milić and Marković, Zoran and Tomanović, Ivan and Crnomarković, Nenad and Stojanović, Andrijana", year = "2023", abstract = "Heating value is an important indicator for assessment of the coal quality. Machine learning models are powerful computational tools that allow for the analysis of various heat and mass transfer phenomena in energy systems. In this paper, Random forest model for determining the lower heating values of coal from the thermal power plant “Kolubara A” is developed based on proximate and ultimate fuel analysis. A database of the proximate and ultimate fuel analysis values and lower heating value of coal was created by experimental measurements in the accredited test laboratory of the Department of Thermal Engineering and Energy (“VINČA” Institute of Nuclear Sciences). The developed Random forest models, applied to a relatively small database, showed acceptable predictions for the lower heating value based on both the proximate analysis (RMSE = 0.22 MJ/kg and MAPE = 2.26%) and the ultimate analysis (RMSE = 0.64 MJ/kg and MAPE = 6.12%), with better accuracy achieved by the model whose input data consisted of the values of technical fuel analysis.", publisher = "Belgrade : Society of Thermal Engineers of Serbia", journal = "International Conference Power Plants 2023 : Proceedings", title = "Random forest model for determination of the lower heating value of TPP “Kolubara A” coal", pages = "748-752", url = "https://hdl.handle.net/21.15107/rcub_vinar_12766" }
Milićević, A., Belošević, S., Erić, M., Marković, Z., Tomanović, I., Crnomarković, N.,& Stojanović, A.. (2023). Random forest model for determination of the lower heating value of TPP “Kolubara A” coal. in International Conference Power Plants 2023 : Proceedings Belgrade : Society of Thermal Engineers of Serbia., 748-752. https://hdl.handle.net/21.15107/rcub_vinar_12766
Milićević A, Belošević S, Erić M, Marković Z, Tomanović I, Crnomarković N, Stojanović A. Random forest model for determination of the lower heating value of TPP “Kolubara A” coal. in International Conference Power Plants 2023 : Proceedings. 2023;:748-752. https://hdl.handle.net/21.15107/rcub_vinar_12766 .
Milićević, Aleksandar, Belošević, Srđan, Erić, Milić, Marković, Zoran, Tomanović, Ivan, Crnomarković, Nenad, Stojanović, Andrijana, "Random forest model for determination of the lower heating value of TPP “Kolubara A” coal" in International Conference Power Plants 2023 : Proceedings (2023):748-752, https://hdl.handle.net/21.15107/rcub_vinar_12766 .