Evaluating performances of 1-D models to predict variable area supersonic gas ejector performances
Само за регистроване кориснике
2018
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
The application of supersonic gas ejector with variable area nozzle can be found in different industries. However, due to different types of variable area nozzle, performance prediction is mainly focused on costly numerical simulations. In this paper, one-dimensional models for performance prediction of variable area gas ejector with specially designed nozzle, were compared. Additionally, operational lines and corresponding modes were analyzed. Two different variable area ejectors were experimentally tested. The first ejector used natural gas as motive fluid, whereas in the second one motive gas was the composition of alkane. Six distinct correlations of ejector component efficiencies were evaluated. Sum of absolute relative errors and coefficient of determination were used as goodness of fit criteria. The results showed that best model has coefficient of determination 0.76 and 0.63 in the case of natural and R2 gas as motive fluids, respectively. In order to improve prediction perform...ances of entrainment ratio, the mixture of experts machine learning technique was used. Moreover, the results of obtained conditional probabilities of models are visualized in space spanned by area and pressure ratios. The presented analysis showed that one model is not generally better than others and can be improved by using an ensemble of models.
Кључне речи:
Variable area nozzle / Supersonic gas ejector / Mixture of experts / Experimental study / Antlion algorithmИзвор:
Energy, 2018, 163, 270-289Издавач:
- Pergamon-Elsevier Science Ltd, Oxford
Финансирање / пројекти:
- Интегритет опреме под притиском при истовременом деловању замарајућег оптерећења и температуре (RS-MESTD-Technological Development (TD or TR)-35011)
DOI: 10.1016/j.energy.2018.08.115
ISSN: 0360-5442
WoS: 000448097800022
Scopus: 2-s2.0-85053186936
Колекције
Институција/група
Mašinski fakultetTY - JOUR AU - Petrović, Andrija AU - Jovanović, Miloš Z. AU - Genić, Srbislav AU - Bugarić, Uglješa AU - Delibasić, Boris PY - 2018 UR - https://machinery.mas.bg.ac.rs/handle/123456789/2903 AB - The application of supersonic gas ejector with variable area nozzle can be found in different industries. However, due to different types of variable area nozzle, performance prediction is mainly focused on costly numerical simulations. In this paper, one-dimensional models for performance prediction of variable area gas ejector with specially designed nozzle, were compared. Additionally, operational lines and corresponding modes were analyzed. Two different variable area ejectors were experimentally tested. The first ejector used natural gas as motive fluid, whereas in the second one motive gas was the composition of alkane. Six distinct correlations of ejector component efficiencies were evaluated. Sum of absolute relative errors and coefficient of determination were used as goodness of fit criteria. The results showed that best model has coefficient of determination 0.76 and 0.63 in the case of natural and R2 gas as motive fluids, respectively. In order to improve prediction performances of entrainment ratio, the mixture of experts machine learning technique was used. Moreover, the results of obtained conditional probabilities of models are visualized in space spanned by area and pressure ratios. The presented analysis showed that one model is not generally better than others and can be improved by using an ensemble of models. PB - Pergamon-Elsevier Science Ltd, Oxford T2 - Energy T1 - Evaluating performances of 1-D models to predict variable area supersonic gas ejector performances EP - 289 SP - 270 VL - 163 DO - 10.1016/j.energy.2018.08.115 ER -
@article{ author = "Petrović, Andrija and Jovanović, Miloš Z. and Genić, Srbislav and Bugarić, Uglješa and Delibasić, Boris", year = "2018", abstract = "The application of supersonic gas ejector with variable area nozzle can be found in different industries. However, due to different types of variable area nozzle, performance prediction is mainly focused on costly numerical simulations. In this paper, one-dimensional models for performance prediction of variable area gas ejector with specially designed nozzle, were compared. Additionally, operational lines and corresponding modes were analyzed. Two different variable area ejectors were experimentally tested. The first ejector used natural gas as motive fluid, whereas in the second one motive gas was the composition of alkane. Six distinct correlations of ejector component efficiencies were evaluated. Sum of absolute relative errors and coefficient of determination were used as goodness of fit criteria. The results showed that best model has coefficient of determination 0.76 and 0.63 in the case of natural and R2 gas as motive fluids, respectively. In order to improve prediction performances of entrainment ratio, the mixture of experts machine learning technique was used. Moreover, the results of obtained conditional probabilities of models are visualized in space spanned by area and pressure ratios. The presented analysis showed that one model is not generally better than others and can be improved by using an ensemble of models.", publisher = "Pergamon-Elsevier Science Ltd, Oxford", journal = "Energy", title = "Evaluating performances of 1-D models to predict variable area supersonic gas ejector performances", pages = "289-270", volume = "163", doi = "10.1016/j.energy.2018.08.115" }
Petrović, A., Jovanović, M. Z., Genić, S., Bugarić, U.,& Delibasić, B.. (2018). Evaluating performances of 1-D models to predict variable area supersonic gas ejector performances. in Energy Pergamon-Elsevier Science Ltd, Oxford., 163, 270-289. https://doi.org/10.1016/j.energy.2018.08.115
Petrović A, Jovanović MZ, Genić S, Bugarić U, Delibasić B. Evaluating performances of 1-D models to predict variable area supersonic gas ejector performances. in Energy. 2018;163:270-289. doi:10.1016/j.energy.2018.08.115 .
Petrović, Andrija, Jovanović, Miloš Z., Genić, Srbislav, Bugarić, Uglješa, Delibasić, Boris, "Evaluating performances of 1-D models to predict variable area supersonic gas ejector performances" in Energy, 163 (2018):270-289, https://doi.org/10.1016/j.energy.2018.08.115 . .