Abstract
Ejectors are implemented in energy conservation applications such as power and refrigeration systems and fuel cell stacks due to their passive nature and geometrical simplicity. Ejectors work on the principle of thermal compression that utilizes low-grade energy to produce a compression effect. A low-enthalpy secondary fluid gets compressed through gasdynamic interactions with a co-flowing high-enthalpy primary flow in ejectors. The aerodynamic choking of the secondary flow within an ejector leads to two modes of ejector operation: (a) critical flow regime and (b) mixed flow regime. Several low-fidelity models for analyzing ejectors have been proposed in the literature. These models are adequate for the rapid design of specific categories of ejectors. However, they yield notable deviations of 20-25% with experimental measurements for different operating conditions. On the other hand, computational fluid dynamics (CFD) simulations for ejectors are computationally expensive. Furthermore, they require a careful selection of numerical solvers and turbulence models to predict performance and flow characteristics accurately. This paper presents a data-driven artificial neural network (ANN) model to predict the critical parameters of supersonic ejectors. The model is trained using experimental measurement for air ejectors at various operating and geometrical parameters. The ANN model consists of five input parameters, representing operating and geometrical parameters of ejectors to estimate two output parameters: (a) entrainment ratio and (b) operating regime. The trained ANN model predicts the entrainment ratio with a maximum deviation of about 7% and classifies the ejector operational mode with an accuracy of 100%.
Similar content being viewed by others
Abbreviations
- A:
-
Area (m\( ^{2} \))
- \( C_{d} \) :
-
Discharge coefficient
- \( \gamma \) :
-
Specific heat ratio
- L/H:
-
Mixing duct length to height ratio
- \( \dot{m} \) :
-
mass flow rate (kg/s)
- \( \mu \) :
-
Mean
- \( P_{o} \) :
-
Stagnation pressure
- R:
-
Characteristics gas constant (8314 J/kg K)
- \( \sigma \) :
-
Standard deviation
- \( T_{o} \) :
-
Stagnation temperature
- W:
-
Weight associated with neurons in ANN
- ANN:
-
Artificial neural network
- AR:
-
Area ratio
- CF:
-
Confusion matrix
- CFD:
-
Computational fluid dynamics
- CR:
-
compression ratio
- ER:
-
Entrainment ratio
- MDL:
-
Mixing duct length
- NAR:
-
Nozzle area ratio
- OR:
-
Operating regime
- ReLU:
-
Rectified linear unit
- RMSE:
-
Root mean square error
- SPR:
-
Stagnation pressure ratio
- e:
-
Exit flow
- p:
-
Primary flow
- s:
-
Secondary flow
References
Kumar AR and Gopalapillai R 2018 Physics of vacuum generation in zero-secondary flow ejectors. Physics of Fluids, 30(6): 066102
Besagni G, Mereu R and Inzoli F 2016 Ejector refrigeration: A comprehensive review. Renewable and Sustainable Energy Reviews, 53: 373–407
Padilla R V, Too Y C S, Benito R, McNaughton R and Stein W 2016 Thermodynamic feasibility of alternative supercritical CO\(_{2}\) brayton cycles integrated with an ejector. Applied energy, 169: 49–62
Rao S M V and Jagadeesh G 2010 Vector evaluated particle swarm optimization (VEPSO) of supersonic ejector for hydrogen fuel cells. Journal of Fuel Cell Science and Technology, 7(4)
Alperin M and Wu J J 1983 Thrust augmenting ejectors, Part I. AIAA J., 21(10): 1428–1436
Shi L, Zhao G, Yang Y, Gao D, Qin F, Wei X and He G 2019 Research progress on ejector mode of rocket-based combined-cycle engines. Progress in Aerospace Sciences, 107: 30–62
Lord W, Jones C, Stern A and Krejsa V, Headand E 1990 Mixer-ejector nozzle for jet noise suppression. In: 26th Joint Propulsion Conference, page 1909
Rao S M V and Jagadees G 2009 Aerodynamic design of supersonic ejectors for wind tunnel applications. In: National Conference on Wind Tunnel Testing, 2: 6
Kracík J, Dvořák V, and Kolář J 2014 Development of air to air ejector for supersonic wind tunnel. In: EPJ Web of Conferences, volume 67, page 02059. EDP Sciences
Gupta P, Rao SMV and Kumar P 2019 Experimental investigations on mixing characteristics in the critical regime of a low-area ratio supersonic ejector. Physics of Fluids, 31(2): 026101
Karthick S K, Rao S M V, Jagadeesh G and Reddy K P J 2018 Experimental parametric studies on the performance and mixing characteristics of a low area ratio rectangular supersonic gaseous ejector by varying the secondary flow rate. Energy, 161: 832–845
Kumar K, Gupta H K and Kumar P 2020 Analysis of a hybrid transcritical co2 vapor compression and vapor ejector refrigeration system.Applied Thermal Engineering, 181: 115945
Chunnanond K, Satha S and Aphornratana 2004 An experimental investigation of a steam ejector refrigerator: the analysis of the pressure profile along the ejector. Appl. Therm. Eng., 24(2-3): 311–322
Keenan J H and Neumann E P 1942 A simple air ejector Journal of Applied Mechanics, 64: 75–84
Keenan J H, Neumann E P and Lustwerk F 1950 An investigation of ejector design by analysis and experiment.J. Appl. Mech., pages 299–317: 1950
Fabri J and Siestrunck R 1958 Supersonic air ejectors. Advances in applied mechanics, 5: pp.1-34
Huang B J, Chang J M, Wang C P and Petrenko V A 1999 A 1-D analysis of ejector performance. International Journal of Refrigeration, 22(5): 354–364
Lamberts O, Chatelain P and Bartosiewicz Y 2018 Numerical and experimental evidence of the fabri-choking in a supersonic ejector. International Journal of Heat and Fluid Flow, 69: 194–209
Gupta P, Kumar P and Rao S M V 2022 newblock Artificial neural network model for single-phase real gas ejectors. Applied Thermal Engineering, 201: 117615
Gupta P, Kumar P and Rao S M V Artificial neural network based shape optimization of supersonic ejectors in the critical flow regime.Available at SSRN 4054176.
Chen W, Chong D, Yan J and Liu J 2013 The numerical analysis of the effect of geometrical factors on natural gas ejector performance. Applied Thermal Engineering, 59(1-2): 21–29
Varga S, Oliveira A C, and Diaconu B 2009 Influence of geometrical factors on steam ejector performance–A numerical assessment. Int. J. Refrig., 32(7): 1694–1701
Gupta P, Rao S M V and Kumar P 2019 Effect of mixing duct geometry of supersonic ejector in the critical flow regime. In: Proceedings of the 32nd International Symposium of Shock Wave July 14–19, NUS Singapore, Singapore
Hemidi A, Henry F, Leclaire S, Seynhaeve J M, and Bartosiewicz Y 2009 CFD analysis of a supersonic air ejector. Part I: Experimental validation of single-phase and two-phase operation. Appl. Therm. Eng., 29(8-9): 1523–1531
Bartosiewicz Y, Aidoun Z, Desevaux P and Mercadier Y 2005 Numerical and experimental investigations on supersonic ejectors.International Journal of Heat and Fluid Flow, 26(1): 56–70
Gupta P, Rao S M V and Kumar P 2021 Numerical studies of a supersonic air ejector using large eddy simulation. In: Proceedings of the 26thNational and 4th International ISHMT-ASTFE Heat and Mass Transfer Conference December 17–20, 2021, IIT Madras, Chennai-600036, Tamil Nadu, India. Begel House Inc., 2021
Croquer S, Lamberts O, Poncet S, Moreau S and Bartosiewicz Y 2022 Large eddy simulation of a supersonic air ejector. Appl. Therm. Eng., 209: 118177
Bouhanguel A, Desevaux P and Gavignet E 2015 Visualization of flow instabilities in supersonic ejectors using Large Eddy Simulation. J. Vis., 18(1): 17–19
Sözen A and Akçayol M A 2004 Modelling (using artificial neural networks) the performance parameters of a solar-driven ejector-absorption cycle. Appl. Energy, 79(3):309–325, 2004
Kalogirou S A 2001 Artificial neural networks in renewable energy systems applications: A review. Renew. Sustain. Energy Rev., 5(4): 373–401
Sözen A, Arcakliolu E and Özalp M 2003 A new approach to thermodynamic analysis of ejector–absorption cycle: Artificial Neural Networks. Appl. Therm. Eng., 23(8): 937–952
Rashidi M M and Raoofi A, Aghagoliand R 2017 Thermodynamic analysis of the ejector refrigeration cycle using the artificial neural network. Energy, 129: 201–215
Haoran C and Wenjian C 2014 Artificial neural network modeling for variable area ratio ejector. In: 2014 9th IEEE Conference on Industrial Electronics and Applications, pages 220–225. IEEE
Rusly E, Aye L, Charters W W S and Ooi A 2005 CFD analysis of ejector in a combined ejector cooling system. Int. J. Refrig., 28(7): 1092–1101
Lee M S, Lee H, Hwang Y, Radermacher R, and Jeong HM 2016 Optimization of two-phase r600a ejector geometries using a non-equilibrium cfd model. Appl. Therm. Eng., 109: 272–282
Chollet E 2021 Deep learning with Python. Simon and Schuster
Brownlee J 2016 Deep learning with Python: develop deep learning models on Theano and TensorFlow using Keras. Machine Learning Mastery
Al-Masri A 2019 How does back-propagation in Artificial Neural Networks work. Towards Data Science
Acknowledgements
The authors acknowledge the funding received from IISc Startup Grant, and DST for the Project.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Gupta, P., Rao, S.M.V. & Kumar, P. Performance evaluation of air ejectors using artificial neural network approach. Sādhanā 48, 45 (2023). https://doi.org/10.1007/s12046-023-02087-2
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12046-023-02087-2