Skip to main content

Advertisement

SpringerLink
Log in

Machine learning for optimal flow control in an axial compressor

  • Regular Article - Flowing Matter
  • Published:
The European Physical Journal E Aims and scope Submit manuscript

Abstract

Air jets for active flow control have proved effective in postponing the onset of stall phenomenon in axial compressors. In this paper, we use a combination of machine learning and genetic algorithm to explore the optimal parameters of air jets to control rotating stall in the axial compressor CME2. Three control parameters are investigated: the absolute injection angle, the number of injector pairs and the injection velocity. Given an experimental dataset, the influence of the air jet parameters on the surge margin improvement and power balance is modeled using two shallow neural networks. Parameters of the air jets are then optimized using a genetic algorithm for three rotational velocities, i.e., \(\Omega = 3200\,\textrm{RPM}, 4500\,\textrm{RPM} \,\textrm{and}\, 6000\,\textrm{RPM}\). First, surge margin improvement and power balance are being maximized independently. Then, a bi-objective optimization problem is posed to explore the trade-off between the two competing objectives. Based on the Pareto front, results suggest that a globally optimal set of parameters is obtained for a velocity ratio (defined as the ratio of the injection velocity to the rotor tip speed) ranging from 1.1 to 1.6 and an injection angle attack varying from \(1^\circ \textrm{to} 11^\circ \). These outcomes point out a potential generalization of the control strategy applicable to other compressors.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Data availability Statement

The data that support the findings of this study are available from the corresponding author upon reasonable request.

References

  1. C. Tan, I. Day, S. Morris, A. Wadia, Spike-type compressor stall inception, detection, and control. Annu. Rev. Fluid Mech. 42, 275–300 (2010)

    Article  ADS  Google Scholar 

  2. M.D Hathaway, Passive endwall treatments for enhancing stability. Technical report (2007)

  3. G. Margalida, P. Joseph, O. Roussette, A. Dazin, Active flow control in an axial compressor for stability improvement: on the effect of flow control on stall inception. Exp. Fluids 62(1), 1–13 (2021)

    Article  Google Scholar 

  4. J. Moubogha Moubogha, G. Margalida, P. Joseph, O. Roussette, A. Dazin, Stall margin improvement in an axial compressor by continuous and pulsed tip injection. Int. J. Turbomach. Propuls. Power 7(1), 10 (2022)

    Article  Google Scholar 

  5. C. Jang, K. Kim, Optimization of a stator blade using response surface method in a single-stage transonic axial compressor. Proc. Inst. Mech. Eng. Part A: J. Power Energy 219(8), 595–603 (2005)

    Article  Google Scholar 

  6. T.W. Simpson, T.M. Mauery, J.J. Korte, F. Mistree, Kriging models for global approximation in simulation-based multidisciplinary design optimization. AIAA J. 39(12), 2233–2241 (2001)

    Article  ADS  Google Scholar 

  7. T. Mengistu, W. Ghaly, Aerodynamic optimization of turbomachinery blades using evolutionary methods and ann-based surrogate models. Optim. Eng. 9(3), 239–255 (2008)

    Article  MathSciNet  MATH  Google Scholar 

  8. J.A. Nelder, R. Mead, A simplex method for function minimization. Comput. J. 7(4), 308–313 (1965). https://doi.org/10.1093/comjnl/7.4.308

    Article  MathSciNet  MATH  Google Scholar 

  9. T. Bäck, H.-P. Schwefel, An overview of evolutionary algorithms for parameter optimization. Evol. Comput. 1(1), 1–23 (1993)

    Article  Google Scholar 

  10. J. Li, X. Du, Martins, J.R.: Machine learning in aerodynamic shape optimization. arXiv preprint arXiv:2202.07141 (2022)

  11. Z. Liu, I.A. Karimi, Gas turbine performance prediction via machine learning. Energy 192, 116627 (2020)

    Article  Google Scholar 

  12. J. Yu, Z. Wang, F. Chen, J. Yu, C. Wang, Kriging surrogate model applied in the mechanism study of tip leakage flow control in turbine cascade by multiple dbd plasma actuators. Aerosp. Sci. Technol. 85, 216–228 (2019)

    Article  Google Scholar 

  13. Z. Li, X. Zheng, Review of design optimization methods for turbomachinery aerodynamics. Prog. Aerosp. Sci. 93, 1–23 (2017)

    Article  ADS  Google Scholar 

  14. S.L. Brunton, B.R. Noack, Closed-loop turbulence control: progress and challenges. Appl. Mech. Rev. 67(5), 1 (2015). https://doi.org/10.1115/1.4031175

    Article  Google Scholar 

  15. F. Ren, H.-B. Hu, H. Tang, Active flow control using machine learning: a brief review. J. Hydrodyn. 32(2), 247–253 (2020)

    Article  ADS  Google Scholar 

  16. T. Bäck, H.-P. Schwefel, An overview of evolutionary algorithms for parameter optimization. Evol. Comput. 1(1), 1–23 (1993)

    Article  Google Scholar 

  17. A. Debien, K.A.F.F. von Krbek, N. Mazellier, T. Duriez, L. Cordier, B.R. Noack, M.W. Abel, A. Kourta, Closed-loop separation control over a sharp edge ramp using genetic programming. Exp. Fluids 57(3), 40 (2016). https://doi.org/10.1007/s00348-016-2126-8

    Article  Google Scholar 

  18. R. Li, B.R. Noack, L. Cordier, J. Borée, F. Harambat, Drag reduction of a car model by linear genetic programming control. Exp. Fluids 58(8), 103 (2017). https://doi.org/10.1007/s00348-017-2382-2

    Article  Google Scholar 

  19. Z. Wu, D. Fan, Y. Zhou, R. Li, B.R. Noack, Jet mixing enhancement using machine learning control. Experiments in Fluids (Accepted in print), 35 (2018). Springer Verlag (Germany). Accessed 8 Jan 2023

  20. J. Rabault, M. Kuchta, A. Jensen, U. Réglade, N. Cerardi, Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control. J. Fluid Mech. 865, 281–302 (2019)

    Article  ADS  MathSciNet  MATH  Google Scholar 

  21. J. Degrave, F. Felici, J. Buchli, M. Neunert, B. Tracey, F. Carpanese, T. Ewalds, R. Hafner, A. Abdolmaleki, D. de las Casas, C. Donner, L. Fritz, C. Galperti , A. Huber, J. Keeling, M. Tsimpoukelli, J. Kay, A. Merle, J.-M. Moret, S. Noury, F. Pesamosca, D. Pfau, O. Sauter, C. Sommariva, S. Coda, B. Duval, A. Fasoli, P. Kohli, K. Kavukcuoglu, D. Hassabis, M. Riedmiller, Magnetic control of tokamak plasmas through deep reinforcement learning. Nature 602(7897), 414–419 (2022). https://doi.org/10.1038/s41586-021-04301-9. Accessed 2022-05-19

  22. P. Garnier, J. Viquerat, J. Rabault, A. Larcher, A. Kuhnle, E. Hachem, A review on Deep Reinforcement Learning for Fluid Mechanics. arXiv:1908.04127 [physics] (2021)

  23. R. Paris, S. Beneddine, J. Dandois, Robust flow control and optimal sensor placement using deep reinforcement learning. J. Fluid Mech. 913, 25 (2021). https://doi.org/10.1017/jfm.2020.1170

    Article  ADS  MathSciNet  MATH  Google Scholar 

  24. H. Tang, J. Rabault, A. Kuhnle, Y. Wang, T. Wang, Robust active flow control over a range of Reynolds numbers using an artificial neural network trained through deep reinforcement learning. Phys. Fluids 32(5), 053605 (2020). https://doi.org/10.1063/5.0006492

    Article  ADS  Google Scholar 

  25. M. Elhawary, Deep Reinforcement Learning for Active Flow Control around a Circular Cylinder Using Unsteady-mode Plasma Actuators. arXiv preprint arXiv:2012.10165 (2020)

  26. N. Benard, J. Pons-Prats, J. Periaux, G. Bugeda, P. Braud, J. Bonnet, E. Moreau, Turbulent separated shear flow control by surface plasma actuator: Experimental optimization by genetic algorithm approach. Exp. Fluids 57(2), 1–17 (2016)

    Article  Google Scholar 

  27. D. Kamari, M. Tadjfar, A. Madadi, Optimization of sd7003 airfoil performance using tbl and cbl at low reynolds numbers. Aerosp. Sci. Technol. 79, 199–211 (2018)

    Article  Google Scholar 

  28. S.L. Brunton, B.R. Noack, P. Koumoutsakos, Machine learning for fluid mechanics. Annu. Rev. Fluid Mech. 52, 477–508 (2020)

    Article  ADS  MathSciNet  MATH  Google Scholar 

  29. T. Duriez, S.L. Brunton, B.R. Noack, Machine Learning Control - Taming Nonlinear Dynamics And Turbulence. Fluid Mech. Appl. 116, 1. https://doi.org/10.1007/978-3-319-40624-4

  30. M. Veglio, A. Dazin, O. Roussette, G. Bois, Pressure measurements in an axial compressor: from design operating conditions to rotating stall inception. In: 49th Symposium of Applied Aerodynamics (2014)

  31. S.B.-F.K.-J. Raub, R. Niehuis, Ejector tip injection system for active aerodynamic compressor stabilization part ii: Cfd investigations (2017)

  32. A. Dazin, P. Joseph, F. Romano, Q. Gallas, J. Marty, G. Aigouy, M. Stô\(\beta \)el, R. Niehuis, The aconit project: an innovative design approach of active flow control for surge prevention in gas turbines. In: IOP Conference Series: Materials Science and Engineering, vol. 1024, p. 012068 (2021). IOP Publishing

  33. D.P. Kingma, J. Ba, Adam: A Method for Stochastic Optimization. arXiv:1412.6980 [cs] (2017)

  34. S.M. Lim, A.B.M. Sultan, M.N. Sulaiman, A. Mustapha, K.Y. Leong, Crossover and mutation operators of genetic algorithms. Int. J. Mach. Learn. Comput. 7(1), 9–12 (2017)

    Article  Google Scholar 

  35. L.A. Yates, Z. Aandahl, S.A. Richards, B.W. Brook, Cross validation for model selection: a review with examples from ecology. Ecol. Monogr. 1557, 1 (2022)

    Google Scholar 

  36. T. Akiba, S. Sano, T. Yanase, T. Ohta, M. Koyama, Optuna: A next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2623–2631 (2019)

  37. L. Kotthoff, C. Thornton, H.H. Hoos, F. Hutter, K. Leyton-Brown, Auto-weka: Automatic model selection and hyperparameter optimization in weka. Automated machine learning: methods, systems, challenges, 81–95 (2019)

  38. M. Feurer, F. Hutter, Hyperparameter optimization. Automated machine learning: Methods, systems, challenges, 3–33 (2019)

  39. O. El Mokkadem, X. Chen, C. Phan, J. Delva, P. Joseph, A. Dazin, F. Romanò, Small widths wall-attached coandă jets for flow control (2022)

Download references

Author information

Author notes

  1. T.I. : Quantitative AI in Complex Fluids and Complex Flows: Challenges and Benchmarks. Guest editors: Luca Biferale, Michele Buzzicotti, Massimo Cencini.

Authors and Affiliations

  1. Univ. Lille, CNRS, ONERA, Arts et Métiers Institute of Technology, Centrale Lille, UMR 9014, LMFL - Laboratoire de Mécanique des Fluides de Lille - Kampé de Fériet, 59000, Lille, France

    M. A. Elhawary, Francesco Romanò & Antoine Dazin

  2. Arts et Métiers Institute of Technology, CNAM, DynFluid, HESAM Université, 75013, Paris, France

    Jean-Christophe Loiseau

Authors
  1. M. A. Elhawary
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Francesco Romanò
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jean-Christophe Loiseau
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Antoine Dazin
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All the authors were involved in preparing the manuscript. All the authors have read and approved the final manuscript.

Corresponding author

Correspondence to Antoine Dazin.

Ethics declarations

Financial interests

This paper is supported by Clean Sky European Union’s Horizon 2020 research and innovation program under grant agreement No 886352, project ACONIT.

Conflict of interest

The authors declare no conflict of interest

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Elhawary, M.A., Romanò, F., Loiseau, JC. et al. Machine learning for optimal flow control in an axial compressor. Eur. Phys. J. E 46, 28 (2023). https://doi.org/10.1140/epje/s10189-023-00284-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1140/epje/s10189-023-00284-9

Search

Navigation