Abstract
This work discusses a closed-loop control strategy for complex systems utilizing scarce and streaming data. A discrete embedding space is first built using hash functions applied to the sensor measurements from which a Markov process model is derived, approximating the complex system’s dynamics. A control strategy is then learned using reinforcement learning once rewards relevant with respect to the control objective are identified. This method is designed for experimental configurations, requiring no computations nor prior knowledge of the system, and enjoys intrinsic robustness. It is illustrated on two systems: the control of the transitions of a Lorenz’63 dynamical system, and the control of the drag of a cylinder flow. The method is shown to perform well.
Similar content being viewed by others
References
Gerhard, J., Pastoor, M., King, R., Noack, B.R., Dillmann, A., Morzynski, M., Tadmor, G.: Model-based control of vortex shedding using low-dimensional Galerkin models. AIAA J. 4262(2003), 115–173 (2003)
Bergmann, M., Cordier, L.: Optimal control of the cylinder wake in the laminar regime by trust-region methods and pod reduced-order models. J. Comput. Phys. 227(16), 7813–7840 (2008)
Ma, Z., Ahuja, S., Rowley, C.W.: Reduced-order models for control of fluids using the eigensystem realization algorithm. Theor. Comput. Fluid Dyn. 25(1–4), 233–247 (2011)
Joe, W.T., Colonius, T., MacMynowski, D.G.: Feedback control of vortex shedding from an inclined flat plate. Theor. Comput. Fluid Dyn. 25(1–4), 221–232 (2011)
Mathelin, L., Pastur, L., Le Maître, O.: A compressed-sensing approach for closed-loop optimal control of nonlinear systems. Theor. Comput. Fluid Dyn. 26(1–4), 319–337 (2012)
Cordier, L., Noack, B.R., Tissot, G., Lehnasch, G., Delville, J., Balajewicz, M., Daviller, G., Niven, R.K.: Identification strategies for model-based control. Exp. Fluids 54(8), 1–21 (2013)
Lee, C., Kim, J., Babcock, D., Goodman, R.: Application of neural networks to turbulence control for drag reduction. Phys. Fluids 9(6), 1740–1747 (1997)
Kegerise, M.A., Cambell, R.H., Cattafesta, L.N.: Real time feedback control of flow-induced cavity tones—part 2: adaptive control. J. Sound Vib. 307, 924–940 (2007)
Huang, S.-C., Kim, J.: Control and system identification of a separated flow. Phys. Fluids 20(10), 101509 (2008)
Hervé, A., Sipp, D., Schmid, P.J., Samuelides, M.: A physics-based approach to flow control using system identification. J. Fluid Mech. 702, 26–58 (2012)
Gautier, N., Aider, J.-L., Duriez, T., Noack, B.R., Segond, M., Abel, M.W.: Closed-loop separation control using machine learning. J. Fluid Mech. 770, 442–457 (2015)
Brunton, S., Noack, B.: Closed-loop turbulence control: progress and challenges. Appl. Mech. Rev. 67(5), 050801 (2015)
Slaney, M., Casey, M.: Locality-sensitive hashing for finding nearest neighbors [lecture notes]. IEEE Signal Process. Mag. 25(2), 128–131 (2008)
Kaiser, E., Noack, B.R., Cordier, L., Spohn, A., Segond, M., Abel, M., Daviller, G., Östh, J., Krajnović, S., Niven, R.K.: Cluster-based reduced-order modelling of a mixing layer. J. Fluid Mech. 754, 365–414 (2014)
Mandl, P.: Estimation and control in markov chains. Adv. Appl. Probab. 6(1), 40–60 (1974)
Watkins, C., Dayan, P.: Q-learning. Mach. Learn. 8(3–4), 279–292 (1992)
Gosavi, A.: Target-sensitive control of Markov and semi-Markov processes. Int. J. Control Autom. 9(5), 941–951 (2011)
Lin, C.T., Jou, C.P.: Controlling chaos by GA-based reinforcement learning neural network. IEEE Trans. Neural Netw. 10(4), 846–859 (1999)
Gadaleta, S., Dangelmayr, G.: Optimal chaos control through reinforcement learning. Chaos 9(3), 775–788 (1999)
Grassberger, P., Procaccia, I.: Measuring the strangeness of strange attractors. Phys. D 9, 189–208 (1983)
Takens, F., Rand, D.A., Young, L.S.: Dynamical systems and turbulence. Lect. Notes Math. 898(9), 366 (1981)
Carter, J.L., Wegman, M.N.: Universal classes of hash functions. In: Proceedings of 9th Annual ACM Theory of Computing, pp. 106–112. ACM (1977)
Andoni, A., Indyk, P.: Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. In: Proceedings of the 47th Annual IEEE Symposium on Foundations of Computer Science, pp. 459–468. IEEE (2006)
Johnson, W., Lindenstrauss, J.: Extensions of Lipschitz mappings into a Hilbert space. Contemp. Math. 26, 189–206 (1984)
Novikov, E.A.: Two-particle description of turbulence, Markov property, and intermittency. Phys. Fluids 1(2), 326–330 (1989)
Renner, C., Peinke, J., Friedrich, R.: Experimental indications for Markov properties of small-scale turbulence. J. Fluid Mech. 433, 383–409 (2001)
Bellman, R.: On the theory of dynamic programming. Proc. Natl. Acad. Sci. USA 38(8), 716 (1952)
Powell, W.: Approximate Dynamic Programming: Solving the Curses of Dimensionality, vol. 703. Wiley, London (2007)
Lewis, F., Vrabie, D.: Reinforcement learning and adaptive dynamic programming for feedback control. IEEE Circuits Syst. Mag. 9(3), 32–50 (2009)
Lorenz, E.N.: Deterministic nonperiodic flow. J. Atmos. Sci. 20(2), 130–141 (1963)
Le Maître, O.P., Scanlan, R.H., Knio, O.M.: Estimation of the flutter derivatives of an NACA airfoil by means of Navier–Stokes simulation. J. Fluids Struct. 17(1), 1–28 (2003)
Lusseyran, F., Pastur, L.R., Letellier, C.: Dynamical analysis of an intermittency in an open cavity flow. Phys. Fluids 20(11), 114101 (2008)
Gorodetsky, A.A., Karaman, S., Marzouk, Y.M.: Efficient high-dimensional stochastic optimal motion control using tensor-train decomposition. In: Robotics: Science and Systems XI, Sapienza University of Rome, Italy, July 13–17 (2015)
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Omar M. Knio.
Rights and permissions
About this article
Cite this article
Guéniat, F., Mathelin, L. & Hussaini, M.Y. A statistical learning strategy for closed-loop control of fluid flows. Theor. Comput. Fluid Dyn. 30, 497–510 (2016). https://doi.org/10.1007/s00162-016-0392-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00162-016-0392-y