Active Simulation of Transient Wind Field in a Multiple-Fan Wind Tunnel via Deep Reinforcement Learning
Publication: Journal of Engineering Mechanics
Volume 147, Issue 9
Abstract
The transient wind field during a nonsynoptic wind event (e.g., thunderstorm downburst) presents time-varying mean and nonstationary fluctuating components, and hence is not easy to be reproduced in a conventional boundary-layer wind tunnel with various passive devices (e.g., spires, roughness elements, and barriers). As a promising alternative, the actively controlled multiple-fan wind tunnel has emerged to effectively generate the laboratory-scale, spatiotemporally varying wind flows. The tracking accuracy of target wind speed histories at selected locations in the multiple-fan wind tunnel depends on the control signals input to individual fans. Conventional hand-design linear control schemes cannot ensure good performance due to the complicated fluid dynamics and nonlinear interactions inside the wind tunnel. In addition, the determination of the control parameters involves a time-consuming manual tuning process. In this paper, an accurate and efficient control scheme based on deep reinforcement learning (RL) is developed to realize the prescribed spatiotemporally varying wind field in a multiple-fan wind tunnel. Specifically, the fully connected deep neural network (DNN) is trained using RL methodology to perform active flow control in the multiple-fan wind tunnel. Accordingly, the optimal parameters (network weights) of the DNN-based nonlinear controller are obtained based on an automated trial-and-error process. The controller complexity needed for active simulation of transient winds can be well captured by a DNN due to its powerful function approximation ability, and the “model-free” and “automation” features of RL paradigm eliminate the need of expensive modeling of fluid dynamics and costly hand tuning of control parameters. Numerical results of the transient winds during a moving downburst event (including nose-shape vertical profiles, time-varying mean wind speeds, and nonstationary fluctuations) present good performance of the proposed deep RL-based control strategy in a simulation environment of the multiple-fan wind tunnel at the University at Buffalo.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
All data that support the findings of this paper are available from the corresponding author upon reasonable request.
Acknowledgments
The support for this project provided by Institute of Bridge Engineering at University at Buffalo is gratefully acknowledged.
References
Aboutabikh, M., T. Ghazal, J. Chen, S. Elgamal, and H. Aboshosha. 2019. “Designing a blade-system to generate downburst outflows at boundary layer wind tunnel.” J. Wind Eng. Ind. Aerodyn. 186 (Mar): 169–191. https://doi.org/10.1016/j.jweia.2019.01.005.
Bienkiewicz, B., J. E. Cermak, J. A. Peterka, and R. H. Scanlan. 1983. “Active modeling of large-scale turbulence.” J. Wind Eng. Ind. Aerodyn. 13 (1–3): 465–475. https://doi.org/10.1016/0167-6105(83)90165-4.
Butler, K., S. Cao, A. Kareem, Y. Tamura, and S. Ozono. 2010. “Surface pressure and wind load characteristics on prisms immersed in a simulated transient gust front flow field.” J. Wind Eng. Ind. Aerodyn. 98 (6–7): 299–316. https://doi.org/10.1016/j.jweia.2009.11.003.
Cao, S., A. Nishi, H. Kikugawa, and Y. Matsuda. 2002. “Reproduction of wind velocity history in a multiple fan wind tunnel.” J. Wind Eng. Ind. Aerodyn. 90 (12–15): 1719–1729. https://doi.org/10.1016/S0167-6105(02)00282-9.
Cermak, J. E. 1971. “Laboratory simulation of the atmospheric boundary layer.” AIAA J. 9 (9): 1746–1754. https://doi.org/10.2514/3.49977.
Chay, M. T., and C. W. Letchford. 2002. “Pressure distributions on a cube in a simulated thunderstorm downburst—Part A: Stationary downburst observations.” J. Wind Eng. Ind. Aerodyn. 90 (7): 711–732. https://doi.org/10.1016/S0167-6105(02)00158-7.
Hao, J., and T. Wu. 2017. “Nonsynoptic wind-induced transient effects on linear bridge aerodynamics.” J. Eng. Mech. 143 (9): 04017092. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001313.
Hao, J., and T. Wu. 2018. “Downburst-induced transient response of a long-span bridge: A CFD-CSD-based hybrid approach.” J. Wind Eng. Ind. Aerodyn. 179 (Aug): 273–286. https://doi.org/10.1016/j.jweia.2018.06.006.
Hjelmfelt, M. R. 1988. “Structure and life cycle of microburst outflows observed in Colorado.” J. Appl. Meteorol. 27 (8): 900–927. https://doi.org/10.1175/1520-0450(1988)027%3C0900:SALCOM%3E2.0.CO;2.
Jesson, M., M. Sterling, C. Letchford, and M. Haines. 2015. “Aerodynamic forces on generic buildings subject to transient, downburst-type winds.” J. Wind Eng. Ind. Aerodyn. 137 (Feb): 58–68. https://doi.org/10.1016/j.jweia.2014.12.003.
Khan, A. A., and N. Rapal. 2006. “Fuzzy PID controller: Design, tuning and comparison with conventional PID controller.” In Proc., 2006 IEEE Int. Conf. on Engineering of Intelligent Systems. New York: IEEE.
Kikitsu, H., J. Kanda, and R. Iwasaki. 1999. “Flow simulation by wind tunnel with computer-controlled multiple fans.” J. Wind Eng. Ind. Aerodyn. 83 (1–3): 421–429. https://doi.org/10.1016/S0167-6105(99)00090-2.
Kobayashi, H., and A. Hatanaka. 1992. “Active generation of wind gust in a two-dimensional wind tunnel.” J. Wind Eng. Ind. Aerodyn. 42 (1–3): 959–970. https://doi.org/10.1016/0167-6105(92)90102-G.
Kobayashi, H., A. Hatanaka, and T. Ueda. 1994. “Active simulation of time histories of strong wind gust in a wind tunnel.” J. Wind Eng. Ind. Aerodyn. 53 (3): 315–330. https://doi.org/10.1016/0167-6105(94)90089-2.
Le, V., and L. Caracoglia. 2019. “Generation and characterization of a non-stationary flow field in a small-scale wind tunnel using a multi-blade flow device.” J. Wind Eng. Ind. Aerodyn. 186 (Mar): 1–16. https://doi.org/10.1016/j.jweia.2018.12.017.
Lillicrap, T. P., J. J. Hunt, A. Pritzel, N. Heess, T. Erez, Y. Tassa, D. Silver, and D. Wierstra. 2016. “Continuous control with deep reinforcement learning.” In Proc., 4th Int. Conf. on Learning Representations, ICLR 2016. Menlo Park, CA: Facebook.
Liu, Y., J. Wang, X. Liu, X. Li, B. Yao, and L. Song. 2020. “Improved model predictive control for the flow field in a wind tunnel with model uncertainty.” J. Franklin Inst. 357 (12): 7439–7455. https://doi.org/10.1016/j.jfranklin.2019.12.004.
Lombardo, F. T., D. A. Smith, J. L. Schroeder, and K. C. Mehta. 2014. “Thunderstorm characteristics of importance to wind engineering.” J. Wind Eng. Ind. Aerodyn. 125 (Feb): 121–132. https://doi.org/10.1016/j.jweia.2013.12.004.
Mason, M. S., G. S. Wood, and D. F. Fletcher. 2009. “Numerical simulation of downburst winds.” J. Wind Eng. Ind. Aerodyn. 97 (11–12): 523–539. https://doi.org/10.1016/j.jweia.2009.07.010.
Mnih, V., et al. 2015. “Human-level control through deep reinforcement learning.” Nature 518 (7540): 529–533. https://doi.org/10.1038/nature14236.
Nishi, A., H. Kikugawa, Y. Matsuda, and D. Tashiro. 1997. “Turbulence control in multiple-fan wind tunnels.” J. Wind Eng. Ind. Aerodyn. 67–68 (Apr–Jun): 861–872. https://doi.org/10.1016/S0167-6105(97)00124-4.
Nishi, A., H. Kikugawa, Y. Matsuda, and D. Tashiro. 1999. “Active control of turbulence for an atmospheric boundary layer model in a wind tunnel.” J. Wind Eng. Ind. Aerodyn. 83 (1–3): 409–419. https://doi.org/10.1016/S0167-6105(99)00089-6.
Nishi, A., and H. Miyagi. 1995. “Computer-controlled wind tunnel for wind-engineering applications.” J. Wind Eng. Ind. Aerodyn. 54–55 (Feb): 493–504. https://doi.org/10.1016/0167-6105(94)00062-I.
Rabault, J., M. Kuchta, A. Jensen, U. Réglade, and N. Cerardi. 2019. “Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control.” J. Fluid Mech. 865: 281–302. https://doi.org/10.1017/jfm.2019.62.
Romanic, D., J. LoTufo, and H. Hangan. 2019. “Transient behavior in impinging jets in crossflow with application to downburst flows.” J. Wind Eng. Ind. Aerodyn. 184 (Jan): 209–227. https://doi.org/10.1016/j.jweia.2018.11.020.
Silver, D., et al. 2017. “Mastering the game of go without human knowledge.” Nature 550 (7676): 354–359. https://doi.org/10.1038/nature24270.
Silver, D., G. Lever, N. Heess, T. Degris, D. Wierstra, and M. Riedmiller. 2014. “Deterministic policy gradient algorithms.” In Proc., 31st Int. Conf. on Machine Learning. Princeton, NJ: International Machine Learning Society.
Smith, J. T., F. J. Masters, Z. Liu, and T. A. Reinhold. 2012. “A simplified approach to simulate prescribed boundary layer flow conditions in a multiple controlled fan wind tunnel.” J. Wind Eng. Ind. Aerodyn. 109 (Oct): 79–88. https://doi.org/10.1016/j.jweia.2012.04.010.
Sutcliffe, P., and M. R. Rennie. 2016. “Neural network model predictive control of wind tunnel test conditions.” In Proc., 54th AIAA Aerospace Sciences Meeting. Reston, VA: American Institute for Aeronautics and Astronautics.
Sutton, R. S., and A. G. Barto. 2018. Reinforcement learning: An introduction. Cambridge, MA: MIT Press.
Sutton, R. S., A. G. Barto, and R. J. Williams. 1992. “Reinforcement learning is direct adaptive optimal control.” IEEE Control Syst. Mag. 12 (2): 19–22. https://doi.org/10.1109/37.126844.
Teunissen, H. W. 1975. “Simulation of the planetary boundary layer in a multiple-jet wind tunnel.” Atmos. Environ. 9 (2): 145–174. https://doi.org/10.1016/0004-6981(75)90065-7.
Vicroy, D. D. 1991. A simple, analytical, axisymmetric microburst model for downdraft estimation. Hampton, VA: National Aeronautics and Space Administration.
Wang, H., and T. Wu. 2018. “Hilbert-wavelet-based nonstationary wind field simulation: A multiscale spatial correlation scheme.” J. Eng. Mech. 144 (8): 04018063. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001490.
Wang, H., and T. Wu. 2020. “Time-varying multiscale spatial correlation: Simulation and application to wind loading of structures.” J. Struct. Eng. 146 (7): 04020138. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002689.
Wang, J. Y., Q. H. Meng, B. Luo, and M. Zeng. 2018. “A multiple-fan active control wind tunnel for outdoor wind speed and direction simulation.” Rev. Sci. Instrum. 89 (3): 035108. https://doi.org/10.1063/1.5009897.
Watkins, C. J., and P. Dayan. 1992. “Q-learning.” Mach. Learn. 8 (3–4): 279–292.
Yang, Q., R. Gao, F. Bai, T. Li, and Y. Tamura. 2018. “Damage to buildings and structures due to recent devastating wind hazards in East Asia.” Nat. Hazards 92 (3): 1321–1353. https://doi.org/10.1007/s11069-018-3253-8.
Information & Authors
Information
Published In
Journal of Engineering Mechanics
Volume 147 • Issue 9 • September 2021
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Oct 26, 2020
Accepted: Mar 31, 2021
Published online: Jul 7, 2021
Published in print: Sep 1, 2021
Discussion open until: Dec 7, 2021
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Shaopeng Li, Teng Wu, A Risk-Informed Decision-Support Framework for Optimal Operation of Hurricane-Impacted Transportation Networks, Natural Hazards Review, 10.1061/NHREFO.NHENG-1631, 24, 3, (2023).
- Teng Wu, Reda Snaiki, Applications of Machine Learning to Wind Engineering, Frontiers in Built Environment, 10.3389/fbuil.2022.811460, 8, (2022).