Stabilization of the fluidic pinball with gradient-enriched machine learning control

Maceda, Guy Y. Cornejo; Li, Yiqing; Lusseyran, François; Morzyński, Marek; Noack, Bernd R.

doi:10.1017/jfm.2021.301

Cited by 34 publications

(45 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This sensor placement has been validated by Cornejo Maceda et al. (2021), in a sense that such arrangement is capable of detecting large-scaled vortex shedding while encompassing phase information between sensors in its feedback flow control experiment. In other words, this arrangement can help to infer the flow state in the dynamically controlled flow with a wide range of control commands.…”

Section: Numerical Plant: the Fluidic Pinballmentioning

confidence: 93%

See 2 more Smart Citations

Machine-learned control-oriented flow estimation for multi-actuator multi-sensor systems exemplified for the fluidic pinball

Noack

2022

J. Fluid Mech.

Self Cite

View full text Add to dashboard Cite

We propose the first machine-learned control-oriented flow estimation for multiple-input, multiple-output plants. The starting point is constant actuation with open-loop actuation commands leading to a database with simultaneously recorded actuation commands, sensor signals and flow fields. A key enabler is an estimator input vector comprising sensor signals and actuation commands. The mapping from the sensor signals and actuation commands to the flow fields is realized in an analytically simple, data-centric and general nonlinear approach. The analytically simple estimator generalizes linear stochastic estimation for actuation commands. The data-centric approach yields flow fields from estimator inputs by interpolating from the database – similar to Loiseau, Noack & Brunton (J. Fluid Mech., vol. 844, 2018, pp. 459–490) for unforced flow. The interpolation is performed with $k$ nearest neighbours ( $k$ NN). The general global nonlinear mapping from inputs to flow fields is obtained from a deep neural network (DNN) via an iterative training approach. The estimator comparison is performed for the fluidic pinball plant, which is a multiple-input, multiple-output wake control benchmark (Deng et al., J. Fluid Mech., vol. 884, 2020, A37) featuring rich dynamics under steady controls. We conclude that the machine learning methods clearly outperform the linear model. The performance of $k$ NN and DNN estimators are comparable for periodic dynamics. Yet the DNN performs consistently better when the flow is chaotic. Moreover, a thorough comparison regarding the complexity, computational cost and prediction accuracy is presented to demonstrate the relative merits of each estimator. The proposed method can be generalized for closed-loop flow control plants.

show abstract

Section: Numerical Plant: the Fluidic Pinballmentioning

confidence: 93%

“…2019; Cornejo Maceda et al. 2021). In this study, only steady, open-loop control commands are considered.…”

Section: Numerical Plant: the Fluidic Pinballmentioning

confidence: 99%

See 1 more Smart Citation

Machine-learned control-oriented flow estimation for multi-actuator multi-sensor systems exemplified for the fluidic pinball

Noack

2022

J. Fluid Mech.

Self Cite

View full text Add to dashboard Cite

show abstract

“…2021) and gradient-based approaches (Cornejo Maceda et al. 2021). Once an optimal configuration is found, the location of the actuators can be frozen for a final design, eliminating the complexity of the apparatus used for optimization and the unused actuator locations.…”

Section: Introductionmentioning

confidence: 99%

“…This physics-free, black-box approach enables the rapid iteration of actuator combinations and parameters experimentally to reach an optimal and feasible design given a set of actuator locations that can be physically constructed. Alternative optimization approaches used in the context of fluid dynamics that are worth noting are extremum seeking control (Déda & Wolf 2022), Bayesian optimization (Blanchard et al 2021) and gradient-based approaches (Cornejo Maceda et al 2021). Once an optimal configuration is found, the location of the actuators can be frozen for a final design, eliminating the complexity of the apparatus used for optimization and the unused actuator locations.…”

Section: Introductionmentioning

confidence: 99%

Reduction of noise in cold and hot supersonic jets using active flow control guided by a genetic algorithm

2022

View full text Add to dashboard Cite

This study demonstrates an experimental platform for active jet noise reduction comprising of an automated system that performs a search for the optimal actuator locations and parameters, powered by a genetic algorithm (GA). Sideline noise reduction levels of 7.3 dB were achieved for a cold overexpanded (nozzle pressure ratio, $NPR=2.8$ ) jet, beyond the state-of-the-art for jet noise reduction with air injection. The reduction in noise was achieved at a mass flow rate of 1.4 % of the main jet, requiring no prior knowledge of the flow physics to inform the placement of the actuators. The same actuator pattern was tested in hot conditions (nozzle temperature ratio, $NTR=1.88$ ), achieving 4.7 dB sideline noise reduction. Detailed examination of the solutions obtained unveils some of the mechanisms leveraged by the GA to accomplish these high levels of noise reduction through microphone measurements and schlieren flow visualization. The GA found that actuating at the diverging wall of the convergent–divergent nozzle, where flow is supersonic, is very effective when combined with air injection near the nozzle lip, outside of the nozzle. Although the external actuation is effective at eliminating the screech tone, it is by actuating inside the nozzle at the diverging wall that sufficient disruption of the shock cell train can be achieved in order to reduce the broadband shock-associated noise.

show abstract

Turbulence Control: From Model-Based to Machine Learned

Deng,

Cornejo Maceda,

Noack

2023

Advances in Mathematical Fluid Mechanics

View full text Add to dashboard Cite

Stabilization of the fluidic pinball with gradient-enriched machine learning control

Abstract: Abstract

Cited by 34 publications

References 57 publications

Machine-learned control-oriented flow estimation for multi-actuator multi-sensor systems exemplified for the fluidic pinball

Machine-learned control-oriented flow estimation for multi-actuator multi-sensor systems exemplified for the fluidic pinball

Reduction of noise in cold and hot supersonic jets using active flow control guided by a genetic algorithm

Turbulence Control: From Model-Based to Machine Learned

Contact Info

Product

Resources

About