Adaptive flow control using simple artificial neural networks

Pindera, Maciej Z.

doi:10.2514/6.2002-990

Cited by 4 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An adaptive algorithm essentially regulates controller parameters in run-time by tuning the parameters via performance optimization 25 . Compared to the model-based control schemes, the current approach dispenses with detailed understanding on the system, and sets unknown parameters by the adaptive algorithm 26,27 .…”

Section: Introductionmentioning

confidence: 99%

Adaptive flow control of low-Reynolds number aerodynamics using dielectric barrier discharge actuator

Cho

Shyy

2011

Progress in Aerospace Sciences

View full text Add to dashboard Cite

The aerodynamics of micro air vehicles (operating at the chord Reynolds number of 10 5 or below) is substantially influenced by the unsteadiness of the wind gust and the aircraft's light weight. In this effort, we investigate the active flow control of the dielectric barrier discharge actuator for flows around the SD7003 airfoil, with the chord Reynolds number of 6×10 4 , to enhance our understanding of the unsteady aerodynamics. Using a recently developed ARMARKOV/Toeplitz control scheme, the characteristics of the adaptive control in response to the fluctuation of the free stream, and impact on the aerodynamics are probed. By varying the voltage amplitude to the DBD actuator, effective control of unsteady flow structure can be performed to attain a desirable lift.

show abstract

Section: Introductionmentioning

confidence: 99%

Adaptive flow control of low-Reynolds number aerodynamics using dielectric barrier discharge actuator

Cho

Shyy

2011

Progress in Aerospace Sciences

View full text Add to dashboard Cite

show abstract

“…Gad-el-Hak (2000) states that, 'For flow-control applications, neural networks offer the possibility of adaptive controllers that are simpler and potentially less sensitive to parameter variations as compared with conventional controllers.' Many examples of this use of neural networks exist and the work of Fan, Hofmann & Herbert (1993), Fan (1995), Pindera (2002), Lee et al (1997) may serve as examples for computational work employing neural networks for feedback control purposes. Gillies (1995Gillies ( , 1998Gillies ( , 2000 employs an ANN-ARX model as a one-step predictor for the POD mode amplitudes in order to close the feedback control loop to control a reduced-order model of the circular cylinder wake at Re = 100.…”

Section: Introductionmentioning

confidence: 99%

Low-dimensional modelling of a transient cylinder wake using double proper orthogonal decomposition

et al. 2008

View full text Add to dashboard Cite

For the systematic development of feedback flow controllers, a numerical model that captures the dynamic behaviour of the flow field to be controlled is required. This poses a particular challenge for flow fields where the dynamic behaviour is nonlinear, and the governing equations cannot easily be solved in closed form. This has led to many versions of low-dimensional modelling techniques, which we extend in this work to represent better the impact of actuation on the flow. For the benchmark problem of a circular cylinder wake in the laminar regime, we introduce a novel extension to the proper orthogonal decomposition (POD) procedure that facilitates mode construction from transient data sets. We demonstrate the performance of this new decomposition by applying it to a data set from the development of the limit cycle oscillation of a circular cylinder wake simulation as well as an ensemble of transient forced simulation results. The modes obtained from this decomposition, which we refer to as the double POD (DPOD) method, correctly track the changes of the spatial modes both during the evolution of the limit cycle and when forcing is applied by transverse translation of the cylinder. The mode amplitudes, which are obtained by projecting the original data sets onto the truncated DPOD modes, can be used to construct a dynamic mathematical model of the wake that accurately predicts the wake flow dynamics within the lock-in region at low forcing amplitudes. This low-dimensional model, derived using nonlinear artificial neural network based system identification methods, is robust and accurate and can be used to simulate the dynamic behaviour of the wake flow. We demonstrate this ability not just for unforced and open-loop forced data, but also for a feedback-controlled simulation that leads to a 90% reduction in lift fluctuations. This indicates the possibility of constructing accurate dynamic low-dimensional models for feedback control by using unforced and transient forced data only.

show abstract

“…It estimates POD modal amplitude more accurately and faster than using Galerkin projection or stochastic estimation [3]. The method can maximize the effectiveness of the real time feedback flow controller, since it excludes the CFD analysis for Navier-Stokes equation.…”

Section: Artificial Neural Network-auto Regressive Exogenous (Ann-arx)mentioning

confidence: 99%

“…The system for the continuous linear model reference control has the form [7]: (3) where is the plant state vector, is the control vector, and is the plant output vector. The objective of the model reference control is to find so that the approximates the output of the reference model which has the form: (4) where is model state vector, is the model input, and is the model output vector.…”

Section: Direct Model Reference Adaptive Controlmentioning

confidence: 99%

“…The basic idea of this method is to project N-dimensional state spaces onto an M-dimensional subspace, where M is much bigger than N. After the POD procedure, a system identification technique is performed to estimate POD modal amplitudes. An artificial Neural Network-Auto Regressive Exogenous (ANN-ARX) method, which estimates POD modal amplitude more accurately and faster than using Galerkin projection or stochastic estimation [3], is used in this paper. The reduced order model (ROM) is completed by organizing the POD method and an ANN-ARX model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Feedback flow control using the POD method on the backward facing step wall model

Cho¹,

Lee²,

Lee³

et al. 2012

International Journal of Aeronautical and Space Sciences

View full text Add to dashboard Cite

Missiles suffer from flight instability problems at high angles of attack, since vortex flow over a fuselage cause lateral force to the body. To overcome this problem at a high angle of attack, the development of a real time vortex controller is needed. In this paper, Proper Orthogonal Decomposition (POD) and feedback controllers are developed for real time vortex control. The POD method is one of the most well known techniques for modeling low order models that represent the original full-order model. An adaptive control algorithm is used for real time control.

show abstract

Adaptive flow control using simple artificial neural networks

Cited by 4 publications

References 12 publications

Adaptive flow control of low-Reynolds number aerodynamics using dielectric barrier discharge actuator

Adaptive flow control of low-Reynolds number aerodynamics using dielectric barrier discharge actuator

Low-dimensional modelling of a transient cylinder wake using double proper orthogonal decomposition

Feedback flow control using the POD method on the backward facing step wall model

Contact Info

Product

Resources

About