Active MEMS-based flow control using artificial neural network

These last years several research works have studied the application of Micro-Electro-Mechanical Systems (MEMS) for aerodynamic active flow control. Controlling such MEMS-based systems remains a challenge. Among the several existing control approaches for time varying systems, many of them use a process model representing the dynamic behavior of the process to be controlled. The purpose of this paper is to study the suitability of an artificial neural network first to predict the flow evolution induced by MEMS, and next to optimize the flow w.r.t. a numerical criterion. To achieve this objective, we focus on a dynamic flow over a backward facing step where MEMS actuators velocities are adjusted to maximize the pressure over the step surface. The first effort has been to establish a baseline database provided by computational fluid dynamics simulations for training the neural network. Then we investigate the possibility to control the flow through MEMS configuration changes. Results are promising, despite slightly high computational times for real time application.

[1]  Julien Henriet,et al.  Respiratory lung motion using an artificial neural network , 2011, Neural Computing and Applications.

[2]  Stephen J. Wright,et al.  Numerical Optimization , 2018, Fundamental Statistical Inference.

[3]  Pierre Sagaut,et al.  NARX Modeling and Adaptive Closed-Loop Control of a Separation by Synthetic Jet in Unsteady RANS computations , 2010 .

[4]  J.R. Frutos,et al.  An electrostatically actuated valve for turbulent boundary layer control , 2005, IEEE Sensors, 2005..

[5]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[6]  Ronald D. Joslin,et al.  Issues in active flow control: theory, control, simulation, and experiment , 2004 .

[7]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[8]  Jacques M. Bahi,et al.  An incremental learning algorithm for function approximation , 2009, Adv. Eng. Softw..

[9]  Active control of a transitional flow over a backward-facing step , 2009 .

[10]  Lutz Prechelt,et al.  Automatic early stopping using cross validation: quantifying the criteria , 1998, Neural Networks.

[11]  O. Ducloux,et al.  MEMS magneto-mechanical microvalves (MMMS) for aerodynamic active flow control , 2010 .

[12]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[13]  Raymond P. LeBeau,et al.  Flow Control Optimization Using Neural Networks and Genetic Algorithms , 2009 .