Improvement of aeroelastic vehicles performance through recurrent neural network controllers

Aeroelastic systems have the peculiarity of changing their behavior with flight conditions. Within such a view, it is difficult to design a single control law capable of efficiently working at different flight conditions. Moreover, control laws are often designed on simple linearized, low-fidelity models, introducing the need of a scheduled tuning over a wide operational range. Obviously, such a design process can be time-consuming, because of the high number of simulations and flight tests required to assure high performance and robustness. The present work aims at proving the high flexibility of neural network-based controllers, testing their adaptive properties when applied to typical fixed and rotary-wing aircraft problems. At first, the proposed control strategy will be used to suppress the limit cycle oscillations experienced by a rigid wing in transonic regime. Then, as a second example, a controller with the same structure will be employed to reduce the hub vibrations of an helicopter rotor with active twist blades.

[1]  Marco Morandini,et al.  An Efficient Formulation for General-Purpose Multibody/Multiphysics Analysis , 2014 .

[2]  Massimo Gennaretti,et al.  Adverse rotorcraft-pilot coupling: Recent research activities in Europe , 2008 .

[3]  Marco Lovera,et al.  Periodic control of helicopter rotors for attenuation of vibrations in forward flight , 2000, IEEE Trans. Control. Syst. Technol..

[4]  Bing Zhu.  Nonlinear adaptive neural network control for a model-scaled unmanned helicopter , 2014 .

[5]  Marco Morandini,et al.  Integrated Aeroservoelastic Analysis of Induced Strain Rotor Blades , 2008 .

[6]  Frank L. Lewis,et al.  Aircraft Control and Simulation , 1992 .

[7]  Fang Wang,et al.  Robust adaptive dynamic surface control design for a flexible air-breathing hypersonic vehicle with input constraints and uncertainty , 2014 .

[8]  Sahjendra N. Singh,et al.  Limit Cycle Oscillation and Orbital Stability in Aeroelastic Systems with Torsional Nonlinearity , 2003 .

[9]  Her-Terng Yau,et al.  Terminal sliding mode control for aeroelastic systems , 2012 .

[10]  Fatma Demet Ulker,et al.  A New Framework For Helicopter Vibration Suppression; Time-Periodic System Identification and Controller Design , 2011 .

[11]  Keum W. Lee,et al.  Immersion- and Invariance-Based Adaptive Control of a Nonlinear Aeroelastic System , 2009 .

[12]  H. Climent,et al.  T-tail flutter: Potential-flow modelling, experimental validation and flight tests , 2014 .

[13]  Martin R. Waszak.  Modeling the Benchmark Active Control Technology Wind-Tunnel Model for Active Control Design Applications , 1998 .

[14]  Brian J. Taylor,et al.  Verification and validation of neural networks: a sampling of research in progress , 2003, SPIE Defense + Commercial Sensing.

[15]  Paolo Mantegazza,et al.  Active Flutter Suppression Using Recurrent Neural Networks , 2000 .

[16]  Yushu Chen,et al.  Supercritical and subcritical Hopf bifurcation and limit cycle oscillations of an airfoil with cubic nonlinearity in supersonic\hypersonic flow , 2012 .

[17]  P. Mantegazza,et al.  Multibody Implementation of Finite Volume C-0 Beams , 2000 .

[18]  A. Kurdila,et al.  Adaptive Feedback Linearization for the Control of a Typical Wing Section with Structural Nonlinearity , 1997, 4th International Symposium on Fluid-Structure Interactions, Aeroelasticity, Flow-Induced Vibration and Noise: Volume III.

[19]  R Waszak Martin,et al.  Robust Multivariable Flutter Suppression for the Benchmark Active Control Technology (BACT) Wind-tunnel Model , 1997 .

[20]  Piergiovanni Marzocca,et al.  Active Aeroelastic Control of Lifting Surfaces via Jet Reaction Limiter Control , 2005, Int. J. Bifurc. Chaos.

[21]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[22]  Mehrdaad Ghorashi,et al.  Nonlinear analysis of the dynamics of articulated composite rotor blades , 2012 .

[23]  Bin Xu,et al.  Robust adaptive neural control of flexible hypersonic flight vehicle with dead-zone input nonlinearity , 2015 .

[24]  Vivek Mukhopadhyay,et al.  Historical Perspective on Analysis and Control of Aeroelastic Responses , 2003 .

[25]  R Waszak Martin,et al.  Parameter Estimation and Analysis of Actuators for the BACT Wind-Tunnel Model , 1996 .

[26]  Sun Jian,et al.  Active flutter suppression control law design method based on balanced proper orthogonal decomposition reduced order model , 2012 .

[27]  Eli Livne,et al.  Future of Airplane Aeroelasticity , 2003 .

[28]  Dennis S. Bernstein,et al.  Higher-Harmonic-Control Algorithm for Helicopter Vibration Reduction Revisited , 2005 .

[29]  Stephen A. Jacklin,et al.  Closing the Certification Gaps in Adaptive Flight Control Software , 2008 .

[30]  E. Lavretsky,et al.  Adaptive control of flight: theory, applications, and open problems , 2006, 2006 American Control Conference.

[31]  W. Keats Wilkie,et al.  Active-Twist Rotor Control Applications for UAVs , 2006 .

[32]  Vivek Mukhopadhyay,et al.  Transonic Flutter Suppression Control Law Design and Wind-Tunnel Test Results , 2000 .

[33]  P. Mantegazza,et al.  Characteristic behavior of prismatic anisotropic beam via generalized eigenvectors , 2010 .

[34]  Paolo Mantegazza,et al.  A \free" approach to Computational Aeroelasticity , 2010 .

[35]  Johannes Riemenschneider,et al.  Development of active twist rotors at the German Aerospace Center (DLR) , 2011 .

[36]  Weiwei Zhang,et al.  The interaction between flutter and buffet in transonic flow , 2015 .

[37]  A. G. Kelkar,et al.  Passivity-Based Robust Control with Application to Benchmark Active Controls Technology Wing , 2000 .

[38]  Paolo Mantegazza,et al.  Active Flutter Suppression for a Three-Surface Transport Aircraft by Recurrent Neural Networks , 2007 .

[39]  Earl H. Dowell,et al.  Some Recent Advances in Nonlinear Aeroelasticity: Fluid- Structure Interaction in the 21 st Century , 2010 .

[40]  Marco Morandini,et al.  H2 Periodic Control on Active Twist Rotor for Vibration Reduction , 2014 .

[41]  Robert C. Scott,et al.  Active control of wind-tunnel model aeroelastic response using neural networks , 2000, Smart Structures.

[42]  Ali H. Nayfeh,et al.  An analytical and experimental investigation into limit-cycle oscillations of an aeroelastic system , 2012, Nonlinear Dynamics.

[43]  A. Mannarino,et al.  Nonlinear aeroelastic reduced order modeling by recurrent neural networks , 2014 .

[44]  Sahjendra N. Singh,et al.  Output Feedback Modular Adaptive Control of a Nonlinear Prototypical Wing Section , 2004 .

[45]  P. Beran,et al.  Studies of Store-Induced Limit-Cycle Oscillations Using a Model with Full System Nonlinearities , 2004 .

[46]  Paolo Mantegazza,et al.  Characterisation of Anisotropic, Non-Homogeneous Beam Sections with Embedded Piezo-Electric Materials , 1997 .

[47]  Paolo Mantegazza,et al.  Coupled CSD/CFD non-linear aeroelastic trim of free-flying flexible aircraft , 2012 .

[48]  Weiwei Zhang,et al.  High Efficient Numerical Method for Limit Cycle Flutter Analysis Based on Nonlinear Aerodynamic Reduced Order Model , 2010 .