Bounding set calculation for neural network-based output feedback adaptive control systems

Evaluating the bounding set of dynamic systems subject to direct neural-adaptive control is a critical issue in applications where the control system must undergo a rigorous verification process in order to comply with certification standards. In this paper, the boundedness problem is addressed for a comprehensive class of uncertain dynamic systems. Several common but unnecessary approximations that are typically performed to simplify the Lyapunov analysis have been avoided in this effort. This leads to a more accurate and general formulation of the bounding set for the overall closed loop system. The conditions under which boundedness can be guaranteed are carefully analyzed; additionally, the interactions between the control design parameters, the ‘Strictly Positive Realness’ condition, and the shape and dimensions of the bounding set are discussed. Finally, an example is presented in which the bounding set is calculated for the neuro-adaptive control of an F/A-18 aircraft, along with a numerical study to evaluate the effect of several design parameters.

[1]  Károly Jordán.  Calculus of finite differences , 1951 .

[2]  Naira Hovakimyan,et al.  Neural Network Adaptive Control for a Class of Nonlinear Uncertain Dynamical Systems With Asymptotic Stability Guarantees , 2008, IEEE Transactions on Neural Networks.

[3]  Marcello R. Napolitano,et al.  Calculation of Bounding Sets for Neural Network Based Adaptive Control Systems , 2008 .

[4]  Petros A. Ioannou,et al.  Robust Adaptive Control , 2012 .

[5]  Manolis A. Christodoulou,et al.  High-order neural networks for the learning of robot contact surface shape , 1997, IEEE Trans. Robotics Autom..

[6]  P. Varaiya,et al.  Ellipsoidal Toolbox (ET) , 2006, Proceedings of the 45th IEEE Conference on Decision and Control.

[7]  Marcelo M. Lamego.  Adaptive structures with algebraic loops , 2001, IEEE Trans. Neural Networks.

[8]  Frank L. Lewis,et al.  Multilayer neural-net robot controller with guaranteed tracking performance , 1996, IEEE Trans. Neural Networks.

[9]  Eduardo D. Sontag,et al.  Neural Networks for Control , 1993 .

[10]  Ieee Std,et al.  IEEE Standard for Software Verification and Validation , 2008 .

[11]  Marios M. Polycarpou,et al.  Backstepping-Based Flight Control with Adaptive Function Approximation , 2005 .

[12]  Anthony J. Calise,et al.  Several Extensions in Methods for Adaptive Output Feedback Control , 2004, IEEE Transactions on Neural Networks.

[13]  Anthony J. Calise,et al.  A novel error observer-based adaptive output feedback approach for control of uncertain systems , 2002, IEEE Trans. Autom. Control..

[14]  Mario Innocenti,et al.  Neural network augmentation of linear controllers with application to underwater vehicles , 2000, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

[15]  L. Praly,et al.  Adaptive nonlinear regulation: estimation from the Lyapunov equation , 1992 .

[16]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[17]  Anthony J. Calise,et al.  Adaptive output feedback control of nonlinear systems using neural networks , 2000, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

[18]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[19]  K. Narendra,et al.  Stable adaptive controller design--Direct control , 1978 .

[20]  Anthony J. Calise,et al.  Neural-Network Augmentation of Existing Linear Controllers , 2001 .

[21]  Naira Hovakimyan,et al.  Design and Analysis of a Novel ${\cal L}_1$ Adaptive Control Architecture With Guaranteed Transient Performance , 2008, IEEE Transactions on Automatic Control.

[22]  Junmin Li,et al.  Decentralized Output-Feedback Neural Control for Systems With Unknown Interconnections , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[23]  Cong Wang,et al.  Learning from neural control , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[24]  Hartmut Logemann,et al.  Multivariable feedback design : J. M. Maciejowski , 1991, Autom..

[25]  Anthony J. Calise,et al.  Nonlinear flight control using neural networks , 1994 .

[26]  Robert S. Eick.  A RECONFIGURATION SCHEME FOR FLIGHT CONTROL ADAPTATION TO FIXED-POSITION ACTUATOR FAILURES , 2003 .

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