Adaptive feedforward control for dynamically substructured systems based on neural network compensation

Abstract The potential applications of dynamically substructured systems (DSS) with both numerical and physical substructures can be found in diverse dynamics testing fields. In this paper, a feedforward adaptive controller based on a neural network (NN) is proposed to improve the DSS testing performance. To facilitate the NN compensation design, a modified DSS framework is developed so that the DSS control can be considered as a regulation problem with disturbance rejection. Then an NN feedforward compensation technique is proposed to cope with uncertainties and nonlinearities in the DSS physical substructure. The proposed NN technique generalizes the existing results in the literature. Real-time experimental results on a mechanical test rig demonstrate the improved performance by using the NN compensation strategy.

[1]  David J. Wagg,et al.  Substructuring of dynamical systems via the adaptive minimal control synthesis algorithm , 2001 .

[2]  Chun-Liang Lin,et al.  Adaptive feedforward control for disturbance torque rejection in seeker stabilizing loop , 2001, IEEE Trans. Control. Syst. Technol..

[3]  Marios M. Polycarpou,et al.  Stable adaptive neural control scheme for nonlinear systems , 1996, IEEE Trans. Autom. Control..

[4]  Stanislaw H. Zak,et al.  Combined observer-controller synthesis for uncertain dynamical systems with applications , 1988, IEEE Trans. Syst. Man Cybern..

[5]  Frank L. Lewis,et al.  Neural Network Control Of Robot Manipulators And Non-Linear Systems , 1998 .

[6]  Martin S. Williams,et al.  Laboratory testing of structures under dynamic loads: an introductory review , 2001, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[7]  Dimitry Gorinevsky,et al.  RBF network feedforward compensation of load disturbance in idle speed control , 1996 .

[8]  David P Stoten,et al.  Adaptive control of dynamically substructured systems: The single-input single-output case , 2006 .

[9]  Andrew Plummer,et al.  Model-in-the-Loop Testing , 2006 .

[10]  Guang Li,et al.  Model predictive control of dynamically substructured systems with application to a servohydraulically-actuated mechanical plant , 2010 .

[11]  Guang Li,et al.  A novel robust disturbance rejection anti-windup framework , 2011, Int. J. Control.

[12]  Chen-Chung Liu,et al.  Adaptively controlling nonlinear continuous-time systems using multilayer neural networks , 1994, IEEE Trans. Autom. Control..

[13]  Frank L. Lewis,et al.  Feedforward control based on neural networks for disturbance rejection in hard disk drives , 2009 .

[14]  Frank L. Lewis,et al.  Neural network compensation control for mechanical systems with disturbances , 2009, Autom..

[15]  Guang Li,et al.  Synthesis and control of generalized dynamically substructured systems , 2009 .

[16]  Delbert Tesar,et al.  Dynamic modeling of serial manipulator arms , 1981 .

[17]  David J. Wagg,et al.  Control issues relating to real‐time substructuring experiments using a shaking table , 2005 .

[18]  F. Lewis,et al.  Neural Network Control of Robot Arms and Nonlinear Systems , 1997 .

[19]  Marko Bacic,et al.  A novel controller design methodology for uncertain non-linear hardware-in-the-loop simulators , 2007, 2007 46th IEEE Conference on Decision and Control.

[20]  Marios M. Polycarpou,et al.  High-order neural network structures for identification of dynamical systems , 1995, IEEE Trans. Neural Networks.

[21]  Martin S. Williams,et al.  Stability and Delay Compensation for Real-Time Substructure Testing , 2002 .

[22]  Tao Zhang,et al.  Stable Adaptive Neural Network Control , 2001, The Springer International Series on Asian Studies in Computer and Information Science.