Substructural neural network controller

Abstract A substructure-based neural network is proposed for the active control of flexible structures. A flexible structure is divided into substructures. Subsequently, subcontrollers are designed for these substructures using the linear quadratic regulator (LQR) control method. These subcontrollers are assembled to obtain the central feedback controller for the whole structure. A radial basis function neural network is trained to emulate the behavior of this central controller designed from substructure levels. The training is based only on the outputs of sensors collocated with the actuators. Therefore, two distinct advantages of the proposed neural network controller are noted as its training being based on substructural LQR controller and collocated sensor data. The performance of the neural network controller is compared favorably with the complete structural LQR controller for various input forces acting on a large flexible structure.

[1]  H. Öz,et al.  Structral–control optimization with H2- and H-norm bounds , 1997 .

[2]  Singiresu S Rao,et al.  A substructures method for the active control design of large periodic structures , 1997 .

[3]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[4]  Edward F. Crawley,et al.  Development of Structural Uncertainty Models , 1997 .

[5]  Nesbitt W. Hagood,et al.  Simultaneous Piezoelectric Sensing/Actuation: Analysis And Application To Controlled Structures , 1994 .

[6]  Anthony Tzes,et al.  Neural network design with genetic learning for control of a single link flexible manipulator , 1994, J. Intell. Robotic Syst..

[7]  Edward F. Crawley,et al.  Classically Rationalized Low-Order, Robust Structural Controllers , 1998 .

[8]  Peter H. Meckl,et al.  An analytical comparison of a neural network and a model-based adaptive controller , 1993, IEEE Trans. Neural Networks.

[9]  H. Flashner,et al.  Neural network based tracking control for mechanical systems , 1997, Proceedings of the 36th IEEE Conference on Decision and Control.

[10]  Edward F. Crawley,et al.  MULTIVARIABLE HIGH-AUTHORITY CONTROL OF PLATE-LIKE ACTIVE STRUCTURES , 1992 .

[11]  Seul Jung,et al.  A new neural network control technique for robot manipulators , 1995, Robotica.

[12]  H. Öz,et al.  Structral–control optimization withH2- andH∞-norm bounds , 1997 .

[13]  András Lörincz,et al.  Neurocontroller using dynamic state feedback for compensatory control , 1997, Neural Networks.

[14]  Billie F. Spencer,et al.  Models for hysteresis and application to structural control , 1997, Proceedings of the 1997 American Control Conference (Cat. No.97CH36041).

[15]  Robert E. Skelton Some open problems in structural control , 1995, Proceedings of 1995 American Control Conference - ACC'95.

[16]  Frank L. Lewis,et al.  A neural network controller for flexible-link robots , 1996, J. Intell. Robotic Syst..

[17]  Edward F. Crawley,et al.  Intelligent structures for aerospace - A technology overview and assessment , 1994 .

[18]  Frank L. Lewis,et al.  Output feedback control of rigid robots using dynamic neural networks , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[19]  Singiresu S Rao,et al.  Substructure decomposition method for the control design of large flexible structures , 1992 .

[20]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[21]  Lee A. Feldkamp,et al.  Neural network control of a four-wheel ABS model , 1994, Proceedings of 1994 37th Midwest Symposium on Circuits and Systems.

[22]  Tzu-Jeng Su,et al.  Substructure-based controller design method for flexible structures , 1995 .

[23]  R. Guyan Reduction of stiffness and mass matrices , 1965 .