A new learning algorithm for neural network state estimation in active vibration control

The authors present a numerical study related to the active control of the vibrations of a cantilevered beam with piezoelectric actuators using the modified independent modal space control (MIMSC) algorithm coupled with a neural network (NN) for state estimation. Among other control strategies the MIMSC algorithm has been shown to have excellent closed-loop structural damping. Such an algorithm requires as input data the modal displacements and velocities of the vibrating beam. A neural network, trained with an extended backpropagation learning algorithm, is proposed as an alternative approach to classic estimation structure for the on-line estimation of the modal parameters. This particular modification of the backpropagation (BP) algorithm introduces heterogeneous processing elements for the hidden and output layers. The results of a numerical study using the standard and extended BP algorithms are presented and discussed.

[1]  Arthur Gelb,et al.  Applied Optimal Estimation , 1974 .

[2]  M. Balas.  Direct Velocity Feedback Control of Large Space Structures , 1979 .

[3]  L. Meirovitch,et al.  Optimal Modal-Space Control of Flexible Gyroscopic Systems , 1980 .

[4]  L. Meirovitch,et al.  CONTROL OF SELF-ADJOINT DISTRIBUTED-PARAMETER SYSTEMS. , 1980 .

[5]  Leonard Meirovitch,et al.  Control of Self -Adj oint Distributed-Parameter Systems , 1982 .

[6]  Leonard Meirovitch,et al.  A comparison of control techniques for large flexible systems , 1983 .

[7]  Richard W. Longman,et al.  On the Number and Placement of Actuators for Independent Modal Space Control , 1984 .

[8]  T. Bailey,et al.  Distributed Piezoelectric-Polymer Active Vibration Control of a Cantilever Beam , 1985 .

[9]  Bernard Widrow,et al.  Adaptive Signal Processing , 1985 .

[10]  L. Meirovitch,et al.  The implementation of modal filters for control of structures , 1985 .

[11]  A. Baz,et al.  A comparison between IMSC, PI and MIMSC methods in controlling the vibration of flexible systems , 1987 .

[12]  E. Crawley,et al.  Use of piezoelectric actuators as elements of intelligent structures , 1987 .

[13]  S. Poh,et al.  Performance of an active control system with piezoelectric actuators , 1988 .

[14]  H. Tzou,et al.  Active vibration isolation by polymeric piezoelectret with variable feedback gains , 1988 .

[15]  S. Poh,et al.  Modified Independent Modal Space Control Method for Active Control of Flexible Systems , 1989 .

[16]  Craig S. Sims,et al.  Innovation approach to reduced-order estimation of complementary states. , 1989 .

[17]  S. Poh,et al.  Experimental implementation of the modified independent modal space control method , 1990 .

[18]  Amr M. Baz,et al.  Active Control of a Flexible Structure Using a Modal Positive Position Feedback Controller , 1990 .

[19]  Amr M. Baz,et al.  A neural observer for dynamic systems , 1992 .

[20]  R. S. Nutter,et al.  An extended back-propagation learning algorithm by using heterogeneous processing units , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[21]  M. Napolitano,et al.  Application of a neural observer as state estimator in active vibration control of a cantilevered beam , 1992 .

[22]  S. Poh,et al.  Independent Modal Space Control With Positive Position Feedback , 1992 .