EXPERIMENTAL STUDY OF IDENTIFICATION AND CONTROL OF STRUCTURES USING NEURAL NETWORK PART 2: CONTROL

SUMMARY Experimental veri"cations of a recently developed active structural control method using neural networks are presented in this paper. The experiments were performed on the earthquake simulator at the University of Illinois at Urbana*Champaign. The test specimen was a 1/4 scale model of a three-storey building. The control system consisted of a tendon/pulley system controlled by a single hydraulic actuator at the base. The control mechanism was implemented through four active pre-tensioned tendons connected to the hydraulic actuator at the "rst #oor. The structure modelling and system identi"cation has been presented in a companion paper. (Earthquake Engng. Struct. Dyn. 28, 995}1018 (1999)). This paper presents the controller design and implementation. Three controllers were developed and designed: two neurocontrollers, one with a single sensor feedback and the other with three sensor feedback, and one optimal controller with acceleration feedback. The experimental design of the neurocontrollers is accomplished in three steps: system identi"cation, multiple emulator neural networks training and "nally the neurocontrollers training with the aid of multiple emulator neural networks. The e!ectiveness of both neurocontrollers are demonstrated from experimental results. The robustness and the relative stability are presented and discussed. The experimental results of the optimal controller performance is presented and assessed. Comparison between the optimal controller and neurocontrollers is presented and discussed. Copyright ( 1999 John Wiley & Sons, Ltd.

[1]  Fereidoun Amini,et al.  Neural Network for Structure Control , 1995 .

[2]  T. T. Soong,et al.  EXPERIMENTAL DIGITAL CONTROL OF STRUCTURES , 1989 .

[3]  Huibert Kwakernaak,et al.  Linear Optimal Control Systems , 1972 .

[4]  Jamshid Ghaboussi,et al.  Active Control of Structures Using Neural Networks , 1995 .

[5]  J. Ghaboussi,et al.  Application of multi-layered feedforward neural networks in digital vibration control , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[6]  James T. P. Yao,et al.  CONCEPT OF STRUCTURAL CONTROL , 1972 .

[7]  Stephen P. Schneider,et al.  Experimental study of identification and control of structures using neural network. Part 1: identification , 1999 .

[8]  T. T. Soong,et al.  Acceleration Feedback Control of MDOF Structures , 1996 .

[9]  Jamshid Ghaboussi.  Some Applications of Neural Networks in Structural Engineering , 1994 .

[10]  Michael Moortgat,et al.  Structural control , 1997 .

[11]  Jamshid Ghaboussi,et al.  Actuator Dynamics and Delay Compensation Using Neurocontrollers , 1996 .

[12]  Shirley J. Dyke,et al.  Implementation of an active mass driver using acceleration feedback control , 1996 .

[13]  Jamshid Ghaboussi,et al.  Autoprogressive training of neural network constitutive models , 1998 .

[14]  T. T. Soong,et al.  Full-Scale Implementation of Active Control. II: Installation and Performance , 1993 .

[15]  Khaldoon A. Bani-Hani,et al.  NONLINEAR STRUCTURAL CONTROL USING NEURAL NETWORKS , 1998 .

[16]  T. T. Soong,et al.  Experiments on Active Control of Seismic Structures , 1988 .

[17]  Jamshid Ghaboussi,et al.  Neural networks for structural control of a benchmark problem, active tendon system , 1998 .

[18]  D. Naidu,et al.  Optimal Control Systems , 2018 .

[19]  T. T. Soong,et al.  Full‐Scale Implementation of Active Control. I: Design and Simulation , 1991 .