Nonlinear control of structure using neuro-predictive algorithm

Abstract

A new neural network (NN) predictive controller (NNPC) algorithm has been developed and tested in the computer simulation of active control of nonlinear structure. In the present method an NN is used as an emulator. This emulator NN has been trained to predict the future response of the structure. Then, it’s employed to determine the control force in order to minimize the difference between the predicted and desired responses via a numerical minimization algorithm. Since the NNPC controller is very time consuming and not suitable for real-time control, it is then used to train an NN controller. The approach is validated by using simulated response of a nonlinear benchmark building excited by several historical earthquake records. Then, fragility curves are generated to consider the effectiveness of the controller on probability of damage. The simulation results are then compared with a linear quadratic Gaussian (LQG) active controller. The results indicate that the proposed algorithm is completely effective in relative displacement reduction