Abstract:A semi-active controller-based neural network for nonlinear benchmark structure equipped with a magnetorheological (MR) damper is presented and evaluated. An inverse neural network model (INV-MR) is constructed to replicate the inverse dynamics of the MR damper. Next, linear quadratic Gaussian (LQG) controller is designed to produce the optimal control force. Thereafter, the LQG controller and the INV-MR models are linked to control the structure. The effectiveness of the INV-MR is illustrated and verified using simulated response of a full-scale, nonlinear, seismically excited, 3-story benchmark building excited by several historical earthquake records. The semi-active system using the INV-MR model is compared to the performance of an active system and a clipped optimal control (COC) system, which are based on the same nominal controller as is used in the INV-MR damper control algorithm. The results demonstrate that using the INV-MR model the MR damper force can be commanded to follow closely the desirable optimal control force. The results also show the control system is effective, and achieves similar performance to the active and COC system.

Keywords