Neuro-PD Controller of Structural System to Mitigate Earthquake Vibrations

In this paper, stabilization of the structural system against earthquake is presented. Because the conventional PD controller is popular and simple in design, our controller is based on PD controller. The main problem of such a controller is its inability to produce desired response and instability against variations in the properties of the structural system. To obviate this issue, the neural network is implemented to tune the gains of the PD controller. Not only the stability of the closed loop system in the presence of structural uncertainty is warranted but also the closed loop system has a more suitable response when it is compared with fixed gains PD controller. The simulation results show the outperformance of the closed loop system.