Control performance of a smart tuned mass damper (TMD) mainly depends on control algorithms. A lot of control strategies have been proposed for semi-active control devices. Recently, machine learning begins to be applied to development of vibration control algorithm. In this study, a reinforcement learning among machine learning techniques was employed to develop a semi-active control algorithm for a smart TMD. The smart TMD was composed of magnetorheological damper in this study. For this purpose, an 11-story building structure with a smart TMD was selected to construct a reinforcement learning environment. A time history analysis of the example structure subject to earthquake excitation was conducted in the reinforcement learning procedure. Deep Q-network (DQN) among various reinforcement learning algorithms was used to make a learning agent. The command voltage sent to the MR damper is determined by the action produced by the DQN. Parametric studies on hyper-parameters of DQN were performed by numerical simulations. After appropriate training iteration of the DQN model with proper hyper-parameters, the DQN model for control of seismic responses of the example structure with smart TMD was developed. The developed DQN model can effectively control smart TMD to reduce seismic responses of the example structure.

This paper is concerned with an experimental research to control of random vibration caused by external loads specially in cable-stayed bridges which tend to be structurally flexible. For the vibration control, we produced a model structure modelled on Seohae Grand Bridge, and we designed a shear type MR damper. On the center of its middle span, we placed a shear type MR damper which was to control its vibration and also acquire its structural responses such as displacement and acceleration at the same site. The experiments concerning controlling vibration were performed according to a variety of theories including un-control, passive on/off control, and clipped-optimal control. Its control performance was evaluated in terms of the absolute maximum displacements, RMS displacements, the absolute maximum accelerations, RMS accelerations, and the total power required to control the bridge which differ from each different experiment method. Among all the methods applied in this paper, clipped-optimal control method turned out to be the most effective to reduces of displacements, accelerations, and external power. Finally, It is proven that the clipped-optimal control method was effective and useful in the vibration control employing a semi-active devices such MR damper.