[4F1-GS-10l] AI応用：製品の品質

[4F1-GS-10l-05] Development of AMD vibration control system using reinforcement learning (Part2 Deployment to wind sway control of buildings)

〇Yuya Aoyama¹, Koichi Nakatsuka¹, Takahiro Suzuki¹, Taku Yoshioka², Tetsuo Shiihashi², Tatsushi Nakano² (1. Obayashi Corporation, 2. Laboro.AI Inc.)

Keywords:Reinforcement Learning, AMD(Active Mass Damper), Vibration Control, Control Law, Vibration control

The purpose of this study was to obtain a high vibration control effect by learning a control law of AMD which reduces the horizontal vibration of the building due to the wind using reinforcement learning.
The simulation using the learned control law confirmed that the vibration control effect exceeded the control law by the conventional optimal control.