Active control of flexible rotors using deep reinforcement learning with application of multi-actor-critic deep deterministic policy gradient

Maheed H. Ahmed, Abdullah AboHussien, Aly El-Shafei, Ahmed M. Darwish, Ahmed H. Abdel-Gawad

Abstract: Highlights•Extended DDPG to work in a periodic system with multi actors and critics (MAC-DDPG).•Developed a vibration controller for rotating machinery using MAC-DDPG.•Successfully applied automatic balancing yielding up to 93% vibration reduction.•Successfully eliminated oil whip instability with the proposed controller.