A Self-Adaptive Vibration Reduction Method Based on Deep Deterministic Policy Gradient (DDPG) Reinforcement Learning Algorithm

Although many adaptive techniques for active vibration reduction have been designed to achieve optimal performance in practical applications, few are related to reinforcement learning (RL). To explore the best performance of the active vibration reduction system (AVRS) without prior knowledge, a self-adaptive parameter regulation method based on the DDPG algorithm was examined in this study. The DDPG algorithm is unsuitable for a random environment and prone to reward-hacking. To solve this problem, a reward function optimization method based on the integral area of the decibel (dB) value between transfer functions was investigated. Simulation and graphical experimental results show that the optimized DDPG algorithm can automatically track and maintain optimal control performance of the AVRS.