ABSTRACT
Accurately and intelligently identifying faults of the planetary gearbox is essential for the safe and reliable operation and maintenance of the mechanical drive system. Recently, fault diagnosis of planetary gearbox has gained tremendous progress, especially with the rising popularity of deep learning (DL). However, most methods are standard supervised learning where the input is directly mapped to a fault type, and with strong feedback. Also, their learning ways are static, unlike human learning, which gradually acquires knowledge by interacting with the environment. To a certain extent, these deficiencies reduce the generalization and intelligence level of DL-based fault diagnosis methods. Besides, due to harsh working conditions, signals acquired often have strong noise and nonlinear features, leading to relatively low accuracy if raw signals are directly used as the input. Thus, this chapter proposes a new fault diagnosis method based on time-frequency representation and deep reinforcement learning (DRL). Experimental results show that this method achieves better generalization and stability in single-speed load cases and outperforms others in multi-work conditions.
