A reinforcement transfer learning method based on a policy gradient for rolling bearing fault diagnosis

Abstract

Accurate rolling bearing fault diagnosis is a basic guarantee of the safe operation of rotating machinery. Therefore, it is critical to select an appropriate fault diagnosis model. Selecting the optimal structure for intelligent fault diagnosis model has gradually become a research hot spot. At the same time, in practical engineering, sufficient data cannot always be guaranteed, which also increases the difficulty of accurate fault diagnosis. This paper proposes a reinforcement transfer learning method based on a policy gradient to identify the optimal structure of an intelligent fault diagnosis model when the number of training samples is insufficient. First, a policy gradient method is used to select the optimal child model in the source domain. Second, a transfer learning method is adopted to transfer the hyperparameters of the optimal child model from the source domain to the target domain. Finally, a small number of labeled training samples are used to fine-tune this model in the target domain. An adequate number of experiments proved the viability of proposed method, confirming the importance of the autonomous selection of a diagnostic model structure.