Deep Residual Joint Transfer Strategy for Cross-Condition Fault Diagnosis of Rolling Bearings

Abstract

Rolling bearings are key components of the drivetrain in wind turbines, and their health is critical to wind turbine operation. In practical diagnosis tasks, the vibration signal is usually interspersed with many disturbing components, and the variation of operating conditions leads to unbalanced data distribution among different conditions. Although intelligent diagnosis methods based on deep learning have been intensively studied, it is still challenging to diagnose rolling bearing faults with small amounts of samples. To address the above issue, we introduce the deep residual joint transfer strategy method for the cross-condition fault diagnosis of rolling bearings. One-dimensional vibration signals are pre-processed by overlapping feature extraction techniques to fully extract fault characteristics. The deep residual network is trained in training tasks with sufficient samples, for fault pattern classification. Subsequently, three transfer strategies are used to explore the generalizability and adaptability of the pre-trained models to the data distribution in target tasks. Among them, the feature transferability between different tasks is explored by model transfer, and it is validated that minimizing data differences of tasks through a dual-stream adaptation structure helps to enhance generalization of the models to the target tasks. In the experiments of rolling bearing faults with unbalanced data conditions, localized faults of motor bearings and planet bearings are successfully identified, and good fault classification results are achieved, which provide guidance for the cross-condition fault diagnosis of rolling bearings with small amounts of training data.

Conflict of Interest Statement

The authors declare no conflicts of interest.