Meta-learning-based fault diagnosis method for rolling bearings under cross-working conditions

Abstract Accurate prediction of bearing failures is crucial for reducing maintenance costs and enhancing production efficiency in rotating machinery. However, the variable speed conditions and complex working environments encountered during operation pose significant challenges to fault diagnosis. Problems such as domain shift and insufficient sample quantity may occur during fault diagnosis under cross-working conditions, which can decrease the accuracy and generalization of deep learning algorithms. In this paper, we introduce a fault diagnosis framework grounded in meta-learning. Centered on a dual-channel feature fusion network and employing a meta-learning training paradigm, the framework not only performs well in cross-condition fault diagnosis tasks but also demonstrates superior performance in few-shot learning scenarios. Firstly, dual-channel network is used to extract the classification features of different domains, and the features are fused. Next, training is conducted using a meta-learning strategy to acquire prior knowledge, enabling rapid model adaptation to cross-working conditions and addressing the challenge of limited training samples. Finally, two public rolling bearing data sets are used to demonstrate the efficacy of the proposed method across different operational conditions. Prior to this, we selected the appropriate sample length and fusion domain through experimental validation. The proposed method also has good fault diagnosis accuracy in cross-device tasks. The experimental results verify the effective classification capability and robustness of the proposed method. Furthermore, comparisons with other meta-learning approaches confirm the superior performance of our method. The ablation experiments validated the importance and irreplaceability of each component of the proposed method.