MLDA-GLFD: a multi-layer domain-adaptive rolling bearing fault diagnosis method fusing global and local features

Abstract In the field of fault diagnosis, transfer learning methods have achieved remarkable progress in rolling bearing fault diagnosis. However, existing approaches still face challenges in feature extraction and feature alignment between source and target domains, which remains difficult for feature networks to effectively capture both local and global features, and the distribution discrepancies between the two domains further degrade the performance of transfer models. To address these issues, this paper proposes a multi-layer domain-adaptive fault diagnosis method which integrates global and local feature discovery (MLDA-GLFD) modules. Specifically, a strengthened local feature extraction (SLFE) module is designed by combining depthwise separable convolution with partial convolution to capture local feature information more precisely. In addition, a global feature aggregation block (GFAB) is constructed, which incorporates a multi-head self-attention mechanism, a global context block and a pyramid pooling module to jointly strengthen global feature extraction. To further achieve feature distribution alignment between the source and target domains, a dynamic convolution module with a hierarchical domain alignment mechanism is designed to adaptively adjust the receptive field of convolutional kernels. Moreover, a combination of maximum mean discrepancy (MMD) and multiple kernel MMD is employed to accurately align inter-domain features, thereby enhancing the model’s transferability to the target domain. Experimental results on two rolling bearing datasets, CWRU and Shandong University of Science and Technology, demonstrate that the proposed MLDA-GLFD method achieves average accuracies of 96% and 94%, respectively, significantly outperforming other comparative methods.