Open Access

ARTICLE

Hybrid Attention-Driven Transfer Learning with DSCNN for Cross-Domain Bearing Fault Diagnosis under Variable Operating Conditions

Qiang Ma^1,2,3,4, Zepeng Li^1,2, Kai Yang^1,2,*, Shaofeng Zhang^1,2, Zhuopei Wei^1,2

1 School of Mechanical and Equipment Engineering, Hebei University of Engineering, Handan, 056038, China
2 Key Laboratory of Intelligent Industrial Equipment Technology of Hebei Province, Hebei University of Engineering, Handan, 056038, China
3 Department of Mechanics, Tianjin University, Tianjin, 300354, China
4 National Demonstration Center for Experimental Mechanics Education, Tianjin University, Tianjin, 300354, China

* Corresponding Author: Kai Yang. Email:

Structural Durability & Health Monitoring 2025, 19(6), 1607-1634. https://doi.org/10.32604/sdhm.2025.069876

Received 02 July 2025; Accepted 05 September 2025; Issue published 17 November 2025

Abstract

Effective fault identification is crucial for bearings, which are critical components of mechanical systems and play a pivotal role in ensuring overall safety and operational efficiency. Bearings operate under variable service conditions, and their diagnostic environments are complex and dynamic. In the process of bearing diagnosis, fault datasets are relatively scarce compared with datasets representing normal operating conditions. These challenges frequently cause the practicality of fault detection to decline, the extraction of fault features to be incomplete, and the diagnostic accuracy of many existing models to decrease. In this work, a transfer-learning framework, designated DSCNN-HA-TL, is introduced to address the enduring challenge of cross-condition diagnosis in rolling-bearing fault detection. The framework integrates a window global mixed attention mechanism with a deep separable convolutional network, thereby enabling adaptation to fault detection tasks under diverse operating conditions. First, a Convolutional Neural Network (CNN) is employed as the foundational architecture, where the original convolutional layers are enhanced through the incorporation of depthwise separable convolutions, resulting in a Depthwise Separable Convolutional Neural Network (DSCNN) architecture. Subsequently, the extraction of fault characteristics is further refined through a dual-branch network that integrates hybrid attention mechanisms, specifically windowed and global attention mechanisms. This approach enables the acquisition of multi-level feature fusion information, thereby enhancing the accuracy of fault classification. The integration of these features not only optimizes the characteristic extraction process but also yields improvements in accuracy, representational capacity, and robustness in fault feature recognition. In conclusion, the proposed method achieved average precisions of 99.93% and 99.55% in transfer learning tasks, as demonstrated by the experimental results obtained from the CWRU public dataset and the bearing fault detection platform dataset. The experimental findings further provided a detailed comparison between the diagnostic models before and after the enhancement, thereby substantiating the pronounced advantages of the DSCNN-HA-TL approach in accurately identifying faults in critical mechanical components under diverse operating conditions.

---

Keywords

---