Multikernel correntropy transfer robust dictionary learning and its application in bearing fault diagnosis

Detecting subtle fault signatures in vibration signals, masked by intense, non-Gaussian noise, poses a major challenge for the early diagnosis of bearing faults. This paper presents a novel multikernel correntropy transfer robust dictionary learning (MKC-TRDL) framework designed to address the challenges in bearing fault diagnosis. MKC-TRDL incorporates a multikernel correntropy-based data fidelity term, specifically crafted to minimize the impact of outliers, thereby ensuring more robust fault feature extraction. Furthermore, a transfer regularization term is introduced to guide the target dictionary to remain closely aligned with the source dictionary, striking an effective balance between preserving general signal features and adapting to the specific operating conditions of the bearing. This approach significantly enhances the robustness of the approach and its capacity to perform reliably in dynamic and noisy environments. Simulations and experimental results show that the MKC-TRDL method effectively extracts early bearing fault features, particularly in the presence of strong complex noise.