Multi-condition bearing fault diagnosis method based on RP–MBRN

Abstract

To address the challenge of extracting invariant bearing fault features under multi-working conditions, an enhanced multi-branch bias residual network (MBRN) based on multi-branch bias and folding calculation is proposed. First, in constructing the fault dataset, the original bearing fault signal is transformed into two-dimensional feature images using recurrent plot. Second, to replace the original residual connection, a multi-branch bias structure is constructed, and the feature tensors in different branches are transformed by idle operation and folding operation. This strategy has improved the diagnostic model’s ability to extract invariant bearing fault features under multi-working conditions. Finally, MBRN is trained using the above fault dataset to achieve fault diagnosis under different bearing conditions. The performance of the proposed diagnostic model was validated on two multi-condition bearing fault datasets and two variable condition bearing datasets. The experimental results demonstrate that the average diagnostic accuracy of the proposed MBRN is 4.05% higher than that of the original MBRN. Furthermore, even when reducing the size of the fault dataset to 20% of its original size, the proposed MBRN still improves diagnostic accuracy by an average of 2.2%.