Multiscale Residual Antinoise Network via Interpretable Dynamic Recalibration Mechanism for Rolling Bearing Fault Diagnosis With Few Samples

Deep learning (DL)-based rolling bearing fault diagnosis method has made significant achievements, but its diagnostic performance is still limited by few samples. Aiming at this problem, a novel intelligent fault diagnosis (IFD) method for rolling bearings, named multiscale residual antinoise network (MRANet) via interpretable dynamic recalibration mechanism (DRM), is proposed. First, the raw vibration signal is generated into a time–frequency diagram with more characteristic domains by short-time Fourier transform (STFT). Then, the shallow mechanism and deep discriminable features are extracted using multibranch dilated convolution and improved residual blocks. Simultaneously, the DRM assists the feature extractor to adaptively adjust the feature weights from the spatial position and the channel information ratio to enhance the local impulse excitation. Furthermore, the corrective effect of DRM on the feature extractor is visualized, which improves the interpretability of the network. Comparative experiments are conducted with other popular IFD methods on public and Lanzhou University of Technology (LUT) bearing dataset, and the results show that MRANet can exhibit superior diagnostic performance with few samples under variable load and multispeed conditions.