Cross-Condition Fault Diagnosis with Limited Data: A Multi-Loss Adversarial Framework and Efficient Feature Learning

Bearing fault diagnosis based on deep learning methods has been widely used. However, it is difficult to collect sufficient bearing fault samples in an industrial environment, which greatly limits the effective training of deep learning models. To address the challenges of feature extraction difficulty and low diagnostic accuracy in deep learning models under small-sample conditions, this paper proposes a small-sample transfer learning diagnostic method called Multi-Loss Domain Adversarial Network (MLDAN) based on multi-loss domain adversarial techniques. Additionally, a feature extractor tailored for small-sample issues, named Conv-SCMABlock-MSCABlock network (CSMN), is introduced. Firstly, the vibration signals of rolling bearings from diverse domains are preprocessed using the Fast Fourier Transform (FFT), and subsequently, these processed signals are fed into the CSMN. The gradient reversal layer of MLDAN is then employed to facilitate adversarial learning between the CSMN and the domain discriminators. To further minimize domain discrepancies, an adaptive MK-MMD loss function is introduced to reduce the distribution differences between the source and target domains, whereas a contrastive loss function with a soft-margin mechanism is applied to enhance feature discriminability. Finally, fault classification was performed using a fault classifier, and the proposed multi-loss domain adversarial optimization strategy was tested on the CWRU and PU datasets under the limited data condition of containing only 50 samples for each fault type in the target domain, with an average accuracy as high as 99.36% and 97.38%, respectively. The results show that the proposed method achieved significant results for both datasets.