Unsupervised Method Based on Adversarial Domain Adaptation for Bearing Fault Diagnosis

This paper contributes to improving a bottleneck residual block-based feature extractor as set of layers for transforming raw data into features classification. structure is utilized avoid the issues deep learning network, such overfitting problems and low computational efficiency caused by redundant computation, high dimensionality, gradient vanishing. With this structure, domain adversarial neural network (DANN), unsupervised model, maximum classifier discrepancy (MCD), adaptation have been applied conduct binary classification fault diagnosis data. In addition, pseudo-label MCD comparison with original one. comparison, several popular models are selected transferability estimation analysis. The experimental results shown that DANN improved achieved accuracy, 96.84% 100%, respectively. Meanwhile, after using semi-supervised learning, average accuracy model increased 15%, increasing 94.19%.