A Semi-Supervised Intelligent Fault Diagnosis Method for Bearings Under Low Labeled Rates

Fault diagnosis is of great significance for ensuring the reliability and safety of electromechanical equipment. However, in practical applications, the cost of labeling samples is high, which poses difficulties for most supervised fault diagnosis models that rely on a large number of labeled samples for training. Therefore, this article proposes a novel semi-supervised fault diagnosis method for bearings under low labeled rates, which has the following characteristics: first, the first convolutional layer of the feature extraction network is reconstructed using the idea of the wavelet transform, addresses the challenges of ineffective learning of the layer caused by long gradient propagation distance, consequently enhancing the feature extraction capability. Second, a semi-supervised loss is defined through pseudolabeling, which makes the boundaries between different classes more explicit in the feature space. Third, a new learning strategy is also designed for this process to overcome the confirmation bias problem. The experimental results based on a widely used public dataset and two real testbeds show that the proposed method achieves satisfactory diagnosis performance at labeled rates as low as 1.25%-5% and is superior to other classic and latest models.