基于对比学习和卷积自注意力网络的少标记样本减速机故障诊断方法OA

[Objectives]To address the challenge of low fault diagnosis accuracy in traditional neural net-works with few labeled samples,a method based on contrastive learning and convolution transformer network is proposed.[Methods]First,raw monitoring data are transformed into similar sample pairs by data aug-mentation.These similar sample pairs are then mapped to a deep feature space by a feature extractor.A trans-former network is utilized to design cross-prediction tasks for both local and global comparisons,facilitating the clustering of data with the same fault type by comparing the intrinsic similarity between the same batches of data.Finally,the downstream classification network is trained with few labeled samples to improve the di-agnostic performance of the proposed model.[Results]The effectiveness of the proposed method is validat-ed using a self-built reducer test rig.The results show that accuracy of the proposed method reaches 98.38%with few labeled samples,showing significant advantages over existing methods.[Conclusions]The re-search results can provide the key technology for fault diagnosis of industrial equipment with few labeled sam-ples,contributing to the advancement of intelligent manufacturing.