电子科技2026，Vol.39Issue(4)：71-78,8.DOI:10.16180/j.cnki.issn1007-7820.2026.04.010
基于改进高斯原型网络的小样本轴承故障诊断方法
A Small Sample Bearing Fault Diagnosis Method Based on Improved Gaussian Prototype Network
摘要
Abstract
In view of the problem of low fault diagnosis accuracy caused by insufficient fault sample data for ro-tating machinery bearings in practical applications,this study proposes an improved Gaussian prototype network for few-shot fault diagnosis.Vibration signals are converted into time-frequency images using continuous wavelet trans-form,and a convolutional attention module is introduced to optimize the residual network structure,which serves as the feature extraction network of the Gaussian prototype network.The FCM(Fuzzy C-Means Clustering,)algorithm is incorporated to optimize the Gaussian prototype network's ability to distinguish subtle fault categories through a soft classification strategy.Few-shot experiments under varying working conditions are conducted using the bearing data-sets from Case western reserve university and the university of Paderborn.The experimental results show that the ac-curacy of the improved Gaussian prototype network reaches 91.17%and 89.95%,respectively,indicating that the proposed method achieves a significant improvement in fault recognition accuracy when compared with other models.关键词
元学习/残差网络/小样本/高斯原型网络/故障诊断/模糊C均值聚类/深度学习/变工况Key words
meta-learning/residual network/limited samples/Gaussian prototype network/fault diagnosis/fuzzy C-means clustering/deep learning/variable operating condition分类
信息技术与安全科学引用本文复制引用
马相春,董宝力..基于改进高斯原型网络的小样本轴承故障诊断方法[J].电子科技,2026,39(4):71-78,8.基金项目
浙江省自然科学基金(LY16F020024)Natural Science Foundation of Zhejiang(LY16F020024) （LY16F020024）
