针对滚动轴承在小样本条件下诊断准确率低和泛化性弱的问题，提出了一种基于注意力特征融合的深度稳定学习(Attention Feature Fusion and Deep Stable Learning，AFF-Stablenet)模型的故障诊断方法。该方法首先使用经验模态分解(Empirical Mode Decompositim，EMD)将样本分解成多段频率的子信号，求取子信号与原始信号的互相关系数，选择系数较高的前三阶子信号;利用连续小波变换(Continuws Narelet Transorm，CWT)将子信号转换为时频图表示，通过注意力特征融合的方式将这些时频图特征进行融合;最后将融合特征输入到深度稳定学习(Stablenet)模型进行训练与预测。为验证模型的有效性，采用凯斯西储大学轴承数据集进行各组对比试验，都灵理工大学轴承数据集进行验证。实验结果表明，AFF-Stablenet模型在小样本情况下的泛化性和鲁棒性均强于其他对比模型，证明了模型的优越性。
Fault diagnosis of small sample bearings based on the AFF-Stablenet model
A fault diagnosis method based on the AFF-Stablenet model is proposed to address the issues of low diagnostic accuracy and weak generalization of rolling bearings under small sample conditions.Initially,the samples are decomposed into sub-signals of multiple frequencies using EMD.The cross-correlation coefficients between the sub-signals and the original signal are computed.The top three sub-signals with higher coefficients are selected.These sub-signals are transformed into time-frequency representations using CWT.Through attention-based feature fusion,the time-frequency features are integrated.Finally,the fused features are input into the Stablenet model for training and prediction.To validate the effectiveness of the proposed model,com-parative experiments are conducted using the Case Western Reserve University bearing dataset and verified using the Politecnico di Torino bearing dataset.Experimental results demonstrate that the AFF-Stablenet model exhibits superior generalization and ro-bustness under small sample conditions compared to other models,affirming the superiority of the proposed approach.
pay attention to feature fusiondeep and stable learningrolling bearingsmall samplesfault diagnosis
万方数据
维普
