基于注意力循环胶囊网络的滚动轴承故障诊断

Fault Diagnosis of Rolling Bearing Based on Attention Recurrent Capsule Network

针对滚动轴承工作工况复杂、载荷大及测得的振动信号信噪比(signal-to-noise ratio,简称SNR)低的特点,提出了一种利用注意力循环机制(attention recurrent,简称AR)构建数字胶囊并与胶囊网络(capsule network,简称Caps)相融合的微弱故障诊断模型。首先,在构建初级胶囊时引入双向长短时记忆网络(bidirectional long short time memory neural network,简称Bi-LSTM),对时频图中的时序特征进行提取,并建立胶囊间的非线性关联;其次,引入注意力循环机制构建数字胶囊,提高时频图中不同时间和频带的能量强度变化的影响力;然后,通过3D卷积与动态路由机制构建的数字胶囊进行自适应融合,实现特征的多样提取;最后,利用softmax分类器将融合特征映射到输出层,实现高噪声环境下的滚动轴承故障诊断。结果表明,该方法对小样本、低信噪比的微弱故障信号较其他诊断模型有更高的诊断精度,并能够有效减小过拟合问题。使用不同负载下的数据做测试集验证了该模型有较强的泛化能力。

In view of the complex working conditions,large load and low signal-to-noise ratio(SNR)of vibra⁃tion signal of rolling bearing,a weak fault diagnosis model based on attention recurrence(AR)is proposed to construct digital capsule and fuse with capsule network(Caps).In this model,the bidirectional long-short time memory neural network(Bi-LSTM)is introduced to extract the temporal features of the time-frequency dia⁃gram,and establish nonlinear association between capsules.Secondly,we use the attention recurrence mecha⁃nism to construct digital capsules to improve the influence of energy intensity changes in different time and fre⁃quency bands of time-frequency diagram.Then the attention recurrence and digital capsules constructed by dy⁃namic routing mechanism are fused by 3D convolution adaptively to realize the diversity of feature extraction.Finally,the softmax classifier is used to map the fusion features to the output layer,to achieve the fault diagnosis of rolling bearing in high noise environment.The results show that this method has higher diagnostic accuracy than other diagnostic models on weak fault signals with small samples and low signal-to-noise ratio.Moreover,the model can effectively reduce the over fitting problem and strong generalization ability.