改进注意力机制的滚动轴承故障诊断方法研究

针对滚动轴承在实际工作环境中噪声较大和负载变化的问题,提出一种基于双注意卷积机制的残差神经网络(Double attention convolution mechanism ResNet,DACM_ResNet)轴承故障诊断方法：首先,对滚动轴承振动信号进行短时傅里叶变换(short-time Fourier transform,STFT)并使用伪彩色处理得到三通道图像数据；然后,对残差神经网络在轴承故障诊断上进行研究,在残差单元的卷积层之后,使用DACM模块,将残差特征在通道和空间维度上进行进一步提取,最后,在凯斯西储大学(CWRU)数据集上进行试验验证,试验结果表明所提出的方法在噪声环境下及负载变化时,平均诊断准确率达到了98%以上,说明所提出的模型有较好的鲁棒性。

Research on fault diagnosis method of rolling bearing with improved attention mechanism

Aiming the situation that rolling bearing in noisy and load changes at the actual working environment, A bearing fault diagnosis method based on Double attention convolution mechanism ResNet (DACM_ResNet) is proposed. First, short-time Fourier transform (STFT) is performed on the vibration signal of the rolling bearing and pseudo-color processing is used to obtain three-channel image data. Then, the residual neural network is studied on bearing fault diagnosis. After the convolution layer of the residual block, the DACM module is used to further extract the residual features from the two dimensions of channel and space, and the connection between the residual and the input is established. Finally, experiments were carried out on the Case Western Reserve University (CWRU) dataset, and the test results show that the proposed method has an average accuracy of more than 98% under the noise environment and load changes, indicating that the proposed model has good noise resistance