优化深度残差网络及其在强噪声环境下滚动轴承故障诊断中的应用

Optimized deep residual network and its application in fault diagnosis of rolling bearing under the strong noise condition

针对传统基于深度学习的故障诊断方法存在抗噪性能差、计算复杂度高和泛化性能不足的问题,提出了一种基于深度可分离残差网络(Depthwise Separable Residual Network,DS‑ResNet)的滚动轴承故障诊断方法。采用快速傅里叶变换(Fast Fourier Transform,FFT)将滚动轴承一维振动转换到频域进行表示;利用深度可分离卷积(Depthwise Separable Convolution,DSC)计算复杂度低和逐点卷积(Pointwise Convolution,PWC)能增强网络非线性表达的优点,分别代替传统深度残差网络中的两个标准卷积层,构建出优化后的DS‑ResNet模型。将各类故障状态下的频域信号作为DS‑ResNet模型的输入进行识别分类,结果表明,在信噪比为-4 dB的强噪声环境中,识别准确率达到92.71%;在变转速工况下,平均识别准确率可达90.19%,高于其他常用深度学习诊断方法,且模型每轮的训练时间仅需2.16 s,证明了所提方法具有更好的抗噪性能、泛化性能和更高的诊断效率。

Aiming at the problems of poor anti-noise performance and high computational complexity in the traditional fault diagnosis method based on deep learning,a rolling bearing fault diagnosis method based on optimized deep residual networks(ResNet)is proposed.The one-dimensional vibration of the rolling bearing is transformed into frequency domain by fast Fourier transform(FFT).The DS-ResNet model is constructed by replacing the standard convolution layer of the traditional deep residual network(ResNet)with the depthwise separable convolution(DSC)which has low computational complexity and the pointwise convolution(PWC)which can enhance the nonlinear expression of the network.The frequency domain signals in various fault states are used as the input of DS-ResNet model for identification and classification.The results show that the recognition accuracy reaches 92.71%in a strong noise environment with a signal-to-noise ratio of−4 dB,and the average recognition accuracy reaches 90.19%under variable speed conditions,which is higher than other commonly used deep learning diagnosis methods,and the training time of the model takes only 2.16 s per round,which proves that the proposed method has better noise immunity,generalization performance and faster diagnosis efficiency.