Considering various fault states under severe working conditions, the comprehensive feature extraction from the raw vibration signal is still a challenge for the diagnosis task of rolling bearing. To deal with strong coupling and high nonlinearity of the vibration signal, this article proposes a novel multilocation and multikernel scale learning network based on deep convolution encoder (DCE) and bidirectional short-term memory network (BiLSTM). The former multifeature learning network of this article proposed combines the skip connection and the DCE network. The network can automatically extract and fuse global and local features from different network depth and time scales of the raw vibration signal. Then, the former network as the input of the latter network is fed into the feature protection layer for further mining sensitive and complementary features. Consequently, the proposed network scheme can perform well in generalization capability. The performance of the proposed method is verified on the two kinds of bearing datasets. The diagnostic results demonstrate that the proposed method can diagnose multiple fault types more accurately. Also, the method performs better in load and speed adaptation compared with other intelligent fault classification methods.

中文翻译：

---

带有跳线连接的多功能和多尺度学习框架，用于复杂工况下的轴承故障诊断

考虑到严酷工况下的各种故障状态，从原始振动信号中综合提取特征仍然是滚动轴承诊断任务中的一个挑战。为了解决振动信号的强耦合和高非线性问题，本文提出了一种基于深度卷积编码器（DCE）和双向短期记忆网络（BiLSTM）的新型多位置和多核尺度学习网络。本文提出的以前的多功能学习网络结合了跳过连接和DCE网络。网络可以从原始振动信号的不同网络深度和时间尺度自动提取和融合全局和局部特征。然后，前一个网络作为后一个网络的输入，被馈入特征保护层，以进一步挖掘敏感和互补的特征。因此，所提出的网络方案在泛化能力方面可以表现良好。在两种轴承数据集上验证了该方法的性能。诊断结果表明，该方法可以更准确地诊断多种故障类型。而且，与其他智能故障分类方法相比，该方法在负载和速度适应方面表现更好。诊断结果表明，该方法可以更准确地诊断多种故障类型。而且，与其他智能故障分类方法相比，该方法在负载和速度适应方面表现更好。诊断结果表明，该方法可以更准确地诊断多种故障类型。而且，与其他智能故障分类方法相比，该方法在负载和速度适应方面表现更好。