Deep learning-based intelligent fault diagnosis methods have attracted increasing attention for their automatic feature extraction ability. However, existing works are usually under the assumption that the training and test dataset share similar distributions, which unfortunately always violates real practice due to the variety of working conditions. In this paper, an end-to-end scheme of joint use of two-direction signals and capsule network (CN) is proposed for fault diagnosis of rolling bearing. With the help of the superior ability of CN in capturing the spatial position information between features, more valuable information can be mined. Aiming to eliminate the influence of different rotational speeds, vertical and horizontal vibration signals are fused as the input to CN, so that invariant features can be extracted automatically from the raw signals. The effectiveness of the proposed method is verified by experimental data of rolling bearing under different rotational speeds and compared with a deep convolutional neural network (DCNN). The results demonstrate that the proposed scheme is able to recognize the fault types of rolling bearing under scenarios of different rotational speeds.
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited