First-order differential filtering spectrum division method and information fusion multi-scale network for fault diagnosis of bearings under different loads

Abstract

In recent years, data-driven intelligent diagnosis methods have been widely applied in the field of bearing fault diagnosis. However, these methods involve some expert experience and knowledge, and cannot accurately mine bearing fault characteristics under different loads. To solve this problem, this paper proposes a First-order differential filtering spectrum division method (FDFSD) and an information fusion multi-scale network (IFMSNet) to realize bearing fault diagnosis under different working conditions. First of all, the proposed spectrum division method based on the first-order differential filtering, the first-order differential processing of time domain signals, and the introduction of triangular filter, reclassify the spectrum features, highlight feature information, can accurately extract bearing fault features. Secondly, a new multi-scale network model of information fusion is constructed in this paper. Convolution kernels of different sizes are used to extract fault features of bearings of different scales, and information fusion is carried out to identify bearing working conditions and realize intelligent diagnosis of bearings under different loads. Finally, in order to verify the effectiveness and accuracy of the proposed method, it is verified on a variety of bearing experimental data sets. The results show that the average prediction accuracy of the proposed method is 99.11% and 97.74%, respectively. Compared with the proposed three single-scale network, K-Nearest Neighbor (KNN), Naive Bayes (NB), Support Vector Machine (SVM) and Random Forest (RF) methods, the proposed method has more advantages in bearing intelligent diagnosis under different loads.

A new dual-channel convolutional neural network and its application in rolling bearing fault diagnosis

“…(1) Collect the vibration signals of rolling bearings through the data acquisition system; (2) Using equations ( 6) and (7) During this experiment, the vibration signals of the drive end bearing were gathered under four different loads: 0, 1, 2, and 3hp. Based on these collected data, four datasets were constructed: A, B, C, and D. Each dataset comprises four types: normal (NORMAL), ball failure (BF), inner race failure (IF), and outer race failure (OF).…”

“…Currently, the mainstream fault diagnosis methods mainly include three types [6]: model-based diagnostic methods, expert experience-based diagnostic methods, and data-driven diagnostic methods. Among them, diagnostic methods based on models and expert experience knowledge are limited in their application due to difficulties in establishing accurate mechanism analysis models and a lack of self-learning ability [7]. The data-driven diagnostic method requires high professional knowledge and experience, and requires a lot of manpower and time [8,9].…”

A multi-layer feature fusion fault diagnosis method for train bearings under noise and variable load working conditions

“…Zhang et al [38] fused CNNs with domain adaptive algorithms to achieve fault classification under variable working conditions. Wang et al [39] adopted the multi-scale information fusion network to realize bearing fault diagnosis under different loads. Bai et al [40] adopted the multi-channel CNN to fuse multi-channel fault information and improve fault classification accuracy.…”