A fault diagnosis method based on improved convolutional neural network for bearings under variable working conditions. (September 2021)

• Record Type: Journal Article
• Authors: Zhang, Ke; Wang, Jingyu; Shi, Huaitao; Zhang, Xiaochen; Tang, Yinghan
• Is Part Of: Measurement. Volume 182(2021)
• Publication Date: 2021-09
• Subjects: TH-17; Rolling bearing fault diagnosis -- Convolutional neural network (CNN) -- Continuous wavelet transform -- Pseudo-label learnings; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2021.109749
• Languages: English
• ISSNs: 0263-2241

Abstract

Abstract: The fault diagnosis of rolling bearing will be negatively reduced because of variable working conditions, large environmental noise interference and insufficient effective data sample. To solve the problem, this paper proposes an improved convolutional neural network (CNN) method. The method firstly constructs a new network, multi-mode CNN (MMCNN) by using multiple parallel convolutional layers to effectively extract rich and complementary fault features, then transforms the 1D time-domain signal of the rolling bearing acquired under different frequency variable conditions to the 2D time–frequency grayscale by continuous wavelet transform (CWT) and put the grayscale into the MMCNN for training. Besides, the method combines the pseudo-label learning method with MMCNN, which can expands the labeled data set by pseudo-label processing of unlabeled data. The experimental results show that the proposed method can effectively improve the fault detection accuracy of rolling bearings under variable working conditions, which is superior to the existing methods. Highlights: A new CNN mechanism called MMCNN is proposed. The mechanism can perform fault diagnosis for bearings under variable conditions. The mechanism combines continuous wavelet transform for data preprocessing. The mechanism is combined with pseudo-label learning to expand the data set.