Research on fault diagnosis method of MS-CNN rolling bearing based on local central moment discrepancy. (October 2022)

• Record Type: Journal Article
• Authors: Meng, Zong; Cao, Wei; Sun, Dengyun; Li, Qian; Ma, Wuxu; Fan, Fengjie
• Is Part Of: Advanced engineering informatics. Volume 54(2022)
• Publication Date: 2022-10
• Subjects: Multi-scale CNN -- Fault detection -- Local central moment discrepancy -- Transfer learning; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2022.101797
• Languages: English
• ISSNs: 1474-0346

Abstract

Highlights: A multi-scale convolutional neural network (MS-CNN) model for transfer learning is proposed. A domain alignment method based on local central moment discrepancy in class subspace is proposed. Compared with the central moment discrepancy (CMD), the local center moment discrepancy (LCMD) performs better in transfer diagnosis. Abstract: Transfer learning is an excellent approach to deal with the problem that the target domain label can not be adequately obtained when rolling bearing cross-condition fault detection. A transfer learning fault diagnosis method of multi-scale CNN rolling bearings based on local central moment discrepancy is presented in this research. The method maps bearing vibration data to a shared space by building a shared multi-scale feature extraction structure and fully connected layers. The source domain label and target domain pseudo-label are used to divide the category subspace in the shared space. And then the local central moment discrepancy is used to match source and target domain in the category subspace to realize fault knowledge transfer under different conditions. The experimental findings reveal that multi-scale CNN migration diagnosis based on local central moment discrepancy has superior accuracy and stability in diverse diagnostic tasks when compared to classic transfer learning approaches.