Enhanced transfer learning method for rolling bearing fault diagnosis based on linear superposition network. (May 2023)

• Record Type: Journal Article
• Authors: Huo, Chunran; Jiang, Quansheng; Shen, Yehu; Zhu, Qixin; Zhang, Qingkui
• Is Part Of: Engineering applications of artificial intelligence. Volume 121(2023)
• Publication Date: 2023-05
• Subjects: Fault diagnosis -- Transfer learning -- Linear superposition network -- Rolling bearing -- Convolutional neural network; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2023.105970
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Deep transfer learning is used to solve the problem of unsupervised intelligent fault diagnosis of rolling bearings. However, when the data distribution between two domains is different, the existing deep transfer learning models which only rely on the domain-invariant features are not enough to complete the target domain data learning. To solve this problem, an enhanced transfer learning method based on the linear superposition network is proposed for rolling bearing fault diagnosis. This method improves the structure of the one-dimensional convolutional neural network (1D-CNN) by constructing linear superposition convolution blocks. At the same time, the loss function of transfer learning is constructed by using the pseudo-label of the target domain from the network, which enhances the ability of rolling bearing fault feature extraction. Compared with the traditional feature-based transfer learning methods, the proposed enhanced transfer learning method based on the linear superposition network can make the network place more stress on the feature learning of the target domain. Experimental results on the Paderborn University (PU) dataset show that, compared with the improved deep adaptation network (DAN) model, the proposed method improves the average diagnosis accuracy by 21% on six transfer tasks, showing improved bearing fault diagnostic precision. Highlights: A linear superposition network is proposed to effectively extract bearing fault features. The improved loss function is constructed by making efficient use of the generated pseudo-labels. A new transfer learning method for bearing diagnosis based on LS-CNN+ETL is proposed. The effectiveness of the proposed method is validated with JNU and PU datasets.