Improved Conditional Domain Adversarial Networks for Intelligent Transfer Fault Diagnosis

Qin, Haihua and Pan, Jiafang and Li, Jian and Huang, Faguo (2024) Improved Conditional Domain Adversarial Networks for Intelligent Transfer Fault Diagnosis. Mathematics, 12 (3). p. 481. ISSN 2227-7390

[thumbnail of mathematics-12-00481.pdf] Text
mathematics-12-00481.pdf - Published Version

Download (8MB)

Abstract

Intelligent fault diagnosis encounters the challenges of varying working conditions and sample class imbalance individually, but very few approaches address both challenges simultaneously. This article proposes an improvement network model named ICDAN-F, which can deal with fault diagnosis scenarios with class imbalance and working condition variations in an integrated way. First, Focal Loss, which was originally designed for target detection, is introduced to alleviate the sample class imbalance problem of fault diagnosis and emphasize the key features. Second, the domain discriminator is improved by the default ReLU activation function being replaced with Tanh so that useful negative value information can help extract transferable fault features. Extensive transfer experiments dealing with varying working conditions are conducted on two bearing fault datasets with the effect of class imbalance. The results show that the fault diagnosis performance of ICDAN-F outperforms several other widely used domain adaptation methods, achieving 99.76% and 96.76% fault diagnosis accuracies in Case 1 and Case 2, respectively, which predicts that ICDAN-F can handle both challenges in a cohesive manner.

Item Type: Article
Subjects: Institute Archives > Multidisciplinary
Depositing User: Managing Editor
Date Deposited: 05 Feb 2024 05:19
Last Modified: 05 Feb 2024 05:19
URI: http://eprint.subtopublish.com/id/eprint/4075

Actions (login required)

View Item
View Item