Cross-Attribute adaptation networks: Distilling transferable features from multiple sampling-frequency source domains for fault diagnosis of wind turbine gearboxes. (15th August 2022)

• Record Type: Journal Article
• Authors: Li, Qikang; Tang, Baoping; Deng, Lei; Xiong, Peng; Zhao, Minghang
• Is Part Of: Measurement. Volume 200(2022)
• Publication Date: 2022-08-15
• Subjects: Cross-attribute adaptation networks -- Attention mechanism -- Fault diagnosis -- Wind turbine gearboxes; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2022.111570
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: A Cross-attribute adaptation network with a multiple branch framework is proposed to learn domain-invariant features from multiple sampling-frequency source domains. Specific feature extractor with attention mechanism further considers the unique information in different sampling-frequency data. Discrepancies in classifiers of the different branches can be aligned to construct a more precise decision boundary. The proposed method achieves end-to-end learning using the vibration data of actual wind turbines gearboxes. Abstract: Vibration signals of wind turbine gearboxes are often collected under various sampling frequencies. However, most traditional domain adaptation methods, which are applied to improve fault diagnosing accuracy with limited or unlabeled datasets, only consider a single source domain with the same sampling frequency. In this paper, a novel domain-invariant feature learning method, i.e., cross-attribute adaptation networks (CAAN), is developed, in which each source domain with a particular sampling frequency has individual feature learning and adaptation modules. Specifically, a multi-branch framework with the attention mechanism is developed to learn and weigh the characteristics of multiple sampling-frequency data separately. Then, the discrepancies between multiple classifiers and the domains are minimized to build a precise decision boundary. Extensive experimental analysis on real wind turbine gearboxes datasets is performed to demonstrate the effectiveness and advantage of the proposed CAAN.