A multisensory time-frequency features fusion method for rotating machinery fault diagnosis under nonstationary case

Jiayang Liu (), Fuqi Xie (), Qiang Zhang (), Qiucheng Lyu (), Xiaosun Wang () and Shijing Wu ()
Additional contact information
Jiayang Liu: Wuhan University
Fuqi Xie: Wuhan University
Qiang Zhang: Wuhan University
Qiucheng Lyu: Wuhan University
Xiaosun Wang: Wuhan University
Shijing Wu: Wuhan University

Journal of Intelligent Manufacturing, 2024, vol. 35, issue 7, No 11, 3197-3217

Abstract: Abstract Mechanical system fault diagnosis is essential to save costs and ensure safety. Generally, rotating machinery operates in nonstationary cases, which makes fault features complex and difficult to identify. However, existing fault diagnosis methods have the following limitations. (1) Consider only time or frequency domain features fusion. (2) Extract the fusion features representation only in the Euclidean domain. Based on that, a novel method based on multisensory time-frequency features fusion and graph attention network is proposed for rotating machinery fault diagnosis under the nonstationary case. First, the multi-sensor time series are converted into multi-sensor time-frequency maps by image-to-matrix, matrix concatenation, and matrix-to-image operations. Then, simple linear iterative clustering is applied to make the superpixels in the multi-sensor time-frequency maps into nodes and form graphs based on color and texture features. Finally, the graph attention network with residual connection is applied to distinguish the rotating machinery’s health status. The proposed method is verified using gearbox test rig data and bearing public data, respectively. The experimental results indicate that the proposed method can provide more reliable and accurate fault diagnosis results for rotating machinery than other methods.

Keywords: Fault diagnosis; Rotating machinery; Multisensory fusion; Time-frequency features; Graph attention networks (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-023-02198-x Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:35:y:2024:i:7:d:10.1007_s10845-023-02198-x

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-023-02198-x

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().