A Tensor Train based Multi-channel Fault Signal De-noising Method for Wind Turbine Generators

Keren Li*, Wenqiang Zhang, Dandan Xiao, Peng Hou, Mohamed L. Shaltout, Xuerui Mao

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

With the continuous development of sensors and information collection related technologies, there are more and more types of data, and the amount of data of the same type is getting larger and larger. For mechanical components such as fan rotating gears, the use of a single sensor for fault diagnosis has limitations, and it is impossible to fully and simultaneously perform auxiliary fault diagnosis on gears, bearings and other components on each shaft. However, the use of multi-channel sensors can solve this problem well, but in actual engineering applications, there is noise interference when multi-channel sensors perform joint fault diagnosis, and it is impossible to accurately extract the fault characteristics of rotating machinery. This paper proposes a feature extraction method based on tensor train fused signal (TTFS) as a means of addressing noise interference in rotating machinery signals within wind farms. Initially, our focus is on data collection, during which we analyse data in tensor format across three dimensions: time, frequency, and channel. In order to emphasise the use of tensor train decomposition, we introduce a tensor reconstruction method with adaptive filter truncation. Subsequently, the continuous wavelet transform (CWT) method is employed to establish tensor data representation across these dimensions. Subsequently, the proposed adaptive filtering truncation tensor reconstruction method is employed to reconstruct the tensor by combining the aforementioned matrices. Finally, the continuous wavelet inverse transform is applied to the reconstructed tensor in order to obtain time-domain signals from different channels. The efficacy of the proposed method is demonstrated through experimental signals, which illustrate the advantages of the method and the improved convergence speed of the objective function.

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE 4th International Conference on Digital Twins and Parallel Intelligence, DTPI 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages138-143
Number of pages6
ISBN (Electronic)9798350349252
DOIs
Publication statusPublished - 2024
Event4th IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2024 - Wuhan, China
Duration: 18 Oct 202420 Oct 2024

Publication series

NameProceedings - 2024 IEEE 4th International Conference on Digital Twins and Parallel Intelligence, DTPI 2024

Conference

Conference4th IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2024
Country/TerritoryChina
CityWuhan
Period18/10/2420/10/24

Keywords

  • Multi-channel signal
  • Rolling bearing
  • Signal denosing
  • Tensor train decomposition
  • Wind turbine generators

Fingerprint

Dive into the research topics of 'A Tensor Train based Multi-channel Fault Signal De-noising Method for Wind Turbine Generators'. Together they form a unique fingerprint.

Cite this

Li, K., Zhang, W., Xiao, D., Hou, P., Shaltout, M. L., & Mao, X. (2024). A Tensor Train based Multi-channel Fault Signal De-noising Method for Wind Turbine Generators. In Proceedings - 2024 IEEE 4th International Conference on Digital Twins and Parallel Intelligence, DTPI 2024 (pp. 138-143). (Proceedings - 2024 IEEE 4th International Conference on Digital Twins and Parallel Intelligence, DTPI 2024). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DTPI61353.2024.10778726