TY - GEN
T1 - A Tensor Train based Multi-channel Fault Signal De-noising Method for Wind Turbine Generators
AU - Li, Keren
AU - Zhang, Wenqiang
AU - Xiao, Dandan
AU - Hou, Peng
AU - Shaltout, Mohamed L.
AU - Mao, Xuerui
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - Multi-channel signal
KW - Rolling bearing
KW - Signal denosing
KW - Tensor train decomposition
KW - Wind turbine generators
UR - http://www.scopus.com/inward/record.url?scp=85214935214&partnerID=8YFLogxK
U2 - 10.1109/DTPI61353.2024.10778726
DO - 10.1109/DTPI61353.2024.10778726
M3 - Conference contribution
AN - SCOPUS:85214935214
T3 - Proceedings - 2024 IEEE 4th International Conference on Digital Twins and Parallel Intelligence, DTPI 2024
SP - 138
EP - 143
BT - Proceedings - 2024 IEEE 4th International Conference on Digital Twins and Parallel Intelligence, DTPI 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2024
Y2 - 18 October 2024 through 20 October 2024
ER -