TY - JOUR
T1 - A multi-sensor fault diagnosis model with adaptive spatial-temporal dual-scale re-modeling
AU - Xu, Zhao
AU - Jia, Zhiyang
AU - Wei, Yi Wei
AU - Gao, Zengwei
AU - Sun, Jiahang
AU - Tian, Luyu
AU - Liu, Jiakang
N1 - Publisher Copyright:
© 2001-2012 IEEE.
PY - 2024
Y1 - 2024
N2 - Recently, multi-sensor fault diagnosis (MSFD) has become a research hotspot in the field of large machine maintenance. However, current research rarely explores in depth the spatial-temporal structural features unique to sensor signals. To address this gap, this paper proposes the ARM-STDS, a novel multi-sensor fault diagnosis model with adaptive spatial-temporal dual-scale remodeling. Sensor signals exhibit sparsity and periodicity in the temporal domain, which poses challenges for efficient processing by time-series models. To tackle this challenge, we have designed an adaptive subseries-level patches segmentation method that enhances the information capacity of short time slices in the signals. This method effectively extracts local semantic information while reducing computational complexity quadratically. Additionally, we introduce a directed graph structural modeling algorithm to better capture the dependencies between sensors. Utilizing directed graphs proves more effective in representing the coupling relationships between sensors compared to traditional undirected graphs. In comparison to other state-of-the-art MSFD models, ARM-STDS demonstrates the most effective diagnostic performance on four publicly available datasets. In the constant system, the average accuracy increased by 3-5%. Notably, in the non-constant system, ARM-STDS exhibited an accuracy improvement of over 5%.
AB - Recently, multi-sensor fault diagnosis (MSFD) has become a research hotspot in the field of large machine maintenance. However, current research rarely explores in depth the spatial-temporal structural features unique to sensor signals. To address this gap, this paper proposes the ARM-STDS, a novel multi-sensor fault diagnosis model with adaptive spatial-temporal dual-scale remodeling. Sensor signals exhibit sparsity and periodicity in the temporal domain, which poses challenges for efficient processing by time-series models. To tackle this challenge, we have designed an adaptive subseries-level patches segmentation method that enhances the information capacity of short time slices in the signals. This method effectively extracts local semantic information while reducing computational complexity quadratically. Additionally, we introduce a directed graph structural modeling algorithm to better capture the dependencies between sensors. Utilizing directed graphs proves more effective in representing the coupling relationships between sensors compared to traditional undirected graphs. In comparison to other state-of-the-art MSFD models, ARM-STDS demonstrates the most effective diagnostic performance on four publicly available datasets. In the constant system, the average accuracy increased by 3-5%. Notably, in the non-constant system, ARM-STDS exhibited an accuracy improvement of over 5%.
KW - Intelligent diagnosis
KW - adaptive processing
KW - deep learning
KW - graph neural networks
KW - multi-source information fusion
UR - http://www.scopus.com/inward/record.url?scp=85210766056&partnerID=8YFLogxK
U2 - 10.1109/JSEN.2024.3502714
DO - 10.1109/JSEN.2024.3502714
M3 - Article
AN - SCOPUS:85210766056
SN - 1530-437X
JO - IEEE Sensors Journal
JF - IEEE Sensors Journal
ER -