Restricted accessResearch articleFirst published online 2025-2
Remaining useful life prediction for multi-sensor mechanical equipment based on self-attention mechanism network incorporating spatio-temporal convolution
Driven by the limitations of spatial feature extraction in graph learning methods of multi-sensor mechanism equipment, this paper proposes a spatio-temporal self-attention mechanism network (STCAN) that integrates spatial relationships and time series information to predict the remaining useful life (RUL). Firstly, a graph convolutional network (GCN) is applied to extract the spatial correlation characteristics and fused with the self-attention mechanism network to obtain the global and local spatial features. Subsequently, a dilated convolutional network (DCN) is integrated into the self-attention mechanism network, to extract the global and multi-step temporal features and mitigate long-term dependency issues. Finally, the extracted spatio-temporal features are used to predict the equipment’s RUL through fully connected layers. The experimental results demonstrate that STCAN outperforms some existing methods in terms of RUL prediction.
WuXYangXHuangJ, et al. Remaining useful life prediction for motor systems by iteratively updated wiener process based on closed-loop performance degradation monitoring. Proc IMechE, Part I: J Systems and Control Engineering2024; 238: 3–15.
2.
GuoRWangY. Remaining useful life prognostics for the rolling bearing based on a hybrid data-driven method. Proc IMechE, Part I: J Systems and Control Engineering2021; 235(4): 517–531.
3.
LiRChuZJinW, et al. Temporal convolutional network based regression approach for estimation of remaining useful life. In: 2021 IEEE international conference on prognostics and health management (ICPHM), Detroit (Romulus), MI, USA, 7–9 June 2021, pp.1–10. New York: IEEE.
4.
GuoRLiuZWangJ. Remaining useful life prediction for the electro-hydraulic actuator based on improved relevance vector machine. Proc IMechE, Part I: J Systems and Control Engineering2020; 234(4): 501–511.
5.
LiuGOuyangZHaoX, et al. Prediction of raw meal fineness in the grinding process of cement raw material: a two-dimensional convolutional neural network prediction method. Proc IMechE, Part I: J Systems and Control Engineering2021; 235(6): 823–838.
6.
SahaPDashSMukhopadhyayS. Physics-incorporated convolutional recurrent neural networks for source identification and forecasting of dynamical systems. Neural Netw2021; 144: 359–371.
7.
LiTZhaoZSunC, et al. Hierarchical attention graph convolutional network to fuse multi-sensor signals for remaining useful life prediction. Reliab Eng Syst Saf2021; 215: 107878.
8.
WangGZhangYLuM, et al. Hierarchical graph neural network with adaptive cross-graph fusion for remaining useful life prediction. Meas Sci Technol2023; 34(5): 055112.
KongZJinXXuZ, et al. Spatio-temporal fusion attention: a novel approach for remaining useful life prediction based on graph neural network. IEEE Trans Instrum Meas2022; 71: 1–12.
11.
LiangPLiYWangB, et al. Remaining useful life prediction via a deep adaptive transformer framework enhanced by graph attention network. Int J Fatigue2023; 174: 107722.
12.
LiuLSongXZhouZ. Aircraft engine remaining useful life estimation via a double attention-based data-driven architecture. Reliab Eng Syst Saf2022; 221: 108330.
13.
ChenLLiuRYangX, et al. STTG-net: a Spatio-temporal network for human motion prediction based on transformer and graph convolution network. Vis Comput Ind Biomed Art2022; 5(1): 19.
14.
MoYWuQLiX, et al. Remaining useful life estimation via transformer encoder enhanced by a gated convolutional unit. J Intell Manuf2021; 32: 1997–2006.
15.
VaswaniAShazeerNParmarN, et al. Attention is all you need. Adv Neural Inf Process Syst2017; 30: 5998–6008.
16.
XuXWuQLiX, et al. Dilated convolution neural network for remaining useful life prediction. J Comput Inf Sci Eng2020; 20(2): 021004.
17.
SaxenaAGoebelKSimonD, et al. Damage propagation modeling for aircraft engine run-to-failure simulation. In: 2008 international conference on prognostics and health management, Denver, CO, USA, 6–9 October 2008, pp.1–9. New York: IEEE.
18.
HeimesFO. Recurrent neural networks for remaining useful life estimation. In: 2008 international conference on prognostics and health management, Denver, CO, USA, 6–9 October 2008, pp.1–6. New York: IEEE.
19.
ZhengSRistovskiKFarahatA, et al. Long short-term memory network for remaining useful life estimation. In: 2017 IEEE international conference on prognostics and health management, Dallas, TX, USA, 19–21 June 2017, pp.88–95. New York: IEEE.
20.
LiXDingQSunJQ. Remaining useful life estimation in prognostics using deep convolution neural networks. Reliab Eng Syst Saf2018; 172: 1–11.
21.
ZhaoZLiangBWangX, et al. Remaining useful life prediction of aircraft engine based on degradation pattern learning. Reliab Eng Syst Saf2017; 164: 74–83.
22.
SateeshBGZhaoPLiXL. Deep convolutional neural network based regression approach for estimation of remaining useful life. In: NavatheSWuWShekharS, et al. (eds) Database systems for advanced applications: 21st international conference. Cham: Springer, 2016, pp.214–228.
23.
HsuCSJiangJR. Remaining useful life estimation using long short-term memory deep learning. In: 2018 IEEE international conference on applied system invention, Chiba, Japan, 13–17 April 2018, pp.58–61. New York: IEEE.
24.
ChenZWuMZhaoR, et al. Machine remaining useful life prediction via an attention-based deep learning approach. IEEE Trans Ind Electron2020; 68(3): 2521–2531.
25.
LiTZhouZLiS, et al. The emerging graph neural networks for intelligent fault diagnostics and prognostics: a guideline and a benchmark study. Mech Syst Signal Process2022; 168: 108653.
26.
LiXLimBSZhouJH, et al. Fuzzy neural network modelling for tool wear estimation in dry milling operation. In: Annual conference of the PHM society, SanDiego, CA, September 2009, vol. 1, no. 1.
27.
HuangCGHuangHZLiYF. A bidirectional LSTM prognostics method under multiple operational conditions. IEEE Trans Ind Electron2019; 66(11): 8792–8802.
28.
WuZYuSZhuX, et al. A weighted deep domain adaptation method for industrial fault prognostics according to prior distribution of complex working conditions. IEEE Access2019; 7: 139802–139814.
29.
TianZLiMQiuM, et al. Block-DEF: a secure digital evidence framework using blockchain. Inf Sci2019; 491: 151–165.
