| Citation: | HU Aijun, LI Chenyang, XING Lei, et al. Gear remaining life prediction based on residual attention TCN and vision transformer[J]. Journal of Aerospace Power, 2025, 40（12）：20240284 doi: 10.13224/j.cnki.jasp.20240284
|
The operating condition of a gear system is influenced by multiple factors exhibiting long-term dependencies over time and differences between local and global features. In order to effectively capture the temporal dependence in data and adaptively adjust the attention to features, a temporal convolutional network (RCMTCN) with residual convolutional block attention mechanism was proposed. By introducing residual connections into the convolutional block attention mechanism, the model can jointly emphasize the original input and attention-weighted information, and improve the model’s ability to perceive local information. On this basis, the vision transformer (ViT) model was combined with RCMTCN to predict the remaining service life (RUL) of gears. The ViT model can effectively obtain the global information in the data. The fusion of these two can fully demonstrate its advantages in local feature extraction capabilities and global information attention in processing time series data, and improve the perception of features of various scales. Finally, the model was verified on two working conditions gear performance degradation datasets, pitting corrosion fault data were selected for training, and pitting corrosion and tooth broken faults were tested respectively. Experimental results showed that compared with other methods, the proposed method can more fully extract key feature information. The scoring function achieved
| [1] |
CHEN Jiaxian, LI Dongpeng, HUANG Ruyi, et al. Aero-engine remaining useful life prediction method with self-adaptive multimodal data fusion and cluster-ensemble transfer regression[J]. Reliability Engineering & System Safety, 2023, 234: 109151.
|
| [2] |
朱永超, 朱才朝, 谭建军, 等. 考虑数据特征差异的风电齿轮箱群组健康状态预测研究[J]. 机械工程学报, 2024, 60(18): 64-75. ZHU Yongchao, ZHU Caichao, TAN Jianjun, et al. Health status prediction of wind turbine gearbox cluster considering data distribution discrepancy[J]. Journal of Mechanical Engineering, 2024, 60(18): 64-75. (in Chinese
ZHU Yongchao, ZHU Caichao, TAN Jianjun, et al. Health status prediction of wind turbine gearbox cluster considering data distribution discrepancy[J]. Journal of Mechanical Engineering, 2024, 60(18): 64-75. (in Chinese)
|
| [3] |
DING Wanmeng, LI Jimeng, MAO Weilin, et al. Rolling bearing remaining useful life prediction based on dilated causal convolutional DenseNet and an exponential model[J]. Reliability Engineering & System Safety, 2023, 232: 109072.
|
| [4] |
NIE Lei, ZHANG Lvfan, XU Shiyi, et al. Remaining useful life prediction for rolling bearings based on similarity feature fusion and convolutional neural network[J]. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2022, 44(8): 328. doi: 10.1007/s40430-022-03638-0
|
| [5] |
张超, 庞永志, 王巍智, 等. 基于CNN-GRU模型的齿轮寿命预测[J]. 机床与液压, 2023, 51(2): 11-16. ZHANG Chao, PANG Yongzhi, WANG Weizhi, et al. Gear life prediction based on CNN-GRU model[J]. Machine Tool & Hydraulics, 2023, 51(2): 11-16. (in Chinese
ZHANG Chao, PANG Yongzhi, WANG Weizhi, et al. Gear life prediction based on CNN-GRU model[J]. Machine Tool & Hydraulics, 2023, 51(2): 11-16. (in Chinese)
|
| [6] |
WAN Lanjun, CHEN Keyu, LI Yuanyuan, et al. A novel remaining useful life prediction method based on CEEMDAN-IFTC-PSR and ensemble CNN/BiLSTM model for cutting tool[J]. IEEE Access, 2022, 10: 2182-2195. doi: 10.1109/ACCESS.2021.3140165
|
| [7] |
ZHANG Jiusi, TIAN Jilun, LI Minglei, et al. A parallel hybrid neural network with integration of spatial and temporal features for remaining useful life prediction in prognostics[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 72: 3501112.
|
| [8] |
HUANG Chenggeng, HUANG Hongzhong, LI Yanfeng, et al. A novel deep convolutional neural network-bootstrap integrated method for RUL prediction of rolling bearing[J]. Journal of Manufacturing Systems, 2021, 61: 757-772. doi: 10.1016/j.jmsy.2021.03.012
|
| [9] |
ZHAO Minghang, ZHONG Shisheng, FU Xuyun, et al. Deep residual shrinkage networks for fault diagnosis[J]. IEEE Transactions on Industrial Informatics, 2020, 16(7): 4681-4690. doi: 10.1109/TII.2019.2943898
|
| [10] |
PASCANU R, MIKOLOV T, BENGIO Y. On the difficulty of training recurrent neural networks[EB/OL]. (2013-02-16)[2024-05-07]. https://arxiv.org/abs/1211.5063.
|
| [11] |
BAI Shaojie, ZICO KOLTER J, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[EB/OL]. (2018-04-19)[2024-05-07]. https://arxiv.org/abs/1803.01271.
|
| [12] |
WU Pin, SUN Junwu, CHANG Xuting, et al. Data-driven reduced order model with temporal convolutional neural network[J]. Computer Methods in Applied Mechanics and Engineering, 2020, 360: 112766. doi: 10.1016/j.cma.2019.112766
|
| [13] |
CAO Y, DING Y, JIA M, et al. A novel temporal convolutional network with residual self-attention mechanism for remaining useful life prediction of rolling bearings[J]. Reliability Engineering & System Safety, 2021, 215: 107813.
|
| [14] |
HE Ke, SU Zuqiang, TIAN Xiaoqing, et al. RUL prediction of wind turbine gearbox bearings based on self-calibration temporal convolutional network[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 3501912.
|
| [15] |
SUN Heng, XIA Min, HU Yawei, et al. A new sorting feature-based temporal convolutional network for remaining useful life prediction of rotating machinery[J]. Computers and Electrical Engineering, 2021, 95: 107413. doi: 10.1016/j.compeleceng.2021.107413
|
| [16] |
WANG Wei, ZHOU Gongbo, MA Guoqing, et al. A novel competitive temporal convolutional network for remaining useful life prediction of rolling bearings[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 3523612.
|
| [17] |
WANG Yiwei, DENG Lei, ZHENG Lianyu, et al. Temporal convolutional network with soft thresholding and attention mechanism for machinery prognostics[J]. Journal of Manufacturing Systems, 2021, 60: 512-526. doi: 10.1016/j.jmsy.2021.07.008
|
| [18] |
WANG Haitao, YANG Jie, WANG Ruihua, et al. Remaining useful life prediction of bearings based on convolution attention mechanism and temporal convolution network[J]. IEEE Access, 2023, 11: 24407-24419. doi: 10.1109/ACCESS.2023.3255891
|
| [19] |
ZHANG X, LIU C, YANG D, et al. RFAConv: innovating spatial attention and standard convolutional operation[EB/OL]. (2024-03-28)[2024-05-07]. https://arxiv.org/abs/2304.03198.
|
| [20] |
ZHAI Xiaohua, KOLESNIKOV A, HOULSBY N, et al. Scaling vision transformers[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, US: IEEE, 2022: 1204-1213.
|
| [21] |
DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: transformers for image recognition at scale[EB/OL]. (2021-06-03)[2024-05-07]. https://arxiv.org/abs/2010.11929?featured_on=pythonbytes.
|
| [22] |
HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, US: IEEE, 2016: 770-778.
|
| [23] |
YAO Qingtao, LI Xianze, XIANG Ling, et al. A new condition-monitoring method based on multi-variable correlation learning network for wind turbine fault detection[J]. Measurement Science and Technology, 2023, 34(2): 024009. doi: 10.1088/1361-6501/ac9f5d
|
| [24] |
WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[R]. Munich, Germany: 15th European Conference on Computer Vision, 2018.
|
| [25] |
向玲, 王凯伦, 胡爱军, 等. 基于Dy Res Net-CBAM网络的滚动轴承剩余寿命预测[J]. 中国工程机械学报, 2023, 21(1): 6-11. XIANG Ling, WANG Kailun, HU Aijun, et al. Remaining life prediction of rolling bearing based on Dy Res Net-CBAM network[J]. Chinese Journal of Construction Machinery, 2023, 21(1): 6-11. (in Chinese
XIANG Ling, WANG Kailun, HU Aijun, et al. Remaining life prediction of rolling bearing based on Dy Res Net-CBAM network[J]. Chinese Journal of Construction Machinery, 2023, 21(1): 6-11. (in Chinese)
|
| [26] |
DENG Feiyue, BI Yan, LIU Yongqiang, et al. Remaining useful life prediction of machinery: a new multiscale temporal convolutional network framework[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 2516913.
|
| [27] |
LI Xiang, DING Qian, SUN Jianqiao. Remaining useful life estimation in prognostics using deep convolution neural networks[J]. Reliability Engineering & System Safety, 2018, 172: 1-11.
|
| [28] |
JIANG Changhong, LIU Xinyu, LIU Yizheng, et al. A method for predicting the remaining life of rolling bearings based on multi-scale feature extraction and attention mechanism[J]. Electronics, 2022, 11(21): 3616. doi: 10.3390/electronics11213616
|
| [29] |
QIN Yi, XIANG Sheng, CHAI Yi, et al. Macroscopic-microscopic attention in LSTM networks based on fusion features for gear remaining life prediction[J]. IEEE Transactions on Industrial Electronics, 2020, 67(12): 10865-10875. doi: 10.1109/TIE.2019.2959492
|
DownLoad:
