A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 15.3, Top 1 (SCI Q1)
    CiteScore: 23.5, Top 2% (Q1)
    Google Scholar h5-index: 77， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2025  > In Press, Accepted Manuscript
S. Fu, Y. Wang, L. Lin, M. Zhao, L. Zu, Y. Lu, F. Guo, S. Suo, Y. Liu, S. Zhang, and S. Zhong, “DKAMFormer: Domain knowledge-augmented multiscale transformer for remaining useful life prediction of aeroengine,” IEEE/CAA J. Autom. Sinica, 2025. doi: 10.1109/JAS.2025.125126
Citation: S. Fu, Y. Wang, L. Lin, M. Zhao, L. Zu, Y. Lu, F. Guo, S. Suo, Y. Liu, S. Zhang, and S. Zhong, “DKAMFormer: Domain knowledge-augmented multiscale transformer for remaining useful life prediction of aeroengine,” IEEE/CAA J. Autom. Sinica, 2025. doi: 10.1109/JAS.2025.125126
shu

DKAMFormer: Domain Knowledge-Augmented Multiscale Transformer for Remaining Useful Life Prediction of Aeroengine

doi: 10.1109/JAS.2025.125126
Funds:  This work was supported in part by the National Natural Science Foundation of China (52305570), the National Natural Science Foundation of China Key Support Project (U2133202), China Postdoctoral Science Foundation (2022M720955), Postdoctoral Science Foundation of Heilongjiang Province (LBH-Z22187), and Outstanding Doctoral Dissertation Funding Project of Heilongjiang Province (LJYXL2022-011)
More Information
    Abstract
  • Transformers have achieved promising results on aeroengine remaining useful life (RUL) prediction, but they still have several limitations: 1) Aeroengine domain knowledge, which contains rich information that can reflect the aeroengine’s health statue, is largely ignored in modeling process; 2) Traditional transformer ignores the valuable degradation information from other time scales. To address these issues, a novel domain knowledge-augmented multiscale transformer (DKAMFormer) is developed by integrating domain knowledge and multiscale learning to improve the prognostic performance and reliability. First, to obtain rich and professional aeroengine domain knowledge, multiple detail and complete knowledge graphs (KGs) are established based on the working principle of aeroengine, including aeroengine structure, components working characteristics and sensor parameters. Second, the domain knowledge contained in KGs is convert to embedded vector by KG representative learning, which are then utilized to strengthen and enrich the original multidimensional time-series (MTS) monitoring data, aiming to intergrade domain knowledge and monitoring data to train DKAMFormer. Third, to learn rich and complementary degradation features, a novel multiscale time scale-guided self-attention (MTSGSA) mechanism is designed, which maps original MTS into different time-scale feature spaces, and then employs multiple independent self-attention head to extract the degradation features from different time-scale spaces. Finally, through a series of comparative experiments on the public CMAPSS and N-CMAPSS datasets and compared with 17 SOTA methods, the developed DKAMFormer significantly improves the RUL prediction performance under multiple operation conditions and degradation modes.

     

    • FullText(HTML)
  • loading
    • References(46)
  • [1]
    L. Zhou and H. Wang, “MST-GAT: A multi-perspective spatial-temporal graph attention network for multi-sensor equipment remaining useful life prediction,” Inf. Fusion, vol. 110, p. 102462, Oct. 2024. doi: 10.1016/j.inffus.2024.102462
    [2]
    R. Jin, M. Wu, K. Wu, K. Gao, Z. Chen, and X. Li, “Position encoding based convolutional neural networks for machine remaining useful life prediction,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 8, pp. 1427–1439, Aug. 2022. doi: 10.1109/JAS.2022.105746
    [3]
    R. Jiao, K. Peng, and J. Dong, “Remaining useful life prediction for a roller in a hot strip mill based on deep recurrent neural networks,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1345–1354, Jul. 2021. doi: 10.1109/JAS.2021.1004051
    [4]
    C. Lai, P. Baraldi, and E. Zio, “Physics-informed deep autoencoder for fault detection in new-design systems,” Mech. Syst. Signal Process, vol. 215, p. 111420, Jun. 2024. doi: 10.1016/j.ymssp.2024.111420
    [5]
    Y. Ma, Z. Wang, J. Gao, and H. Chen, “A novel method for remaining useful life of solid-state lithium-ion battery based on improved CNN and health indicators derivation,” Mech. Syst. Signal Process, vol. 220, p. 111646, Nov. 2024. doi: 10.1016/j.ymssp.2024.111646
    [6]
    D. Li, J. Chen, R. Huang, Z. Chen, and W. Li, “Sensor-aware CapsNet: Towards trustworthy multisensory fusion for remaining useful life prediction,” J. Manuf. Syst., vol. 72, pp. 26–37, Feb. 2024. doi: 10.1016/j.jmsy.2023.11.009
    [7]
    J. Chen, R. Huang, Z. Chen, W. Mao, and W. Li, “Transfer learning algorithms for bearing remaining useful life prediction: A comprehensive review from an industrial application perspective,” Mech. Syst. Signal Process, vol. 193, p. 110239, Jun. 2023. doi: 10.1016/j.ymssp.2023.110239
    [8]
    J. Chen, D. Li, R. Huang, Z. Chen, and W. Li, “Aero-engine remaining useful life prediction method with self-adaptive multimodal data fusion and cluster-ensemble transfer regression,” Reliab. Eng. Syst. Saf., vol. 234, p. 109151, Jun. 2023. doi: 10.1016/j.ress.2023.109151
    [9]
    J. Chen, D. Li, R. Huang, Z. Chen, and W. Li, “A transfer regression network-based adaptive calibration method for remaining useful life prediction considering individual discrepancies in the degradation process of machinery,” J. Intell. Manuf., vol. 36, no. 4, pp. 2767–2783, May 2024.
    [10]
    H.-B. Zhang, D.-J. Cheng, K.-L. Zhou, and S.-W. Zhang, “Deep transfer learning-based hierarchical adaptive remaining useful life prediction of bearings considering the correlation of multistage degradation,” Knowl.-Based Syst., vol. 266, p. 110391, Apr. 2023. doi: 10.1016/j.knosys.2023.110391
    [11]
    F. Xiang, Y. Zhang, S. Zhang, Z. Wang, L. Qiu, and J.-H. Choi, “Bayesian gated-transformer model for risk-aware prediction of aero-engine remaining useful life,” Expert Syst. Appl., vol. 238, p. 121859, Mar. 2024. doi: 10.1016/j.eswa.2023.121859
    [12]
    Y. Zhang, C. Su, J. Wu, H. Liu, and M. Xie, “Trend-augmented and temporal-featured Transformer network with multi-sensor signals for remaining useful life prediction,” Reliab. Eng. Syst. Saf., vol. 241, p. 109662, Jan. 2024. doi: 10.1016/j.ress.2023.109662
    [13]
    L. Jiang, T. Zhang, W. Lei, K. Zhuang, and Y. Li, “A new convolutional dual-channel Transformer network with time window concatenation for remaining useful life prediction of rolling bearings,” Adv. Eng. Inform., vol. 56, p. 101966, Apr. 2023. doi: 10.1016/j.aei.2023.101966
    [14]
    J. Zhang, X. Li, J. Tian, H. Luo, and S. Yin, “An integrated multi-head dual sparse self-attention network for remaining useful life prediction,” Reliab. Eng. Syst. Saf., vol. 233, p. 109096, May 2023. doi: 10.1016/j.ress.2023.109096
    [15]
    X. Liu, Y. Lei, N. Li, X. Si, and X. Li, “RUL prediction of machinery using convolutional-vector fusion network through multi-feature dynamic weighting,” Mech. Syst. Signal Process, vol. 185, p. 109788, Feb. 2023. doi: 10.1016/j.ymssp.2022.109788
    [16]
    S. Fu, L. Lin, Y. Wang, F. Guo, M. Zhao, B. Zhong, and S. Zhong, “MCA-DTCN: A novel dual-task temporal convolutional network with multi-channel attention for first prediction time detection and remaining useful life prediction,” Reliab. Eng. Syst. Saf., vol. 241, p. 109696, Jan. 2024. doi: 10.1016/j.ress.2023.109696
    [17]
    S. Suh, P. Lukowicz, and Y. O. Lee, “Generalized multiscale feature extraction for remaining useful life prediction of bearings with generative adversarial networks,” Knowl.-Based Syst., vol. 237, p. 107866, Feb. 2022. doi: 10.1016/j.knosys.2021.107866
    [18]
    Y. Wei and D. Wu, “Conditional variational transformer for bearing remaining useful life prediction,” Adv. Eng. Inform., vol. 59, p. 102247, Jan. 2024. doi: 10.1016/j.aei.2023.102247
    [19]
    J. Shi, J. Zhong, Y. Zhang, B. Xiao, L. Xiao, and Y. Zheng, “A dual attention LSTM lightweight model based on exponential smoothing for remaining useful life prediction,” Reliab. Eng. Syst. Saf., vol. 243, p. 109821, Mar. 2024. doi: 10.1016/j.ress.2023.109821
    [20]
    K. You, G. Qiu, and Y. Gu, “A 3-D attention-enhanced hybrid neural network for turbofan engine remaining life prediction using CNN and BiLSTM models,” IEEE Sens. J., vol. 24, no. 14, pp. 21893–21905, Jul. 2024. doi: 10.1109/JSEN.2023.3296670
    [21]
    P. Ma, G. Li, H. Zhang, C. Wang, and X. Li, “Prediction of remaining useful life of rolling bearings based on multiscale efficient channel attention CNN and bidirectional GRU,” IEEE Trans. Instrum. Meas., vol. 73, p. 2508413, 2024.
    [22]
    L. Hu, X. He, and L. Yin, “Remaining useful life prediction method combining the life variation laws of aero-turbofan engine and auto-expandable cascaded LSTM model,” Appl. Soft Comput., vol. 147, p. 110836, Nov. 2023. doi: 10.1016/j.asoc.2023.110836
    [23]
    Y. Cheng, J. Qv, K. Feng, and T. Han, “A Bayesian adversarial probsparse Transformer model for long-term remaining useful life prediction,” Reliab. Eng. Syst. Saf., vol. 248, p. 110188, Aug. 2024. doi: 10.1016/j.ress.2024.110188
    [24]
    L. Wang, H. Cao, H. Xu, and H. Liu, “A gated graph convolutional network with multi-sensor signals for remaining useful life prediction,” Knowl.-Based Syst., vol. 252, p. 109340, Sep. 2022. doi: 10.1016/j.knosys.2022.109340
    [25]
    Y. Wei and D. Wu, “Remaining useful life prediction of bearings with attention-awared graph convolutional network,” Adv. Eng. Inform., vol. 58, p. 102143, Oct. 2023. doi: 10.1016/j.aei.2023.102143
    [26]
    Y. Zhang, W. Zhou, J. Huang, X. Jin, and G. Xiao, “Temporal knowledge graph informer network for remaining useful life prediction,” IEEE Trans. Instrum. Meas., vol. 72, p. 3528610, 2023.
    [27]
    Z. Wang, Z. Wu, X. Li, H. Shao, T. Han, and M. Xie, “Attention-aware temporal–Spatial graph neural network with multi-sensor information fusion for fault diagnosis,” Knowl.-Based Syst., vol. 278, p. 110891, Oct. 2023. doi: 10.1016/j.knosys.2023.110891
    [28]
    Y. Liu, B. Tian, Y. Lv, L. Li, and F. Wang, “Point cloud classification using content-based Transformer via clustering in feature space,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 1, pp. 231–239, Jan. 2024. doi: 10.1109/JAS.2023.123432
    [29]
    L. Wang, H. Cao, Z. Ye, H. Xu, and J. Yan, “DVGTformer: A dual-view graph Transformer to fuse multi-sensor signals for remaining useful life prediction,” Mech. Syst. Signal Process, vol. 207, p. 110935, Jan. 2024. doi: 10.1016/j.ymssp.2023.110935
    [30]
    Y. Li, Y. Chen, H. Shao, and H. Zhang, “A novel dual attention mechanism combined with knowledge for remaining useful life prediction based on gated recurrent units,” Reliab. Eng. Syst. Saf., vol. 239, p. 109514, Nov. 2023. doi: 10.1016/j.ress.2023.109514
    [31]
    Z. X. Tan, “Research on the performance prediction of commercial aircraft engine by multi-source information fusion,” Ph.D. dissertation, Harbin Institute of Technology, Harbin, China, 2018.
    [32]
    L. Zu, L. Lin, S. Fu, F. Guo, and J. Wu, “SelectE: Multi-scale adaptive selection network for knowledge graph representation learning,” Knowl.-Based Syst., vol. 291, p. 111554, May 2024. doi: 10.1016/j.knosys.2024.111554
    [33]
    A. Saxena, K. Goebel, D. Simon, and N. Eklund, “Damage propagation modeling for aircraft engine run-to-failure simulation,” in Proc. Int. Conf. Prognostics and Health Management, Denver, USA, 2008, pp. 1–9.
    [34]
    H. Tian, L. Yang, and B. Ju, “Spatial correlation and temporal attention-based LSTM for remaining useful life prediction of turbofan engine,” Measurement, vol. 214, p. 112816, Jun. 2023. doi: 10.1016/j.measurement.2023.112816
    [35]
    J. Zhang, Y. Jiang, S. Wu, X. Li, H. Luo, and S. Yin, “Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism,” Reliab. Eng. Syst. Saf., vol. 221, p. 108297, May 2022. doi: 10.1016/j.ress.2021.108297
    [36]
    Q. Zhang, Q. Liu, and Q. Ye, “An attention-based temporal convolutional network method for predicting remaining useful life of aero-engine,” Eng. Appl. Artif. Intell., vol. 127, p. 107241, Jan. 2024. doi: 10.1016/j.engappai.2023.107241
    [37]
    H. Wei, Q. Zhang, and Y. Gu, “Remaining useful life prediction of bearings based on self-attention mechanism, multi-scale dilated causal convolution, and temporal convolution network,” Meas. Sci. Technol., vol. 34, no. 4, p. 45107, Apr. 2023. doi: 10.1088/1361-6501/acb0e9
    [38]
    X. Li, H. Jiang, Y. Liu, T. Wang, and Z. Li, “An integrated deep multiscale feature fusion network for aeroengine remaining useful life prediction with multisensor data,” Knowl.-Based Syst., vol. 235, p. 107652, Jan. 2022. doi: 10.1016/j.knosys.2021.107652
    [39]
    K. Zhao, Z. Jia, F. Jia, and H. Shao, “Multi-scale integrated deep self-attention network for predicting remaining useful life of aero-engine,” Eng. Appl. Artif. Intell., vol. 120, p. 105860, Apr. 2023. doi: 10.1016/j.engappai.2023.105860
    [40]
    J. Li, Y. Jia, M. Niu, W. Zhu, and F. Meng, “Remaining useful life prediction of turbofan engines using CNN-LSTM-SAM approach,” IEEE Sens. J., vol. 23, no. 9, pp. 10241–10251, May 2023. doi: 10.1109/JSEN.2023.3261874
    [41]
    H. Al-Khazraji, A. R. Nasser, A. M. Hasan, A. K. Al Mhdawi, H. Al-Raweshidy, and A. J. Humaidi, “Aircraft engines remaining useful life prediction based on a hybrid model of Autoencoder and deep belief network,” IEEE Access, vol. 10, pp. 82156–82163, 2022. doi: 10.1109/ACCESS.2022.3188681
    [42]
    T. Jing, P. Zheng, L. Xia, and T. Liu, “Transformer-based hierarchical latent space VAE for interpretable remaining useful life prediction,” Adv. Eng. Inform., vol. 54, p. 101781, Oct. 2022. doi: 10.1016/j.aei.2022.101781
    [43]
    M. Arias Chao, C. Kulkarni, K. Goebel, and O. Fink, “Aircraft engine run-to-failure dataset under real flight conditions for prognostics and diagnostics,” Data, vol. 6, no. 1, p. 5, Jan. 2021. doi: 10.3390/data6010005
    [44]
    X. Xu, X. Li, W. Ming, and M. Chen, “A novel multi-scale CNN and attention mechanism method with multi-sensor signal for remaining useful life prediction,” Comput. Ind. Eng., vol. 169, p. 108204, Jul. 2022. doi: 10.1016/j.cie.2022.108204
    [45]
    F. Deng, Y. Bi, Y. Liu, and S. Yang, “Remaining useful life prediction of machinery: A new multiscale temporal convolutional network framework,” IEEE Trans. Instrum. Meas., vol. 71, p. 2516913, 2022.
    [46]
    Z. Zhou, Z. Long, R. Wang, M. Bai, J. Liu, and D. Yu, “An aircraft engine remaining useful life prediction method based on predictive vector angle minimization and feature fusion gate improved transformer model,” J. Manuf. Syst., vol. 76, pp. 567–584, Oct. 2024. doi: 10.1016/j.jmsy.2024.08.025
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(25)  / Tables(7)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (118) PDF downloads(27) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return