Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
SpringerLink
Log in

Dynamic spatial–temporal graph-driven machine remaining useful life prediction method using graph data augmentation

  • Published:
Journal of Intelligent Manufacturing Aims and scope Submit manuscript

Abstract

It is beneficial to maintain the normal operation of machines by conducting remaining useful life (RUL) prediction. Recently, graph data-driven machine RUL prediction methods have made a great success, since graph can model spatial and temporal dependencies of signals. However, the constructed graphs still have some limitations: (1) In the practical industrial production, the installation of multi-sensor networks is expensive and hard to achieve, so the single sensor is commonly used for data monitoring. However, most of these methods constructed graphs by establishing relationships between the different sensors, which are completely unsuitable for prediction tasks in single-sensor scenarios. (2) The quality of constructed graph is low, where the graph structure is fixed, failing in representing the machine degradation process. To overcome these limitations, a dynamic spatial–temporal (ST) graph-driven machine RUL prediction method using graph data augmentation (GDA) is proposed. The ST graph is constructed using short-time Fourier transform, capturing the frequency-domain and time-domain information hidden in the signals. Then, a GDA framework is designed to generate dynamic ST graphs, enlarging the structural differences of subgraphs. Subsequently, a GDA-based graph deep learning prediction model is constructed for dynamic ST graph-based RUL prediction, where an autoencoder-based graph embedding module is designed to replace simple Readout. Verification experiments are conducted on two case studies, and the results show that the proposed prediction method achieves a competitive performance.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Abbreviations

BiLSTM:

Bi-directional LSTM

ChebGCN:

Chebyshev graph convolutional network

CNN:

Convolutional neural network

FC:

Fully connected

GAT:

Graph attention network

GCN:

Graph convolutional network

GDA:

Graph data augmentation

GDAGDL:

GDA-based graph deep learning

LSTM:

Long short-term memory neural network

MAE:

Mean absolute error

MSE:

Mean squared error

RMSE:

Root mean squared error

RUL:

Remaining useful life

ST:

Spatial–temporal

STFT:

Short-time Fourier transform

A :

Adjacent matrix

A d :

Adjacent matrix of dynamic ST graph

a T :

Weight vector of GAT

c t / \(\tilde{c}_{t}\) :

Updated/ Candidate status in input gate

E :

Edge set

G/ G d :

Graph/ Dynamic ST graph

\({\varvec{g}}_{i}\) :

Output of encoder network

h t -1/ h t :

Output of previous/ current recurring unit

T/ T i :

Node feature matrix/ Node feature

\(\user2{T^{\prime}}_{i}\) :

Output of the graph attention layer

V/ v i :

Node set/ Node

W P :

Pearson correlation coefficient matrix

\({\varvec{W}}^{\varphi }\) :

Weight vector obtained from FC

\({\varvec{W}}^{\phi }\) :

Node importance vector

W G :

Learned weight matrix from GAT

W i/ W c/ W f/ W o :

Weight matrix of input gate/ cell/ forget gate/ output gate

x t :

Information flowing into the recurrent unit of LSTM

Y(k,m):

STFT magnitude

Y GAT/ Y auto/Y LSTM :

Output of GAT/ autoencoder/ LSTM

\({\varvec{y}}_{i}\) :

Reconstructed original input

Z :

Predicted RUL

\(\zeta^{\prime}_{ij}\)/\(\zeta_{ij}\) :

Regularized attention coefficient/Attention coefficient

References

  • Chen, C., Lu, N., Jiang, B., Xing, Y., & Zhu, Z. (2021). Prediction interval estimation of aeroengine remaining useful life based on bidirectional long short-term memory network. IEEE Transactions on Instrumentation and Measurement, 70, 1–13.

    Google Scholar 

  • Chen, Y., Peng, G., Zhu, Z., & Li, S. (2020). A novel deep learning method based on attention mechanism for bearing remaining useful life prediction. Applied Soft Computing, 86, 105919.

    Article  Google Scholar 

  • Gao, Y., & Yu, D. (2020). Total variation on horizontal visibility graph and its application to rolling bearing fault diagnosis. Mechanism and Machine Theory, 147, 103768.

    Article  Google Scholar 

  • He, Z., Shao, H., Ding, Z., Jiang, H., & Cheng, J. (2022). Modified deep auto-encoder driven by multi-source parameters for fault transfer prognosis of aero-engine. IEEE Transactions on Industrial Electronics, 69(1), 845–855.

    Article  Google Scholar 

  • Kim, T., & Sohn, S. (2021). Multitask learning for health condition identification and remaining useful life prediction: Deep convolutional neural network approach. Journal of Intelligent Manufacturing, 32, 2169–2179.

    Article  Google Scholar 

  • Kipf, T. N., & Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv preprint, arXiv:1609.02907.

  • Kundu, P., Chopra, S., & Lad, B. K. (2019). Multiple failure behaviors identification and remaining useful life prediction of ball bearings. Journal of Intelligent Manufacturing, 30, 1795–1807.

    Article  Google Scholar 

  • Li, N., Xu, P., Lei, Y., Cai, X., & Kong, D. (2022a). A self-data-driven method for remaining useful life prediction of wind turbines considering continuously varying speeds. Mechanical Systems and Signal Processing, 165, 108315.

    Article  Google Scholar 

  • Li, P., Liu, X., & Yang, Y. (2021a). Remaining useful life prognostics of bearings based on a novel spatial graph-temporal convolution network. Sensors, 21, 4217.

    Article  Google Scholar 

  • Li, T., Zhao, Z., Sun, C., Yan, R., & Chen, X. (2021b). Multi-receptive field graph convolutional networks for machine fault diagnosis. IEEE Transactions on Industrial Electronics, 68(12), 12739–12749.

    Article  Google Scholar 

  • Li, T., Zhao, Z., Sun, C., Yan, R., & Chen, X. (2021c). Domain adversarial graph convolutional network for fault diagnosis under variable working conditions. IEEE Transactions on Instrumentation and Measurement, 70, 1–10.

    Google Scholar 

  • Li, T., Zhao, Z., Sun, C., Yan, R., & Chen, X. (2021d). Hierarchical attention graph convolutional network to fuse multi-sensor signals for remaining useful life prediction. Reliability Engineering & System Safety, 215, 107878.

    Article  Google Scholar 

  • Li, X., Zhang, W., Ma, H., Luo, Z., & Li, X. (2021e). Degradation alignment in remaining useful life prediction using deep cycle-consistent learning. IEEE Transactions on Neural Networks and Learning Systems, 33(10), 5480–5491.

    Article  Google Scholar 

  • Li, X., Zhang, Z., Gao, L., & Wen, L. (2022b). A new semi-supervised fault diagnosis method via deep coral and transfer component analysis. IEEE Transactions on Emerging Topics in Computational Intelligence, 6(3), 690–699.

    Article  Google Scholar 

  • Liu, Y., Ge, M., Zhang, C., & Liu, J. (2021b). A deep feature learning method based on time-frequency images and MSCNN_SE for rul prediction. 2021b IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control, 163–167.

  • Liu, J., Hu, Y., Wu, B., Fan, J., & Hu, Z. (2018). An integrated multi-sensor fusion-based deep feature learning approach for rotating machinery diagnosis. Measurement Science and Technology, 29(5), 055103.

    Article  Google Scholar 

  • Liu, J., Zhou, K., Yang, C., & Lu, G. (2021). Imbalanced fault diagnosis of rotating machinery using autoencoder-based SuperGraph feature learning. Frontiers of Mechanical Engineering, 16, 829–839.

    Article  Google Scholar 

  • Nectoux, P., Gouriveau, R., Medjaher, K., Ramasso, E., Chebel-Morello, B., Zerhouni, N., & Varnier, C. (2012). PRONOSTIA: An experimental platform for bearings accelerated degradation tests. IEEE International Conference on Prognostics and Health Management, PHM’12. 1–8.

  • Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2017). Graph attention networks. arXiv preprint, arXiv:1710.10903.

  • Wang, B., Lei, Y., Li, N., & Li, N. (2020a). A hybrid prognostics approach for estimating remaining useful life of rolling element bearings. IEEE Transactions on Reliability, 69(1), 401–412.

    Article  Google Scholar 

  • Wang, B., Lei, Y., Yan, T., Li, N., & Guo, L. (2020b). Recurrent convolutional neural network: A new framework for remaining useful life prediction of machinery. Neurocomputing, 379, 117–129.

    Article  Google Scholar 

  • Wang, T., Liu, Z., Lu, G., & Liu, J. (2021a). Temporal-spatio graph based spectrum analysis for bearing fault detection and diagnosis. IEEE Transactions on Industrial Electronics, 68(3), 2598–2607.

    Article  Google Scholar 

  • Wang, Y., Gao, L., Gao, Y., & Li, X. (2021b). A new graph-based semi-supervised method for surface defect classification. Robotics and Computer-Integrated Manufacturing, 68, 102083.

    Article  Google Scholar 

  • Wu, J., Wu, M., Chen, Z., Li, X., & Yan, R. (2021). Degradation-aware remaining useful life prediction with LSTM autoencoder. IEEE Transactions on Instrumentation and Measurement, 70, 1–10.

    Google Scholar 

  • Yang, C., Zhou, K., & Liu, J. (2021). SuperGraph: Spatial-temporal graph-based feature extraction for rotating machinery diagnosis. IEEE Transactions on Industrial Electronics, 69(4), 4167–4176.

    Article  Google Scholar 

  • Zhang, D., Stewart, E., Entezami, M., Roberts, C., & Yu, D. (2020). Intelligent acoustic-based fault diagnosis of roller bearings using a deep graph convolutional network. Measurement, 156, 107585.

    Article  Google Scholar 

  • Zhang, Y., Li, Y., Wang, Y., Yang, Y., & Wei, X. (2022). Adaptive spatio-temporal graph information fusion for remaining useful life prediction. IEEE Sensors Journal, 22(4), 3334–3347.

    Article  Google Scholar 

  • Zhao, T., Liu, Y., Neves, L., Woodford, O., Jiang, M., & Shah, N. (2020). Data augmentation for graph neural networks. arXiv preprint, arXiv:2006.06830.

  • Zhao, T., Liu, G., Wang, D., Yu, W., & Jiang, M. (2021). Counterfactual Graph Learning for Link Prediction. arXiv preprint, arXiv:2106.02172.

  • Zhou, J., Shan, Y., Liu, J., Xu, Y., & Zheng, Y. (2020). Degradation tendency prediction for pumped storage unit based on integrated degradation index construction and hybrid CNN-LSTM model. Sensors, 20, 4277.

    Article  Google Scholar 

  • Zhou, K., Yang, C., Liu, J., & Xu, Q. (2022a). Dynamic graph-based feature learning with few edges considering noisy samples for rotating machinery fault diagnosis. IEEE Transactions on Industrial Electronics, 69(10), 10595–10604.

    Article  Google Scholar 

  • Zhou, K., Yang, C., Liu, J., & Xu, Q. (2022b). Deep graph feature learning-based diagnosis approach for rotating machinery using multi-sensor data. Journal of Intelligent Manufacturing. https://doi.org/10.1007/s10845-021-01884-y

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported in part by the National Key Research and Development Program of China under Grant 2020YFB1711203, and the National Natural Science Foundation of China under Grants 52205104, 61873101 and 72171096.

Funding

National Key Research and Development Program of China, 2020YFB1711203, Jie Liu. National Natural Science Foundation of China, 52205104, Jie Liu, 61873101, Kaibo Zhou, 72171096, Jie Liu

Author information

Authors and Affiliations

  1. MOE Key Laboratory of Image Information Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, 430074, China

    Chaoying Yang & Kaibo Zhou

  2. School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan, 430074, China

    Jie Liu

  3. State Key Laboratory of Digital Manufacturing Equipment & Technology, Huazhong University of Science and Technology, Wuhan, 430074, China

    Xinyu Li

Authors
  1. Chaoying Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jie Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kaibo Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xinyu Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jie Liu.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, C., Liu, J., Zhou, K. et al. Dynamic spatial–temporal graph-driven machine remaining useful life prediction method using graph data augmentation. J Intell Manuf 35, 355–366 (2024). https://doi.org/10.1007/s10845-022-02052-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10845-022-02052-6

Keywords

Search

Navigation