Skip to main content
SpringerLink
Log in

VAE-TALSTM: a temporal attention and variational autoencoder-based long short-term memory framework for dam displacement prediction

  • Original Article
  • Published:
Engineering with Computers Aims and scope Submit manuscript

Abstract

The safety and health monitoring of dams has attracted increasing attention. In this paper, a novel prediction model based on variational autoencoder (VAE) and temporal attention-based long short-term memory (TALSTM) network is proposed for the long-term deformation of arch dams. In the proposed model, the convolutional neural network-based VAE is applied to extracting the features of environmental data. The TALSTM is employed to construct the relationship between the dam displacement and extracted features. For verification, an arch dam is taken as an example. Through the comparison among nine baseline prediction models, the proposed model is more stable and effective than other prediction models. Furthermore, the proposed model could capture the features of environmental data accurately and provide better prediction results. Therefore, the proposed model is more suitable for engineering applications.

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

Access this article

Log in via an institution

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
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

References

  1. Bui K-TT, Bui DT, Zou J, Van Doan C, Revhaug I (2016) A novel hybrid artificial intelligent approach based on neural fuzzy inference model and particle swarm optimization for horizontal displacement modeling of hydropower dam. Neural Comput Appl 29:1495–1506

    Article  Google Scholar 

  2. Chen B, Hu T, Huang Z, Fang C (2018) A spatio-temporal clustering and diagnosis method for concrete arch dams using deformation monitoring data. Struct Heal Monit 18:1355–1371

    Article  Google Scholar 

  3. Shu X, Bao T, Li Y, Zhang K, Wu B (2020) Dam safety evaluation based on interval-valued intuitionistic fuzzy sets and evidence theory. Sensors 20:2648

    Article  Google Scholar 

  4. Willm G, Beaujoint N (1967) Les méthodes de surveillance des barrages au service de la production hydraulique d'Electricité de France, problèmes anciens et solutions nouvelles. In: IXth international congress on large dams

  5. Wu ZR, Shen CS, Ruan HX (1988) Factor selection of statistical model for concrete dam deformation. J Hohai Univ 16(6):1–9

    Google Scholar 

  6. Gu CS, Li Y, Song JX (2010) Study on safety monitoring model for deformation of RCCD. Chin J Comput Mech 27(2):286–290

    Google Scholar 

  7. Gu CS, Li B, Xu BS, Hu J (2008) Safety monitoring model of roller-compacted concrete dam seepage. J Hohai Univ (Natural Sciences) 36(5):579–584

    Google Scholar 

  8. Su H, Li X, Yang B et al (2018) Wavelet support vector machine-based prediction model of dam deformation [J]. Mech Syst Signal Process 110:412–427

    Article  Google Scholar 

  9. Li LH, Peng SJ, Jiang ZX (2014) Prediction model of concrete dam deformation based on adaptive unscented Kalman Filter and BP neural network. Appl Mech Mater 513:4076–4079

    Article  Google Scholar 

  10. Li Y, Bao T, Gong J et al (2020) The prediction of dam displacement time series using STL, extra-trees, and stacked LSTM neural network [J]. IEEE Access 8(99):1–1

    Google Scholar 

  11. Liu W, Pan J, Ren Y et al (2020) Coupling prediction model for long-term displacements of arch dams based on long short-term memory network[J]. Struct Control Health Monit 27:e2548. https://doi.org/10.1002/stc.2548

    Article  Google Scholar 

  12. Wang YH, Xu C (2010) Using genetic artificial neural network to model dam monitoring data. Second Int Conf Comput Model Simul 2:3–7

    Google Scholar 

  13. Kingma DP, Welling M (2014) Auto-encoding variational bayes[C]. In: International conference on learning representations

  14. Boquet G, Morell A, Serrano J et al (2020) A variational autoencoder solution for road traffic forecasting systems: Missing data imputation, dimension reduction, model selection and anomaly detection[J]. Transp Res Part C Emerg Technol

  15. Ma X, Lin Y, Nie Z et al (2020) Structural damage identification based on unsupervised feature-extraction via Variational Auto-encoder[J]. Measurement 107811

  16. Fan Y, Wen G, Li D et al (2018) Video anomaly detection and localization via gaussian mixture fully convolutional variational autoencoder[J]. Comput Vis Image Underst

  17. Xie R, Jan NM, Hao K et al (2020) Supervised variational autoencoders for soft sensor modeling with missing data[J]. IEEE Trans Ind Inf 16(4):2820–2828

    Article  Google Scholar 

  18. Blei DM, Kucukelbir A, Mcauliffe J et al (2017) Variational inference: a review for statisticians[J]. J Am Stat Assoc 112(518):859–877

    Article  MathSciNet  Google Scholar 

  19. Rawat W, Wang Z (2017) Deep convolutional neural networks for image classification: a comprehensive review. Neural Comput 29(9):2352–2449

    Article  MathSciNet  Google Scholar 

  20. Kim D, Park C, Oh J et al (2016) Convolutional matrix factorization for document context-aware recommendation[C]. In: Conference on recommender systems, pp 233–240

  21. Yin Y, Chen L, Xu Y et al (2019) QoS prediction for service recommendation with deep feature learning in edge computing environment[J]. Mobile Netw Appl:1–11

  22. Ma C, Huang J, Yang X et al (2019) Robust visual tracking via hierarchical convolutional features[J]. IEEE Trans Pattern Anal Mach Intell 41(11):2709–2723

    Article  Google Scholar 

  23. Dung CV, Anh LD (2019) Autonomous concrete crack detection using deep fully convolutional neural network[J]. Autom Construct:52–58

  24. Hochreiter S, Schmidhuber J (1997) Long short-term memory[J]. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  25. Zhou G, Wu J, Zhang C et al (2016) Minimal gated unit for recurrent neural networks[J]. Int J Autom Comput 13(3):226–234

    Article  Google Scholar 

  26. Zhao R, Wang D, Yan R et al (2018) machine health monitoring using local feature-based gated recurrent unit networks[J]. IEEE Trans Ind Electron 65(2):1539–1548

    Article  Google Scholar 

  27. Tai KS, Socher R, Manning CD (2015) Improved semantic representations from tree-structured long short-term memory networks[J]. Comput Lang 5(1):36

    Google Scholar 

  28. Vaswani et al (2017) Attention is all you need. Adv Neural Inf Process Syst

  29. Wang Q, Hao Y (2020) ALSTM: an attention-based long short-term memory framework for knowledge base reasoning[J]. Neurocomputing 399:342–351

    Article  Google Scholar 

  30. Du S, Li T, Yang Y et al (2020) Multivariate time series forecasting via attention-based encoder-decoder framework[J]. Neurocomputing:269–279

  31. Xiao X, Zhang D, Hu G et al (2020) CNN-MHSA: a convolutional neural network and multi-head self-attention combined approach for detecting phishing websites[J]. Neural Netw 125:303–312

Download references

Acknowledgements

Some or all data, models, or code generated or used during the study are available from the corresponding author by request.

Funding

This work was supported by the National Key R&D program of China (2018YFC1508603), the National Natural Science Foundation of China (Grant nos. 51579086, 51739003).

Author information

Authors and Affiliations

  1. State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, Hohai University, Nanjing, 210098, China

    Xiaosong Shu, Tengfei Bao, Yangtao Li, Jian Gong & Kang Zhang

  2. College of Water-Conservancy and Hydropower, Hohai University, Nanjing, 210098, China

    Xiaosong Shu, Tengfei Bao, Yangtao Li, Jian Gong & Kang Zhang

  3. College of Hydraulic and Environmental Engineering, China Three Gorges University, Yichang, 443002, China

    Tengfei Bao

Authors
  1. Xiaosong Shu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tengfei Bao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yangtao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jian Gong
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Kang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization: XS and TB; methodology: XS and TB; validation: XS, YL and JG; formal analysis: XS, YL, JG and KZ; data curation: XS, YL and JG; writing—original draft preparation, XS and TB; writing—review and editing, XS and TB; funding acquisition, TB.

Corresponding author

Correspondence to Tengfei Bao.

Ethics declarations

Conflict of interest

The authors declare no conflict of interest.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shu, X., Bao, T., Li, Y. et al. VAE-TALSTM: a temporal attention and variational autoencoder-based long short-term memory framework for dam displacement prediction. Engineering with Computers 38, 3497–3512 (2022). https://doi.org/10.1007/s00366-021-01362-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00366-021-01362-2

Keywords

Search

Navigation