Skip to main content
SpringerLink
Log in

Anomaly detection method for TBM construction based on improved VMD-XGBoost-BILSTM combined model

  • Methodology
  • Published:
Earth Science Informatics Aims and scope Submit manuscript

Abstract

TBM method construction is an important accompanying construction form vigorously developed in China, and its anomaly detection is an important link to provide a basis for system operation and maintenance decision-making. The abnormal operation state of TBM caused by different surrounding rock geology, jamming or rock burst will directly affect the tunneling speed and ability, and then affect the system safety and construction progress. In this paper, a TBM construction anomaly detection method based on historical tunneling speed and other construction monitoring data is proposed. Firstly, the preprocessing steps based on outlier removal and correlation analysis are used to remove the noise in the original data and select the best features. Secondly, the variational mode decomposition is used to decompose the data into multiple modal components to extract the periodic and aperiodic features of TBM tunneling. Furthermore, an improved VMD-XGBoost-BILSTM combination model is constructed, and the characteristics of combination weighting, attention mechanism and improved whale optimization algorithm are used to realize the normal prediction of accurate and stable tunneling speed. Finally, by comparing with the actual measured values, the set rules are used to judge the anomalies. The experiments are carried out on the actual mining data of YE long-distance water conveyance tunnel in Xinjiang. The results show that the method proposed in this paper improves the RMSE by more than 20% compared with the single BILSTM or XGBoost model. The attention mechanism and IWOA algorithm bring 5.53% and 10.73% results improvement respectively, which can achieve the effect of early warning of different geological information changes.

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

Similar content being viewed by others

Data availability

Data and materials are available from the corresponding author upon request.

References

  • Dragomiretskiy K, Zosso D (2013) Variational mode decomposition[J]. IEEE Trans Signal Process 62(3):531–544

    Article  Google Scholar 

  • Du QF, Zhang SL, Zhang CX et al (2022) Mud-water balanced shield tunneling speed prediction method based on mean filter denoising and XGBoost algorithm[J]. Modern Tunneling Technology 59(06):14–23. https://doi.org/10.13807/j.cnki.mtt.2022.06.002

    Article  Google Scholar 

  • Hou JZ, Jia GP, Liu B et al (2022a) Advance prediction method for rock mass stability of tunnel boring based on deep neural network of time series. Proc Inst Mech Eng C J Mech Eng Sci 236(10). https://doi.org/10.1177/09544062211061682

  • Hou SK, Liu YR, Yang Q (2022b) Real-time prediction of rock mass classification based on TBM operation big data and stacking technique of ensemble learning. J Rock Mech Geotech Eng 14(01):123–143

    Article  Google Scholar 

  • Li ZM, Yazdani BB, Behn A et al (2021) A hybrid GEP and WOA approach to estimate the optimal penetration rate of TBM in granitic rock mass. Soft Comput 25(17). https://doi.org/10.1007/S00500-021-06005-8

  • Liu FP, Liu Y, Yang C, et al (2022) A New Precipitation Prediction Method Based on CEEMDAN-IWOA-BP Coupling[J]. Water Resour Manag (12). https://doi.org/10.1007/S11269-022-03277-Z

  • Liang Y, Jiang K, Gao SJ, Yin YH (2022) Prediction of Tunnelling Parameters for Underwater Shield Tunnels, Based on the GA-BPNN Method. Sustainability https://doi.org/10.3390/SU142013420

  • Lu YH, Tang LQ, Chen CB, et al (2023) Reconstruction of structural long-term acceleration response based on BILSTM networks. Eng Struct https://doi.org/10.1016/J.ENGSTRUCT.2023.116000

  • Niu DX, Yu M, Sun LJ, et al (2022) Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism[J]. Appl Energy, 313

  • Wang Q, Xie XY, Shahrour I, Huang Y (2021) Use of deep learning, denoising technic and cross-correlation analysis for the prediction of the shield machine slurry pressure in mixed ground conditions. Autom Constr https://doi.org/10.1016/J.AUTCON.2021.103741

  • Wang KY, Zhang LM, Fu XL (2023) Time series prediction of tunnel boring machine (TBM) performance during excavation using causal explainable artificial intelligence (CX-AI)[J]. Autom Constr, 147

  • Yan CB, Gao ZA, Yao XT, et al (2023) A weighted random forest prediction model for TBM construction speed considering uncertainty[J/OL]. J Geotech Eng, pp. 1–9

  • Zhao GF, Jiang YB, Rui FX et al (2023) Numerical simulation-based model for evaluating TBM tunneling performance in complex rock bodie [J]s. Journal of Central South University (Natural Science Edition) 54(03):984–997

    Google Scholar 

Download references

Acknowledgments

The author thanks Xinjiang Shuifa Group Co., Ltd. Saltuohai KS Tunnel management Office for providing data support, Xinjiang Agricultural University for providing research practice platform.

Funding

This study was not funded.

Author information

Authors and Affiliations

  1. College of Water Resources and Civil Engineering, Xinjiang agricultural university, Urumqi, 830000, China

    Zhipeng Lu & Kebin Shi

Authors
  1. Zhipeng Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kebin Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. Writing and editing: Kebin Shi and Zhipeng Lu; chart editing and preliminary data collection: Zhipeng Lu. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Kebin Shi.

Ethics declarations

Ethical approval and consent to participate are

Not applicable.

Consent to publish

Written informed consent for publication was obtained from all participants.

Competing interests

The authors declare no competing interests.

Additional information

Communicated by: Hassan Babaie

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

Lu, Z., Shi, K. Anomaly detection method for TBM construction based on improved VMD-XGBoost-BILSTM combined model. Earth Sci Inform 16, 4273–4284 (2023). https://doi.org/10.1007/s12145-023-01101-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12145-023-01101-9

Keywords

Search

Navigation