ALSTNet: Autoencoder fused long- and short-term time-series network for the prediction of tunnel structure

Abstract

It is crucial to predict future mechanical behaviors for the prevention of structural disasters. Especially for underground construction, the structural mechanical behaviors are affected by multiple internal and external factors due to the complex conditions. Given that the existing models fail to take into account all the factors and accurate prediction of the multiple time series simultaneously is difficult using these models, this study proposed an improved prediction model through the autoencoder fused long- and short-term time-series network driven by the mass number of monitoring data. Then, the proposed model was formalized on multiple time series of strain monitoring data. Also, the discussion analysis with a classical baseline and an ablation experiment was conducted to verify the effectiveness of the prediction model. As the results indicate, the proposed model shows obvious superiority in predicting the future mechanical behaviors of structures. As a case study, the presented model was applied to the Nanjing Dinghuaimen tunnel to predict the stain variation on a different time scale in the future.

Keywords

autoencoder / deep learning / structural health monitoring / time-series prediction

References

[1] Cao B-T, Obel M, Freitag S, Mark P, Meschke G. Artificial neural network surrogate modelling for real-time predictions and control of building damage during mechanised tunnelling. Adv Eng Softw. 2020; 149:102869.

[2] Chen T, Yin H, Chen H, et al. Tada: trend alignment with dual-attention multi-task recurrent neural networks for sales prediction. IEEE International Conference on Data Mining (ICDM). IEEE; 2018: 49-58.

[3] Fahimifar A, Tehrani FM, Hedayat A, Vakilzadeh A. Analytical solution for the excavation of circular tunnels in a visco-elastic Burger's material under hydrostatic stress field. Tunnel Undergr Space Technol. 2010; 25(4): 297-304.

[4] Farahani RV, Penumadu D. Full-scale bridge damage identification using time series analysis of a dense array of geophones excited by drop weight. Struct Control Health Monitor. 2016; 23(7): 982-997.

[5] Feng X, Jimenez R, Zeng P, Senent S. Prediction of time-dependent tunnel convergences using a Bayesian updating approach. Tunnel Undergr Space Technol. 2019; 94:103118.

[6] Freitag S, Cao BT, Ninić J, Meschke G. Hybrid surrogate modelling for mechanised tunnelling simulations with uncertain data. Int J Reliab Saf. 2015; 9: 154-173.

[7] Freitag S, Cao B, Ninić J, Meschke G. Recurrent neural networks and proper orthogonal decomposition with interval data for real-time predictions of mechanised tunnelling processes. Comput Struct. 2018; 207: 258-273.

[8] Goulet J-A. Bayesian dynamic linear models for structural health monitoring. Struct Control Health Monitor. 2017; 24:e2035.

[9] Goulet J-A, Koo K. Empirical validation of Bayesian dynamic linear models in the context of structural health monitoring. J Bridge Eng. 2018; 23:05017017.

[10] Lai G, Chang W-C, Yang Y, Liu H. Modeling long-and short-term temporal patterns with deep neural networks. The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. ACM; 2018: 95-104.

[11] Liu B, Wang R, Zhao G, et al. Prediction of rock mass parameters in the TBM tunnel based on BP neural network integrated simulated annealing algorithm. Tunnel Undergr Space Technol. 2020; 95:103103.

[12] Mahdevari S, Torabi SR. Prediction of tunnel convergence using Artificial Neural Networks. Tunnel Undergr Space Technol. 2012; 28: 218-228.

[13] Mahmoodzadeh A, Mohammadi M, Daraei A, Faraj RH, Mohammed Dler Omer R, Sherwani AF. Decision-making in tunneling using artificial intelligence tools. Tunnel Undergr Space Technol. 2020; 103:103514.

[14] Mahmoodzadeh A, Mohammadi M, Ibrahim HH, et al. Tunnel geomechanical parameters prediction using Gaussian process regression. Mach Learn Appl. 2021; 3:100020.

[15] Mei L, Mita A, Zhou J. An improved substructural damage detection approach of shear structure based on ARMAX model residual. Struct Control Health Monitor. 2016; 23: 218-236.

[16] Prakash G, Sadhu A, Narasimhan S, Brehe J-M. Initial service life data towards structural health monitoring of a concrete arch dam. Struct Control Health Monitor. 2018; 25:e2036.

[17] Sajedi SO, Liang X. A data-driven framework for near real-time and robust damage diagnosis of building structures. Struct Control Health Monitor. 2020; 27:e2488.

[18] Sharifzadeh M, Tarifard A, Moridi MA. Time-dependent behavior of tunnel lining in weak rock mass based on displacement back analysis method. Tunnel Undergr Space Technol. 2013; 38: 348-356.

[19] Shih S-Y, Sun F-K, Lee H. Temporal pattern attention for multivariate time series forecasting. Mach Learn. 2019; 108: 1421-1441.

[20] Spencer Jr. BF, Ruiz-Sandoval ME, Kurata N. Smart sensing technology: opportunities and challenges. Struct Control Health Monitor. 2004; 11: 349-368.

[21] Sterpi D, Gioda G. Visco-plastic behaviour around advancing tunnels in squeezing rock. Rock Mech Rock Eng. 2009; 42: 319-339.

[22] Tan X, Chen W, Wang L, Tan X, Yang J. Integrated approach for structural stability evaluation using real-time monitoring and statistical analysis: underwater shield tunnel case study. J Perform Constr Facilit. 2020; 34:04019118.

[23] Tan X, Chen W, Wu G, Wang L, Yang J. A structural health monitoring system for data analysis of segment joint opening in an underwater shield tunnel. Struct Health Monitor. 2020; 19: 1032-1050.

[24] Wang YW, Ni YQ. Bayesian dynamic forecasting of structural strain response using structural health monitoring data. Struct Control Health Monitor. 2020; 27:e2575.

[25] Wong K-Y. Instrumentation and health monitoring of cable-supported bridges. Struct Control Health Monitor. 2004; 11: 91-124.

[26] Yuan Y, Bai Y, Liu J. Assessment service state of tunnel structure. Tunnel Undergr Space Technol. 2012; 27: 72-85.

[27] Zhu H, Wang X, Chen X, Zhang L. Similarity search and performance prediction of shield tunnels in operation through time series data mining. Autom Constr. 2020; 114:103178.

RIGHTS & PERMISSIONS

2024 The Authors. Deep Underground Science and Engineering published by John Wiley & Sons Australia, Ltd on behalf of China University of Mining and Technology.