Predicting Convergence Rate of Namaklan Twin Tunnels Using Machine Learning Methods

Torabi-Kaveh, Mehdi; Sarshari, B.

doi:10.1007/s13369-019-04239-1

Cited by 23 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its advantages are that it only requires the input of convergence deformation measurement data, simple calculation, and high efficiency. Data analysis methods include time series models [10][11][12], machine learning models [13][14][15][16], grey prediction models [17][18][19], and other data-driven special prediction models. Time series models represented by the ARIMA model exhibit stable performance and wide applicability.…”

Section: Introductionmentioning

confidence: 99%

Lateral Convergence Deformation Prediction of Subway Shield Tunnel Based on Kalman Model

Bao,

Zheng,

Tang

et al. 2024

Sustainability

View full text Add to dashboard Cite

In order to optimize the structure of a subway shield tunnel, minimize injuries, and avoid potential safety hazards, the lateral convergence deformation of subway shield tunnels should be predicted. In terms of accuracy and stability, existing prediction models perform poorly in obtaining the lateral convergence deformation value of a non-stationary small-sized sample of a subway shield tunnel. In this paper, a lateral convergence model of a subway shield tunnel based on the Kalman algorithm is constructed based on Kalman filtering theory. The model is efficient, adaptive, and robust and can accurately predict the lateral convergence deformation of a subway shield tunnel. Taking the horizontal diameter of a 200-ring shield segment in the interval section of a subway tunnel as an example, we have proved that the residuals of the Kalman prediction model are small, the residual distribution conforms to the normal distribution, and the prediction effect is great. The model is suitable for the prediction of more than five periods of data, and the prediction accuracy of the model improves with an increase in the number of data periods. In addition, in this paper, we compare the Kalman model with the GM(1,1) model and the GM–Markov model, and the RMSE, NRMSE, MAPE, and R2 are used as evaluation indices. The results show that the Kalman model has a higher prediction accuracy and is more suitable for predicting the lateral convergence deformation of a subway shield tunnel.

show abstract

Section: Introductionmentioning

confidence: 99%

Lateral Convergence Deformation Prediction of Subway Shield Tunnel Based on Kalman Model

Bao,

Zheng,

Tang

et al. 2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…The empirical method does not rely on the finite element model, but the empirical formula summarized by the empirical data has a smaller scope of application and lower prediction accuracy. The prediction of time series model includes ARIMA model [6][7][8], artificial neural network [9][10][11][12], grey prediction model [13][14][15][16][17], etc. It only needs to input the measured data of convergence deformation, and it has simple calculation and high efficiency.…”

Section: Introductionmentioning

confidence: 99%

Lateral Convergence Deformation Prediction of Subway Shield Tunnel Based on Kalman Model

Bao,

Zheng,

Tang

et al. 2024

Preprint

View full text Add to dashboard Cite

In order to master the structure state of subway shield tunnel, reduce the diseases and avoid the potential safety hazards, the lateral convergence deformation of subway shield tunnels should be predicted. For the non-stationarity small sample size of subway shield tunnel lateral convergence deformation value, the existing prediction models have poor performance in terms of accuracy and stability. In this paper, a lateral convergence model of subway shield tunnel based on Kalman algorithm is constructed based on Kalman filtering theory. The model is efficient, adaptive and robust, and can accurately predict the lateral convergence deformation of subway shield tunnel. Taking the horizontal diameter of 200 rings shield segment in the interval section of a subway tunnel as an example, it is proved that the residuals of the Kalman prediction model are small, the residual distribution conforms to the normal distribution, and the prediction effect is great. The model is suitable for the prediction of more than 5 periods of data, and the prediction accuracy of the model is improved with the increase of the number of data periods. In addition, the Kalman model is compared with GM(1,1) model and GM-Markov model, and RMSE and MAPE are introduced as evaluation indexes. The results show that the Kalman model has higher prediction accuracy and is more suitable for predicting the lateral convergence deformation of subway shield tunnel.

show abstract

“…The influence is usually decided by the ground properties, in-situ stress, tunnel span, rock pillar thickness, and excavation methods. Existing research concentrates on the interaction between left–right twin tunnels 8 – 13 , mechanical characteristics during tunnel construction 14 – 16 , ground settlement characteristic 17 , 18 , optimization of rock pillar thickness and construction sequences 19 – 23 , the prediction method of tunnel convergence 24 , as well as the influence of twin tunnels on the surrounding buildings 25 . Previous studies have also showed that excavation methods have a significant influence on the stability of twin tunnels 26 , 27 .…”

Section: Introductionmentioning

confidence: 99%

Stability evaluation of rock pillar between twin tunnels using the YAI

Zhang

Liu

et al. 2023

Sci Rep

View full text Add to dashboard Cite

The stability of rock pillar is crucial for ensuring the construction safety of twin tunnels with small clearance, especially when transitioning from the traditional left–right tunnel layouts to the up-down configurations due to complex and variable site constraints. However, there are limited researches on the evaluation and comparative study of the stability of these two types of rock pillars in twin tunnels. This paper introduces the yield approach index (YAI) as a measure to assess the stability of rock pillar in twin tunnels with small clearance, and various influencing factors including side pressure coefficient (SPC), stress release rate (SRR), and the thickness of rock pillar (characterised by the ratio of rock pillar thickness to tunnel diameter, RPT/TD) are considered in the analysis. The study compares and analyzes the stability differences of the rock pillar in different situations. It is observed that the two sides of up-down tunnels pose a higher risk while the rock pillar in the left–right configuration being the most vulnerable. The stability of the rock pillar between the up-down tunnels is significantly higher than that of the left–right tunnels under similar conditions. Moreover, the up-down tunnels exhibit greater sensitivity to SPC, whereas the left–right tunnels are more sensitive to SRR. Additionally, the study reveals that increasing the RPT/TD can effectively improve the stability of the rock pillar within a specific range (1/4 to 2/3). The research method and obtained results of this paper can provide some important references for the stability evaluation and design of twin tunnels with small clearance.

show abstract

Predicting Convergence Rate of Namaklan Twin Tunnels Using Machine Learning Methods

Cited by 23 publications

References 29 publications

Lateral Convergence Deformation Prediction of Subway Shield Tunnel Based on Kalman Model

Lateral Convergence Deformation Prediction of Subway Shield Tunnel Based on Kalman Model

Lateral Convergence Deformation Prediction of Subway Shield Tunnel Based on Kalman Model

Stability evaluation of rock pillar between twin tunnels using the YAI

Contact Info

Product

Resources

About