Prediction of shield jamming risk for double-shield TBM tunnels based on numerical samples and random forest classifier

Hou, Shaokang; Liu, Yaoru; Zhuang, Wenyu; Zhang, Kai; Zhang, Rujiu; Yang, Qiang

doi:10.1007/s11440-022-01567-9

Cited by 15 publications

(1 citation statement)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some promising research domains for machine learning in tunnelling are the geological prognosis ahead of the face, the interpretation of monitoring results, automation and maintenance [32]. At present, however, research appears to be focussed on the following topics: prediction of TBM operational parameters [34,[39][40][41][42][43][44][45][46], penetration rate [47][48][49][50][51][52][53][54][55][56][57][58][59][60][61][62][63], porewater pressure [64], ground settlement [65][66][67], disc cutter replacement [68][69][70], jamming risk [71,72] and geological classification [73][74][75][76]). Few authors estimated the face support pressure of TBMs with machine learning [35,52].…”

Section: Introductionmentioning

confidence: 99%

Reinforcement learning for the face support pressure of tunnel boring machines

Soranzo¹,

Guardiani²,

Wu³

2023

Preprint

View full text Add to dashboard Cite

In tunnel excavation with boring machines, the tunnel face is supported to avoid collapse and minimise settlement. This article proposes the use of reinforcement learning, specifically the Deep Q-Network algorithm, to predict the face support pressure. The approach is tested both analytically and numerically. By using the soil properties ahead of the tunnel face and the overburden depth as the input, the algorithm is capable of predicting the optimal tunnel face support pressure, adapting to changes in geological and geometrical conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

Reinforcement learning for the face support pressure of tunnel boring machines

Soranzo¹,

Guardiani²,

Wu³

2023

Preprint

View full text Add to dashboard Cite

show abstract

Effects of Creep on Shield Tunnelling Through Squeezing Ground

Leone,

Nordas,

Anagnostou

2023

Rock Mech Rock Eng

View full text Add to dashboard Cite

The present work aims to improve the reliability of shield jamming and lining damage risk assessment in squeezing ground by analysing the effects of creep on the evolution of rock pressure over time. The study is based on numerical simulations of typical mechanised tunnelling processes, generally consisting of shield advance phases alternating with shorter or longer standstills for lining installation, maintenance, etc. A linear elastic—viscous plastic constitutive model based upon Perzyna’s overstress theory is employed, which considers the time-dependency of plastic deformations via a single viscosity parameter. The investigations demonstrate the following: (i) shield loading during advance increases with increasing viscosity under certain conditions, which contradicts the common perception in many existing works that creep is thoroughly favourable for shield jamming; (ii) creep is thoroughly unfavourable for shield loading during long standstills and long-term lining loading, due to the additional viscoplastic ground deformations manifested over time; (iii) the commonly adopted simplifying assumption of continuous excavation with the gross advance rate is adequate only where standstills are very short (e.g., for lining erection during the stop-and-go shield tunnelling process), but otherwise underestimates the shield loading, even in cases of regular inspection and maintenance standstills lasting only a few hours. Two application examples, the Fréjus safety gallery and the Gotthard Base tunnel, demonstrate the need to consider creep and the accuracy of modelling tunnel construction by a semi-discrete approach, where only the very short standstills for lining erection are considered via an average advance rate, but longer standstills are explicitly simulated.

show abstract