Tunnel boring machine vibration-based deep learning for the ground identification of working faces

Liu, Mengbo; Liao, Shaoming; Yang, Yifeng; Men, Yanqing; He, Junzuo; Huang, Yong‐Liang

doi:10.1016/j.jrmge.2021.09.004

Cited by 65 publications

(14 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The geological conditions are always continued in a construction site. Therefore, the shield parameters can be clustered as factors to evaluate the types of geological characteristics [14] , [15] , [16] .…”

Section: Experimental Design Materials and Methodsmentioning

confidence: 99%

Data on prediction of geological characteristics during shield tunnelling in mixed soil and rock ground

Yan

2022

Data in Brief

View full text Add to dashboard Cite

Section: Experimental Design Materials and Methodsmentioning

confidence: 99%

Data on prediction of geological characteristics during shield tunnelling in mixed soil and rock ground

Yan

2022

Data in Brief

View full text Add to dashboard Cite

“…The results demonstrated that the accuracy is significantly improved after adding the vibration data. Liu et al [13] mounted accelerometers on a tunnel boring machine to identify the ground conditions of the working face. They investigated a number of machine learning methods and concluded that residual neural network outperformed other methods and achieved the highest accuracy of 98.28%.…”

Section: Introductionmentioning

confidence: 99%

Application of seismic sensors on measurement while drilling for real-time rock property detection

Khanal

Shen

Duan

et al. 2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Rock type and geological structures are often characterized with geotechnical and geological data gathered from boreholes that are drilled considerable distances apart. Such characterization may not identify localized variations associated with rock mass. The continual acquisition of rock data while drilling on a local scale has a potential to provide confidence in detecting rock types and interpreting rock properties, and depending on the application, may inform downstream operations. Drill returned parameters, such as, rotary speed, penetration rate, sound, torque, vibration, can provide insights into rock geotechnical properties. In the past, most of the researches in this area are limited to the use of conventional drill parameters such as penetration rate, rotary speed, torque and weight on bit. Noisy signals from drilling operations often pose a major challenge from using these conventional parameters to reliably interpret rock properties. To overcome this issue, in addition to the conventional drill parameters, the feasibility and application of seismic sensors on identifying relative rock properties have been explored in the current research. The interaction between the drill bit and rock mass being drilled generates seismic signals, which vary with different rock conditions and drilling operations. These seismic signals can be interpreted to detect rock types, rock properties, rock-ore interfaces and geological structures on a local scale. Laboratory experiments with a rotary drilling machine on synthesized rock samples with and without interfaces have been conducted. Preliminary laboratory results show clear seismic signatures when drilling through the rocks with various strengths and interfaces. The results obtained using the conventional drill parameters and seismic data have also been compared in this paper.

show abstract

“…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

Tunnel boring machine vibration-based deep learning for the ground identification of working faces

Cited by 65 publications

References 72 publications

Data on prediction of geological characteristics during shield tunnelling in mixed soil and rock ground

Data on prediction of geological characteristics during shield tunnelling in mixed soil and rock ground

Application of seismic sensors on measurement while drilling for real-time rock property detection

Reinforcement learning for the face support pressure of tunnel boring machines

Contact Info

Product

Resources

About