Calculation of surface settlements caused by EPBM tunneling using artificial neural network, SVM, and Gaussian processes

Ocak, Ibrahim; Şeker, Şadi Evren

doi:10.1007/s12665-012-2214-x

Cited by 97 publications

(26 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, less work has been devoted to the influence of the interaction between tunnels on the structural forces induced in tunnel linings (Do et al 2014). Ocak and Seker (2013) predicted surface settlement over the twin EPB tunnels using three different methods: an artificial neural network, a support vector machine and Gaussian processes. This study considered 18 different parameters, that is, EPB operation factors, geometric properties of the tunnel and ground properties.…”

Section: Introductionmentioning

confidence: 99%

3D numerical investigation on the interaction between mechanized twin tunnels in soft ground

2014

View full text Add to dashboard Cite

During the construction of twin tunnels excavated in close proximity to each other, the prediction of the influence of a new tunnel construction on an already existing one plays an important role in the design and construction of the tunnels. The researches in the literature indicate that this influence depends to a great extent on the distance between the tunnels. However, most of the reported cases in the literature on the mechanized excavation of twin tunnels have focused on the effects of the relative position between the two tunnels on surface settlements. Some of them have dealt with the behaviour of the tunnel structure through the use of simplified numerical models. The numerical investigation performed in this study, using the FLAC 3D finite difference code, has made it possible to predict the impact between tunnels using full three-dimensional simulations, in which most of the elements of a mechanized tunnel process have been modelled. The effects of tunnel distance on the structural forces induced in both tunnels, and the displacements in the surrounding ground have been highlighted. A modification has been made to the superposition method to predict the settlement surface trough over twin tunnels.

show abstract

Section: Introductionmentioning

confidence: 99%

3D numerical investigation on the interaction between mechanized twin tunnels in soft ground

2014

View full text Add to dashboard Cite

show abstract

“…In this section, in order to investigate the influences of different parameters on the ground surface heave caused by tail void grouting pressure, taking Channel Tunnel Rail Link Contract 250 (C250) as an example, a series of parametric analyses are carried out on the basis of (24). e influences of the elastic modulus, tail void grouting pressure, tunnel radius, and tunnel depth are considered and analyzed.…”

Section: Parametric Analysismentioning

confidence: 99%

“…A large amount of research methods for prediction surface settlement induced by the shield tunnel have been developed over these years and can be summarized in empirical methods [1][2][3][4][5][6][7][8], analytical methods [9][10][11][12][13][14][15][16], and numerical simulation [17][18][19][20][21]. In recent years, artificial neural network [22][23][24] has been developed for analysis of surface settlement caused by the shield tunnel. However, the effect of tail void grouting pressure is not taken seriously in these methods predicting surface settlement.…”

Section: Introductionmentioning

confidence: 99%

Analytical Method for Evaluating the Ground Surface Settlement Caused by Tail Void Grouting Pressure in Shield Tunnel Construction

Zhu

2018

Advances in Civil Engineering

View full text Add to dashboard Cite

e tail void grouting is a key step in shield tunnel construction and has an important influence on the loading on the surrounding soil and on the resulting settlement. In order to estimate the ground surface settlement caused by tail void grouting pressure in tunnel construction, the loading on the surrounding soil is simplified as an expansion problem of the cylindrical cavity in semi-infinite elastic space. A simple analytical formula is deduced by using the virtual image technique and Fourier transform solutions. e effectiveness of the proposed method is verified by case studies. e effects of elastic modulus, tail void grouting pressure, tunnel radius, and tunnel depth on the ground surface heave are conducted. e results indicate that the computed results are in accordance with Ye's solution and it is more rational to consider the ground surface heave induced by tail void grouting pressure in the prediction of ground settlement due to shield excavation. Moreover, the ground surface heave owing to tail void grouting pressure resembled a Gaussian distributed curve. us, no matter the ground surface subsidence or ground surface heave can be predicted by means of adding the presented empirical formula to the Peck formula which cannot predict the ground surface heave. e ground surface heave decreases with an increase in elastic modulus. On the contrary, as the tail void grouting pressure and tunnel radius increase, the ground surface heave increases, respectively. e ground surface heave first steadily increases and then declines gradually with the tunnel depth increase.

show abstract

“…The results are evaluated via the root mean square error (RMSE) [9] and relative absolute error (RAE) [10]. …”

Section: ) Levenshtein Distance 2) Jaccard Index 3) Maxkfreqhashingmentioning

confidence: 99%

A Novel String Distance Function Based on Most Frequent K Characters

Şeker¹,

Altun²,

Ayan³

et al. 2014

IJMLC

Self Cite

View full text Add to dashboard Cite

Abstract-This study aims to publish a novel similarity metric to increase the speed of comparison operations. Also the new metric is suitable for distance-based operations among strings.Most of the simple calculation methods, such as string length are fast to calculate but doesn't represent the string correctly. On the other hand the methods like keeping the histogram over all characters in the string are slower but good to represent the string characteristics in some areas, like natural language.We propose a new metric, easy to calculate and satisfactory for string comparison.Method is built on a hash function, which gets a string at any size and outputs the most frequent K characters with their frequencies.The outputs are open for comparison and our studies showed that the success rate is quite satisfactory for the text mining operations.

show abstract

Calculation of surface settlements caused by EPBM tunneling using artificial neural network, SVM, and Gaussian processes

Cited by 97 publications

References 23 publications

3D numerical investigation on the interaction between mechanized twin tunnels in soft ground

3D numerical investigation on the interaction between mechanized twin tunnels in soft ground

Analytical Method for Evaluating the Ground Surface Settlement Caused by Tail Void Grouting Pressure in Shield Tunnel Construction

A Novel String Distance Function Based on Most Frequent K Characters

Contact Info

Product

Resources

About