Probabilistic assessment of tunnel construction performance based on data

Abstract

A probabilistic model for estimating tunnel excavation time is learnt with data from past tunnel projects. The model is based on the Dynamic Bayesian Network technique. The model inputs are determined through an analysis of data from three tunnels built by means of the conventional tunneling method. The data motivate the development of a novel probability distribution to describe the excavation performance. In addition, the probability of construction failure events and the delay caused by such failures are estimated using databases available in the literature. The model is applied to a case study, in which it is demonstrated how observations from the tunnel construction process can be included to continuously update the prediction of excavation time.

Predicting tunnel squeezing with incomplete data using Bayesian networks

“…BNs were introduced by Pearl (1986) to more easily deal with conditional dependency relationships between the (observable or unobservable) random variables of a statistical model, and they have been shown to have advantages to deal with inference, classification, and decision making problems (Aguilera et al, 2011). As a result, they are becoming increasingly popular in fields such as environmental science (Aguilera et al, 2011;Uusitalo, 2007), ecology (Landuyt et al, 2013), water resources management (Batchelor and Cain, 1999), and agriculture (Cain et al, 2003); and they have also been employed in geotechnical engineering (Huang et al, 2012;Jimenez-Rodriguez and Sitar, 2006;Medina-Cetina and Nadim, 2008;Peng et al, 2014;Schubert et al, 2012;Song et al, 2012;Sousa and Einstein, 2012;Špačková et al, 2013;Xu et al, 2011;Zazzaro et al, 2012;Zhang et al, 2011).…”

Construction and Operation for Utilities Tunnel Public Project in China: An Analysis Based on G-S Interactive Finance Framework

“…Different with traditional open-cut style for pipelines, utilities tunnel can avoid resource wasting and inconvenience to society, because traditional open-cut style need dig the ground many times. It can also decrease safety questions and can repair timely for pipeline obstacle [1][2][3][4][5].…”

Entropy-Based Risk Control of Geological Disasters in Mountain Tunnels Under Uncertain Environments

“…The relationship between uncertainty and risk and its impact on risk analysis has been discussed by many scholars, such as Aven [14] who proposed that using (C, U) instead of (C, P), where "U" indicates uncertainty lead to a risk description associated with the definition of (C, U) as (C', Q, K), where C' denotes specified consequences; Q is a measure of uncertainty such as probability [15,16], imprecise probability [17], or a fuzzy number [18,19]; and K can be considered to represent background knowledge on which the specifications and assignments of C' and Q are based [20,21]. For the new definition of risk, it can be seen that the main contents of risk research is: representing entropy was used to quantify the degree of uncertainty of background knowledge.…”