Shield proximity existing tunnel safety evaluation method based on data mining and data fusion

Abstract

The invention belongs to the field of shield underneath pass existing tunnel safety risk evaluation, and particularly discloses a shield proximity existing tunnel safety evaluation method based on data mining and data fusion. The method comprises the following steps: establishing a shield underneath pass existing tunnel safety evaluation index system and a risk grading standard; designing a Bayesian network by adopting a fault tree analysis method; obtaining an expert evaluation interval fuzzy set of a root node in the Bayesian network based on a group decision judged by an expert, and fusingthe expert evaluation interval fuzzy set by adopting an improved evidence theory to obtain fuzzy prior probability distribution of the root node of the Bayesian network; and based on the constructed Bayesian network model, carrying out risk probability reasoning and sensitivity analysis of shield underneath passing through the existing tunnel, and determining the safety risk level and key controlfactors of shield underneath passing through the existing tunnel. According to the method, more accurate and reasonable comprehensive evaluation of the safety risk of shield underneath passing throughthe existing tunnel is realized, and a powerful basis is provided for safety risk early warning and control decision of engineering.

Description

technical field [0001] The present invention belongs to the field of safety risk assessment of existing tunnels under shield tunneling, in particular, it relates to a safety assessment method based on data mining and data fusion for shield approaching existing tunnels, and more specifically, it relates to a method based on fuzzy Bayesian and Evidence theory-based data mining and data fusion are close to existing tunnel safety evaluation methods. Background technique [0002] In recent years, my country's underground rail network lines have become more and more dense, and it has become more and more common for new tunnel shields to pass under existing tunnels. When the shield tunnel passes through the existing tunnel for construction, it will inevitably cause disturbance and deformation of the soil layer, thereby inducing the settlement and deformation of the existing tunnel, and seriously affecting the normal operation of the existing tunnel. Therefore, it is of great engin...

AI Technical Summary

Problems solved by technology

Most of these studies mainly focus on analyzing the deformation of existing tunnels through numerical simulation and model tests. They are often modeled and analyzed under simplified assumptions, and they do not take into account the ambiguity and Uncertainty, there is a certain degree of error and deviation from the actual engineering situation

At present, there are very few studies on the systematic safety evaluation and early warning of tunnel construction safety issues from the perspective of risk assessment, and the analysis methods are still stuck in the traditional AHP and fuzzy comprehensive evaluation methods.

Among them, the analytic hierarchy process mainly uses the method of pairwise comparison to determine the relative importance of each element, and solves the eigenvector of the judgment matrix to determine the weight of each element, and does not consider the fuzzy and uncertain information of the system; Although the fuzzy comprehensive evaluation method can quantitatively evaluate fuzzy evaluation objects, its calculation is complicated, and the determination of index weight is more subjective.

Although these studies have taken into account the comprehensive effects of multi-source risk factors to a certain extent, the mining of data information is still not sufficient and objective for shield tunneling under the existing tunnel system that integrates fuzzy, random and uncertain information. , so that the safety hazards in the construction process cannot be identified, and it is difficult to achieve better safety risk decision-making and control

Images