Reliability Analysis of Deep Foundation Pit Using the Gaussian Copula-Based Bayesian Network
Bin Tan, Qiyuan Peng
Source abstract
Urban underground space development has heightened concerns over the safety of deep foundation pit construction. This study conducted time-series monitoring of critical safety-influencing factors and applied the Gaussian copula-based Bayesian network (GCBN) model for comprehensive reliability analysis of deep foundation pit support structures. The GCBN model, integrating the multivariate data management of pair copula with Bayesian network’s uncertainty handling, found that building settlement has the greatest impact on the safety of deep foundation pit and revealed a reliability index (β) of 0.44 in an actual case, suggesting a hazardous condition. Based on the reliability index β, emergency measures were promptly taken. Compared to traditional reliability methods, the approach presented in this paper takes into account the dependence among monitoring indicators, which is more aligned with actual engineering conditions and holds significant reference value for the safety assessment of underground engineering structures.
Evidence graph
No public relationships recorded yet.
Integrity note: This page is a factual metadata record created by deterministic ingestion. It is not a claim that the work moves a mathematical frontier or has been independently verified.