Using Bayesian Networks for the Purpose of Risk Analysis at Railway Level Crossings

Abstract

According to accident/incident statistics, railway level crossing (LX) is one of the most critical points in railways form the safety point of view. In the present paper, causal reasoning analysis of LX accidents is carried out based on Bayesian networks (BNs). In particular, causal structural constraints are introduced to establish BN risk model for the purpose of combining empirical knowledge and statistical data, thus to identify effective causalities and avoid inappropriate structural connections. Moreover, forward and reverse inferences based on the BN risk model are performed to predict LX accident occurrence and quantify the contribution degree of various impacting factors respectively, so as to identify the riskiest factors. Besides, influence strength analysis is further carried out to scrutinize the influence strength of various causal factors on LX accident occurrence. The outcomes of the BN risk model offer significant insights on exploring practical improvement recommendations to improve LX safety.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 10 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.