Diversion tunnel safety evaluation method, system and device and medium

The invention discloses a diversion tunnel safety evaluation method, system and device and a medium, and the method comprises the steps: firstly, obtaining the prior probability of a Bayesian network through the combination of inspection data and model simulation; then, according to a fuzzy set theory, converting the fault tree of the system into a corresponding Bayesian network model, and obtaining a conditional probability table of different node features; and finally, based on Bayesian network bidirectional reasoning calculation and sensitivity analysis capability, calculating a safety risk occurrence probability and identifying a key risk factor, and performing accident cause diagnosis at the same time. The method has the advantages that the probability of each node of the Bayesian network is accurately obtained by analyzing historical data, the logic relation between the failure probability of the network event and different characteristics between the event nodes is constructed by adopting the fuzzy set