Risk Diagnosis Analysis of Ethane Storage Tank Leakage Based on Fault Tree and Fuzzy Bayesian Network

This study proposes a risk assessment method for ethane tank leakage based on Fault Tree Analysis (FTA) and the Fuzzy Bayesian Network (FBN). It aims to diagnose and probabilistically evaluate system risks in scenarios where leakage data are imprecise and insufficient. Initially, a fault tree for ethane tank leakage risk is constructed using the connectivity of logical gates. Then, through the analysis of minimal cut sets, the fundamental causes of ethane tank leakage risk are identified, including cracking, instability, and corrosion perforation. Subsequently, the fault tree is mapped into a Bayesian network, which is then integrated to transform it into an FTA-FBN risk diagnostic probability model. Prior probabilities of parent nodes and conditional probability tables are obtained through fuzzy mathematics principles and expert guidance. These are combined with Bayesian inference to derive posterior probabilities, thereby determining the contribution of each basic event to the ethane tank leakage risk. By leveraging the advantages of the fuzzy Bayesian network in handling uncertain problems, the model and analysis effectively address the ambiguities encountered in real-world scenarios. In order to better cope with the uncertainty of leakage, the weakest t-norm algorithm and the similarity aggregation method are introduced for the parameter learning of the fuzzy Bayesian network to achieve an accurate solution of the model. Finally, this integrated model is used in a real case to study the causes of ethane storage tank leakage. The research results are of great scientific significance for revealing the evolution mechanism of ethane storage tank leakage accidents and ensuring system safety throughout the life cycle.