A fuzzy Bayesian network-based approach to target ship situation analysis

Abstract

The naval battlefield environment is complex, and extracting key situational factors and conducting ship situational estimation becomes a key problem in operations. To address this problem, a fuzzy Bayesian network-based ship situational analysis method is proposed to decompose and construct a fault tree model of the factors influencing the naval battlefield situational situation; then perform node conversion between fault tree and Bayesian network to establish a Bayesian network model; quantify the expert evaluation results using fuzzy sets and improve the conditional probability table. Simulation analysis is conducted, and the results show that the proposed method has a correct rate of over 75% for ship's situational pattern estimation.