A Novel Method of Emergency Situation Evaluation for Deep-Sea Based on Bayesian Network

• Main Authors: Kun Lang, Dongsen Si, Zhihong Ma
• Format: Article
• Language: English
• Published: IEEE 2020-01-01
• Series: IEEE Access
• Subjects: Situation analysis; deep-sea emergency; Bayesian network; fuzzy comprehensive evaluation
• Online Access: https://ieeexplore.ieee.org/document/9262916/

In order to make effective emergency decisions timely, this paper proposes an intelligent emergency situation evaluation method based on the Bayesian network for deep-sea emergency response, which is used to evaluate the deep-sea emergency situation quantitatively by calculating the occurrence probability of emergency situation risk at each risk level. In this research, a Bayesian network is constructed to analyze the deep-sea emergency situation firstly. Aiming at the bottleneck problem of insufficient case data for the Bayesian network's parameter learning, an automatic parameter allocation algorithm is presented based on the domain knowledge. Then, in order to obtain the quantitative analysis results of the overall emergency situation, a comprehensive situation evaluation model is presented based on the Bayesian network reasoning results, and the fuzzy comprehensive evaluation theory. Finally, a case study is given to illustrate this proposed method's application, which can provide a scientific basis for decision-making in the deep-sea emergency practice.