A Knowledge Transfer-based Methodology for Risk Assessment of Emergency Schemes

Abstract

Due to insufficient knowledge of rare accidents, it is essential to transfer knowledge from source systems with sufficient cases into target systems with limited cases. In this study, a knowledge transfer-based methodology is proposed to evaluate emergency schemes from the perspective of emergency risk in presence of limited accident cases. By considering dynamic evolution and operational characteristics of accidents, a hybrid model integrating dynamic Bayesian networks (DBN) and program evaluation and review technique (PERT) is introduced. In the integrated model, we transferred graph structures and parameters to obtain emergency schemes based on the similarities between the source systems and target systems. On the one hand, to design the operation of emergency schemes, we utilized PERT to judge the logical relationships and the response-time requirement of the emergency procedures. On the other hand, to evaluate and prevent emergency risk, we employed DBN to conduct the dynamic risk assessment of emergency operations.