Study on Safety Assessment of Air Traffic Management System Based on Bayesian Networks

An index system of evaluating safety for air traffic management system based on system engineering idea and principle, where human, facility, environment and management are considered as essential factors was established. A method for Air Traffic Management safety assessment using Bayesian network (BN) was constructed, based on its excellent abilities of expressing and reasoning knowledge under uncertain environment. The assessment model is able to deal with complicated logic relationship as well as the different opinions of experts. The output of the safety assessment model can be used to predict and diagnose different safety conditions. It was suggested that the safety assessment model is effective and reasonable by applying to safety assessment of Air Traffic Management units.