Research on Situation Awareness of Airport Operation Based on Petri Nets

The civil aviation industry is undergoing rapid development. However, the on-time rate of airport flights and passenger service quality are not particularly satisfying. The cause of the above problems is the contradiction between the limited operational support capability and the continuous growth of passenger traffic volume. Therefore, the key to solving these problems is achieving situation awareness of airport operation. Many situation awareness algorithms, typically categorized into modeling and machine learning, have been proposed in the past years. However, existing models lack flexibility and their prediction accuracy is unstable. Machine learning’s results cannot be timely and effective when external conditions are suddenly changed although some related algorithms have higher accuracy because of the retraining of artificial neural network (ANN). This paper proposes a situation awareness method based on Petri nets (PNs). This method introduces the queuing theory and perceptual parameters into the existing PN and constructs the perceptual PNs’ model for general service systems so that it can quickly model different scene service systems. In combination with the ANN, this paper proposes a complete situation awareness algorithm to realize a sustained and accurate situation awareness prediction of the service system by solving point estimations of the macroscopic and microscopic situation in this model, which helps to address some challenges faced by current civil aviation airports. By experimenting on-ground support in civil aviation airports and the access of website as well as comparing the situation separately with Airport Collaborative Decision Making and stochastic PNs, the validity and accuracy of the algorithm proposed in this paper are well verified.