Search

AII aims to infer the most likely future intent based on current aircraft motion states, therefore, it has become an essential method to enhance air traffic situational awareness [1]. Generally, aircraft motion states consist of aircraft IDs, latitude/longitude/altitude coordinates, ground speeds, accelerations and heading angles, which could be directly gained from the surveillance infrastructures like Radars and Automatic Dependent Surveillance-Broadcast (ADS-B) systems. Given current aircraft motion states, one important issue in gaining future air traffic situation prediction is to infer aircraft intent. This is significant because AII plays a fundamental role in conflict detection and avoidance, which hence determines the operational safety of air transportation system.

With the increasing incidence of malfunctions of air transportation system due to severe weather, the Air Traffic Flow Network Rerouting (ATFNR) is playing an important role in improving the global efficiency of air traffic. This paper adopts a multi-objective optimization model to solve the ATFNR problem to make a tradeoff between the total delay costs and the airlines fairness. Meanwhile, a specially-designed algorithm based on multi-objective comprehensive learning particle swarm optimizer (MOCLPSO) under the cooperative co-evolution framework is presented to handle this large scale, multi-objective real-world optimization problem. The empirical studies show that the presented methodology is effective and outperforms an existing approach to ATFNR problem as well as two well-known Multi-Objective Optimization Algorithms.