A Fuzzy-Neural Model for Co-ordination in Air Traffic Flow Management

The paper presents a methodological approach in the area of complex system studies. It provides a description of a model aimed at protecting air traffic sectors against overload in a large-scale air traffic system. In such a problem, different aspects must be taken into account: data uncertainty, complexity due to the large dimension of the air traffic system, structural and functional interactions, etc. The model proposed is a decentralised and co-ordinated system composed of a co-ordination level and a control level. The study points on the co-ordination level which decomposes the large sector network into several smaller overlapping subnetworks that can be controlled independently. A modified interaction prediction method is developed using a fuzzy model. This model provides the co-ordination parameters on the basis of imprecise data and an approximate reasoning. A specific inference mechanism based on a neural network is adopted in order to reduce time inference costs and provide a satisfying output.