Research In Detection Of Flight Delay Based On Biological Immune Algorithm

The detection and early warning of large-scale flight delays in hub airport have become urgent to study and solve problems. The detection of the state of flight delays and the distinguish between self and non-self in the immune system are greatly similay. The paper attempts to apply the immune algorithm to diagnosis and forecast of the state of the airport scheduled flight delay, making useful explorations. the main work include:Putting forward to the detecting method of airport scheduled flight delay state base on immune negative selection algorithm, associating the immune mechanism of a biological system with the flight operational mechanism of an airport, and establishing the corresponding self aggregate, cells for detecting, antigen information and the matching model for them, and making the authentication and implementing; putting forward to the detecting and early warning method of the dynamic clonal selection algorithm based on probability, applying the dynamic clonal selection algorithm to test flight, using the probability of flight delay in a certain period as divisiory standards of mature detector and memory detector, presenting the concept of the relative age in eliminating anile detectors in the process of training detectors, using corresponding flight data according to different time section of different date, definiting the weight coefficient of flight operation data, and improving the detecting and forecasting accuracy; aiming at the actual operation of flights happened for one moment in one day, making use of real-timely predicted method based on the distributed detection model and predicting the departure flight delayed state in the next moment with real-timely trained detectors for every week, the experimental results show that this method can not only exactly real-timely detect departure flight status, but also accurately predict the cumulative number of flights delayed in the next time period.