Research on the Interval Estimation of Aircraft Fuel Consumption based on the Data Distribution Characteristics

The interval estimation of aircraft fuel consumption is an important basis for airline system planning and operation decision. In order to solve the problem that the dispersion characteristics of actual payloads, itinerary difference in traditional fuel consumption estimation, and the uncertainty of operating environment and pilot accustomization and other factors are not fully considered,which affects the overall interval estimation results, this paper proposed an aircraft fuel consumption interval estimation method based on data deviation and density distribution under-sampling(US-D-DD). For all itineraries of the same type of aircraft, considering the deviation and density distribution of the data, the relevance vector machine(RVM) is used to establish the aircraft fuel consumption interval estimation model, and the aircraft fuel consumption interval estimation results with a certain level of confidence are obtained. Finally, the comprehensive evaluation index is given, and the results before and after considering the data distribution characteristics are compared. The experimental results show that the method achieves better interval estimation effect and verifies its effectiveness.