Reliable and predictable ground operations are essential for 4D aircraft trajectories. The ground trajectory of an aircraft primarily consists of the handling processes at the stand, defined as the aircraft turnaround. The turnaround is mainly controlled by operational experts, but the critical aircraft boarding is driven by the passengers' experience and willingness or ability to follow the proposed procedures. Using a complexity metric for the evaluation of the boarding progress we developed a machine learning approach to predict the boarding progress over time. A calibrated boarding model provides reliable input data for our recurrent neural network approach for both learning and prediction. The input contains of discrete time series, which inherently considers the dynamic passenger behavior. In particular we use a Long Short-Term Memory network to learn this dynamical behavior over time with regards to the given boarding progress indicators.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Real-time Prediction of Aircraft Boarding


    Contributors:


    Publication date :

    2018-09-01


    Size :

    1056250 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Aircraft Boarding Ramp

    G. K. Bobov / V. T. Mishin / V. T. Kostenko | NTIS | 1969


    AIRCRAFT BOARDING OPTIMISATION SYSTEM

    PANJER FREDERIK ADRIAN STEPHAN | European Patent Office | 2024

    Free access

    ADAPTIVE AIRCRAFT BOARDING SYSTEM

    MIGNOGNA ALESSANDRO | European Patent Office | 2023

    Free access

    AIRCRAFT PASSENGER BOARDING SYSTEM

    COX JOSEPH J / COX ISAIAH W | European Patent Office | 2015

    Free access

    Aircraft passenger boarding system

    COX JOSEPH J / COX ISAIAH W | European Patent Office | 2017

    Free access