Machine learning approach to predict aircraft boarding

Kết quả hình ảnh cho Machine learning approach to predict aircraft boarding images

Since no operational data of the specific passenger behavior is available, we used a reliable, validated boarding simulation environment to provide data about the aircraft boarding events. First predictions show that uni-variate input (seat load progress) produces insufficient results, so we consider expected passenger interactions in the aircraft cabin as well. A reliable prediction of all aircraft-related processes along the specific trajectories is essential for punctual operations.

The ground trajectory of an aircraft primarily consists of the handling processes at the stand (deboarding, catering, fueling, cleaning, boarding, unloading, and loading), which are defined as the aircraft turnaround. Since today there are no operational sensor data available from inside the cabin, we simulated the boarding process with a validated boarding model (Schultz, 2018aSchultz, 2018b). The complexity metric is a multi-variate input for an LSTM model, which is trained with boarding simulation data (time series) and enables a prediction of the final boarding time. We could demonstrate that the proposed complexity metric is a necessary element for prediction of the aircraft boarding progress. A closer look at differences between boarding progress and prediction shows an inherent positive offset.

Collected and summarized from the source below by Minh Pham