Consideration of Passenger Interactions for the Prediction of Aircraft Boarding Time

Abstract

In this paper we address the prediction of aircraft boarding using a machine learning approach. Reliable process predictions of aircraft turnaround are an important element to further increase the punctuality of airline operations. In this context, aircraft 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. Thus, we used a developed complexity metric to evaluate the actual boarding progress and a machine learning approach to predict the final boarding time during running operations. A validated passenger boarding model is used to provide reliable aircraft status data, since no operational data are available today. These data are aggregated to a time-based complexity value and used as input for our recurrent neural network approach for predicting the boarding progress. In particular we use a Long Short-Term Memory model to learn the dynamical passenger behavior over time with regards to the given complexity metric. Status QuoOur research is connected to three different topics: Aircraft turnaround, passenger behavior, and machine learning. Comprehensive overviews are provided for aircraft turnaround [16], for boarding [17], and for the corresponding economic impact [12,18,19]. Relevant studies include, but are not limited to, the following current examples.Aircraft turnaround, as part of the aircraft trajectory over the day of operations, has to be part of the optimization strategies for minimizing flight delays [20] and ensuring flight connections considering operational uncertainties [21,22]. In this context, turnaround absorbs inbound delay [15] and could enhance slot adherence at airports [23] or mitigate problems of push-back scheduling [24]. A microscopic turnaround model provides an open and closed-loop process control for higher automation levels in turnaround management [25]. The inter-aircraft propagated delay is focused on in Reference [26], since individual delays could result in parallel demand of turnaround resources (personnel, space, and equipment). Furthermore, delayed use of infrastructure may cause excessive demand in later time frames, and both turnaround stability and resource efficiency will provide significant benefits for airline and airport operations [15,27]. The compatibility of airline operations, existing ground handling procedures and airport infrastructure requirements were analyzed in the context of alternative energy concepts [28]. With a focus on efficient aircraft boarding, Milne and Kelly [29] develop a method that assigns passengers to seats so that their luggage is distributed evenly throughout the cabin, assuming a less time-consuming process for finding available storage in the overhead compartment. Qiang et al. [30] propose a boarding strategy that allows passengers with a large amount of hand luggage to board first. Milne and Salari [31] assign passengers to seats according to the number of hand luggage items and propose that passenge...

Applications of Artificial Intelligence in the Air Transport Industry: A Bibliometric and Systematic Literature Review

“…This cluster contains the largest number of studies, comprising 65% of the total. Several of these studies address the topic of delay prediction (Etani 2019;Schultz and Reitmann 2018;Wang et al 2018), employing algorithms from various types, including supervised, unsupervised, artificial neural networks (ANN), and reinforcement learning. However, a critical argument can be made: the results of these studies primarily focus on optimising algorithm parameters for improved future predictions, without sufficient consideration for real-life applicability, as confirmed by our findings.…”