Airport connectivity can improve the competitiveness of regions by attracting tourism and inward investment. Regions traditionally accessed international destinations via connecting flights to national gateway airports usually operated by full service network carriers (FSNC). However, the entry of low-cost carriers (LCC) in these markets has led to changes in incumbent FSNC service provision. We analyse how intra-European connectivity has changed at small airports between 2002 and 2012 and how LCC entry has affected the quality of day-return schedules in these markets. Results show that offline LCC connectivity is greater than that scheduled by FSNCs. Furthermore, LCC entry had a negative effect on the quality of the connectivity offered by FSNCs. Interestingly, we also found that day-return itineraries become more difficult for passengers in markets where the LCC is the sole operator. Regional policy-makers may need to more carefully consider the connectivity implications in the design of LCC start-up incentive schemes.

No abstract

The use of aircraft operation logs to develop a data-driven model to predict probable failures that could cause interruption poses many challenges and has yet to be fully explored. Given that aircraft is high-integrity assets, failures are exceedingly rare. Hence, the distribution of relevant log data containing prior signs will be heavily skewed towards the typical (healthy) scenario. Thus, this study presents a novel deep learning technique based on the auto-encoder and bidirectional gated recurrent unit networks to handle extremely rare failure predictions in aircraft predictive maintenance modelling. The auto-encoder is modified and trained to detect rare failures, and the result from the auto-encoder is fed into the convolutional bidirectional gated recurrent unit network to predict the next occurrence of failure. The proposed network architecture with the rescaled focal loss addresses the imbalance problem during model training. The effectiveness of the proposed method is evaluated using real-world test cases of log-based warning and failure messages obtained from the fleet database of aircraft central maintenance system records. The proposed model is compared to other similar deep learning approaches. The results indicated an 18% increase in precision, a 5% increase in recall, and a 10% increase in G-mean values. It also demonstrates reliability in anticipating rare failures within a predetermined, meaningful time frame.

No abstract

No abstract