Search Results

The exponential increase in the number of aircrafts and air travelers has triggered new innovations which aim to make airline services more reliable and consumer friendly. Quick and efficient maintenance actions with minimum downtime are the need of the hour. Areas that have a large potential for improvement in this regard are the real time use of diagnostic data, filtering/elimination of nuisance faults and machine learning capabilities with respect to maintenance actions. Although, numerous LRUs installed on the aircraft generate massive amounts of diagnostic data to detect any possible issue or LRU failure, it is seldom used in real time. The turnaround time for LRU maintenance can be greatly reduced if the results of the diagnostics conducted during LRU normal operation is relayed to ground stations in real-time. This enables the maintenance engineers to plan ahead and initiate maintenance actions well before the aircraft lands and becomes available for maintenance.

Turbulence is by far the number one concern of anxious passengers and a cause for airline injuries. Apart from causing discomfort to passengers, it also results in unplanned downtime of aircrafts. Currently the Air Traffic Control (ATC) and the meteorological weather charts aid the pilot in devising flight paths that avoid turbulent regions. Even with such tailored flight paths, pilots report constant encounters with turbulence. The probability of turbulence avoidance can be increased by the use of predictive models on historical and transactional data. This paper proposes the use of predictive analytics on meteorological data over the geographical area where the aircraft is intended to fly. The weather predictions are then relayed to the cloud server which can be accessed by the aircraft planned to fly in the same region. Predictive algorithms that use Time series forecasting models are discussed and their comparative performance is documented.