(Georgia Institute of Technology, 2019-12)
Puranik, Tejas G.; Mavris, Dimitri N.
Quantification and improvement of safety is one of the most important objectives among the General Aviation community. In recent years, machine learning techniques have emerged as an important enabler in the data-driven safety enhancement of aviation operations with a number of techniques being applied to flight data to identify and isolate anomalous (and potentially unsafe) operations. Energy-based metrics provide measurable indications of the energy state of the aircraft and can be viewed as an objective currency to evaluate various safety-critical conditions across a heterogeneous fleet of aircraft and operations. In this paper, a novel method of identifying instantaneous anomalies for retrospective safety analysis in General Aviation using energy-based metrics is proposed. Each flight data record is processed by a sliding window across the multi-variate time series of evaluated metrics. A Gaussian Mixture Model using energy metrics and their variability within each window is fit in order to predict the probability of any instant during the flight being nominal. Instances during flights that deviate from the nominal are isolated to identify potential increased levels of risk. The identified anomalies are compared with traditional methods of safety assessment such as exceedance detection to highlight the benefits of the developed method. The methodology is demonstrated using flight data records from two representative aircraft for critical phases of flight.
(Georgia Institute of Technology, 2019-06)
Mangortey, Eugene; Pinon, Olivia J.; Puranik, Tejas G.; Mavris, Dimitri N.
Traffic Management Initiatives (TMI) such as Ground Delay Programs (GDP) are instituted by traffic management personnel to address and reduce the impacts of constraints in the National Airspace System. Ground Delay Programs are initiated whenever demand is projected to exceed an airport’s acceptance rate over a lengthy period of time. Such instances occur when an airport is affected by conditions such as inclement weather, aircraft congestion, runway-related incidents, equipment failures, and other causes that do not fall in these categories. Over the years, efforts have been made to reduce the impact of Ground Delay Programs on airports and flight operations by predicting their occurrence. However, these efforts have largely focused on weather-related Ground Delay Programs, primarily due to a lack of access to comprehensive Ground Delay Program data. There has also been limited benchmarking of Machine Learning algorithms to predict the occurrence of Ground Delay Programs. Consequently, this research 1)fused data from the Traffic Flow Management System (TFMS), Aviation System Performance Metrics (ASPM), and Automated Surface Observing Systems (ASOS) datasets, and 2) leveraged supervised Machine Learning algorithms to develop prediction models as a means to predict the occurrence of weather and volume-related Ground Delay Programs. The Kappa Statistic evaluation metric revealed that Boosting Ensemble was the best suited algorithm for predicting the occurrence of weather and volume-related Ground Delay Programs.