Mason Archival Repository Service

Anomaly Detection in Aircraft Performance Data

Show simple item record

dc.contributor.advisor Tecuci, Gheorghe Nanduri, Syam Kiran Anvardh
dc.creator Nanduri, Syam Kiran Anvardh 2015-12-11 2016-09-09T16:55:45Z 2016-09-09T16:55:45Z
dc.description en_US
dc.description.abstract Detecting anomalous behavior in aircraft both during and after the flight is very important and it is of high interest for aviation safety agencies as well as airliners to ensure safe, efficient and environmentally clean flight operations. In this thesis, we study the capability of artificial neural networks in learning to identify anomalous behaviors in archived multivariate time series aircraft data and also in online data streams. The data is collected from flying 500 approaches to San Francisco International Airport on Boeing 777-200 ER aircraft using the X-Plane aircraft simulation. We analyzed the performance of Deep Autoencoders, Recurrent Neural Networks with Long Short-Term Memory units and Recurrent Neural Networks with Gate Recurrent Neural Networks units on the archived timeseries data. Once trained, the Recurrent Neural Network based algorithms can be applied to either previously collected flight data for retrospective analysis (offline mode) or they can be deployed during the flight to detect the anomalies in real time and alert the crew members (online mode). The performance of these algorithms is compared against MKAD, a Support Vector Machine based algorithm developed at NASA. These algorithms detected the anomalous flight types which MKAD was able to detect and also other anomalous flight types which MKAD was not able to detect. Experiments were conducted using various parameters combinations for MKAD to see how the resolution of Symbolic Aggregate Approximation encoding and size of alphabet set impact its performance. Similarly, various architectures of autoencoders and recurrent neural networks were designed and their performance was evaluated in terms of precision, recall and F1 score. Experimental results show that recurrent neural networks outperformed all other models in overall performance.
dc.language.iso en en_US
dc.subject anomaly detection en_US
dc.subject aircraft performance en_US
dc.subject recurrent neural networks en_US
dc.subject simulation data en_US
dc.subject autoencoders en_US
dc.subject Machine learning en_US
dc.title Anomaly Detection in Aircraft Performance Data en_US Master of Science in Computer Science en_US master's en_US Computer Science en_US George Mason University en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search MARS


My Account