Skip to content
Back to outputs

A two phase method to detect abnormalities in aircraft flight data and to rank their impact on individual flights

Research output: Contribution to journalArticlepeer-review

Standard

A two phase method to detect abnormalities in aircraft flight data and to rank their impact on individual flights. / Smart, Edward; Brown, David J.; Denman, J.

In: IEEE Transactions on Intelligent Transportation Systems, Vol. 13, No. 3, 09.2012, p. 1253-1265.

Research output: Contribution to journalArticlepeer-review

Harvard

Smart, E, Brown, DJ & Denman, J 2012, 'A two phase method to detect abnormalities in aircraft flight data and to rank their impact on individual flights', IEEE Transactions on Intelligent Transportation Systems, vol. 13, no. 3, pp. 1253-1265. https://doi.org/10.1109/TITS.2012.2188391

APA

Smart, E., Brown, D. J., & Denman, J. (2012). A two phase method to detect abnormalities in aircraft flight data and to rank their impact on individual flights. IEEE Transactions on Intelligent Transportation Systems, 13(3), 1253-1265. https://doi.org/10.1109/TITS.2012.2188391

Vancouver

Author

Smart, Edward ; Brown, David J. ; Denman, J. / A two phase method to detect abnormalities in aircraft flight data and to rank their impact on individual flights. In: IEEE Transactions on Intelligent Transportation Systems. 2012 ; Vol. 13, No. 3. pp. 1253-1265.

Bibtex

@article{9b0a5fa523f54d80a5c2a1266f331bfb,
title = "A two phase method to detect abnormalities in aircraft flight data and to rank their impact on individual flights",
abstract = "A two phase novelty detection approach to locating abnormalities in the descent phase of aircraft flight data is presented. It has the ability to model normal time series data by analysing snapshots at chosen heights in the descent, weight individual abnormalities and quantitatively assess the overall level of abnormality of a flight during the descent to a given runway. The method models normal approaches to a given runway (as determined by the airline 19s Standard Operating Procedures) and detects and ranks deviations from that model. The approach expands on a recommendation by the UK Air Accident Investigation Branch to the UK Civil Aviation Authority. The first phase quantifies abnormalities at certain heights in a flight. The second phase ranks all flights to identify the most abnormal; each phase using a one class classifier. For both the first and second phases, the Support Vector Machine (SVM), the Mixture of Gaussians and the K-means one class classifiers are compared. The method is tested using a dataset containing manually labelled abnormal flights. The results show that the SVM provides the best detection rates and that the approach identifies unseen abnormalities with a high rate of accuracy. The feature selection tool F-score is used to identify differences between the abnormal and normal datasets. It identifies the heights where the discrimination between the two sets is largest and the aircraft parameters most responsible for these variations. The method presented adds much value to the existing event based approach.",
keywords = "aircraft landing guidance, artificial intelligence, fault diagnosis, support vector machines",
author = "Edward Smart and Brown, {David J.} and J. Denman",
note = "Funders: EPSRC.",
year = "2012",
month = sep,
doi = "10.1109/TITS.2012.2188391",
language = "English",
volume = "13",
pages = "1253--1265",
journal = "IEEE Transactions on Intelligent Transportation Systems",
issn = "1524-9050",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

RIS

TY - JOUR

T1 - A two phase method to detect abnormalities in aircraft flight data and to rank their impact on individual flights

AU - Smart, Edward

AU - Brown, David J.

AU - Denman, J.

N1 - Funders: EPSRC.

PY - 2012/9

Y1 - 2012/9

N2 - A two phase novelty detection approach to locating abnormalities in the descent phase of aircraft flight data is presented. It has the ability to model normal time series data by analysing snapshots at chosen heights in the descent, weight individual abnormalities and quantitatively assess the overall level of abnormality of a flight during the descent to a given runway. The method models normal approaches to a given runway (as determined by the airline 19s Standard Operating Procedures) and detects and ranks deviations from that model. The approach expands on a recommendation by the UK Air Accident Investigation Branch to the UK Civil Aviation Authority. The first phase quantifies abnormalities at certain heights in a flight. The second phase ranks all flights to identify the most abnormal; each phase using a one class classifier. For both the first and second phases, the Support Vector Machine (SVM), the Mixture of Gaussians and the K-means one class classifiers are compared. The method is tested using a dataset containing manually labelled abnormal flights. The results show that the SVM provides the best detection rates and that the approach identifies unseen abnormalities with a high rate of accuracy. The feature selection tool F-score is used to identify differences between the abnormal and normal datasets. It identifies the heights where the discrimination between the two sets is largest and the aircraft parameters most responsible for these variations. The method presented adds much value to the existing event based approach.

AB - A two phase novelty detection approach to locating abnormalities in the descent phase of aircraft flight data is presented. It has the ability to model normal time series data by analysing snapshots at chosen heights in the descent, weight individual abnormalities and quantitatively assess the overall level of abnormality of a flight during the descent to a given runway. The method models normal approaches to a given runway (as determined by the airline 19s Standard Operating Procedures) and detects and ranks deviations from that model. The approach expands on a recommendation by the UK Air Accident Investigation Branch to the UK Civil Aviation Authority. The first phase quantifies abnormalities at certain heights in a flight. The second phase ranks all flights to identify the most abnormal; each phase using a one class classifier. For both the first and second phases, the Support Vector Machine (SVM), the Mixture of Gaussians and the K-means one class classifiers are compared. The method is tested using a dataset containing manually labelled abnormal flights. The results show that the SVM provides the best detection rates and that the approach identifies unseen abnormalities with a high rate of accuracy. The feature selection tool F-score is used to identify differences between the abnormal and normal datasets. It identifies the heights where the discrimination between the two sets is largest and the aircraft parameters most responsible for these variations. The method presented adds much value to the existing event based approach.

KW - aircraft landing guidance

KW - artificial intelligence

KW - fault diagnosis

KW - support vector machines

U2 - 10.1109/TITS.2012.2188391

DO - 10.1109/TITS.2012.2188391

M3 - Article

VL - 13

SP - 1253

EP - 1265

JO - IEEE Transactions on Intelligent Transportation Systems

JF - IEEE Transactions on Intelligent Transportation Systems

SN - 1524-9050

IS - 3

ER -

ID: 168861