Operational anomaly detection in flight data using a multivariate Gaussian mixture model

Guoyi Li, Ashwin Rai, Hyunseong Lee, Aditi Chattopadhyay

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents a robust real-time aircraft health monitoring framework using a machine learning based approach, specifically the multivariate Gaussian mixture model (mGMM), for the detection of in-air operational anomalies of an aircraft system. Sensor fusion and noise filtering algorithms have also been adopted to reduce dimensionality of the feature space while avoiding the elimination of useful information from the original flight data. Random noise in each feature, induced by the aircraft sensors and data acquisition system, is filtered out using a weighted averaging window while maintaining inherent variances. The filtered dataset is then fused according to the underlying physics of each sensed feature to reduce redundant features and subsequently trained using the mGMM. The methodology allows monitoring the behavior of each feature as well as correlations between features, significantly improving detection sensitivity. The high computational efficiency of this approach permits real-time monitoring of an aircraft system.

Original languageEnglish (US)
Title of host publicationPHM 2018 - 10th Annual Conference of the Prognostics and Health Management Society
EditorsMarcos Orchard, Anibal Bregon
PublisherPrognostics and Health Management Society
ISBN (Electronic)9781936263059
StatePublished - Aug 24 2018
Event10th Annual Conference of the Prognostics and Health Management Society, PHM 2018 - Philadelphia, United States
Duration: Sep 24 2018Sep 27 2018

Publication series

NameProceedings of the Annual Conference of the Prognostics and Health Management Society, PHM
ISSN (Print)2325-0178

Conference

Conference10th Annual Conference of the Prognostics and Health Management Society, PHM 2018
CountryUnited States
CityPhiladelphia
Period9/24/189/27/18

Fingerprint

Aircraft
Monitoring
Physics
Sensors
Computational efficiency
Information Systems
Learning systems
Noise
Data acquisition
Fusion reactions
Air
Health

ASJC Scopus subject areas

  • Information Systems
  • Electrical and Electronic Engineering
  • Health Information Management
  • Computer Science Applications

Cite this

Li, G., Rai, A., Lee, H., & Chattopadhyay, A. (2018). Operational anomaly detection in flight data using a multivariate Gaussian mixture model. In M. Orchard, & A. Bregon (Eds.), PHM 2018 - 10th Annual Conference of the Prognostics and Health Management Society (Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM). Prognostics and Health Management Society.

Operational anomaly detection in flight data using a multivariate Gaussian mixture model. / Li, Guoyi; Rai, Ashwin; Lee, Hyunseong; Chattopadhyay, Aditi.

PHM 2018 - 10th Annual Conference of the Prognostics and Health Management Society. ed. / Marcos Orchard; Anibal Bregon. Prognostics and Health Management Society, 2018. (Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, G, Rai, A, Lee, H & Chattopadhyay, A 2018, Operational anomaly detection in flight data using a multivariate Gaussian mixture model. in M Orchard & A Bregon (eds), PHM 2018 - 10th Annual Conference of the Prognostics and Health Management Society. Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM, Prognostics and Health Management Society, 10th Annual Conference of the Prognostics and Health Management Society, PHM 2018, Philadelphia, United States, 9/24/18.
Li G, Rai A, Lee H, Chattopadhyay A. Operational anomaly detection in flight data using a multivariate Gaussian mixture model. In Orchard M, Bregon A, editors, PHM 2018 - 10th Annual Conference of the Prognostics and Health Management Society. Prognostics and Health Management Society. 2018. (Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM).
Li, Guoyi ; Rai, Ashwin ; Lee, Hyunseong ; Chattopadhyay, Aditi. / Operational anomaly detection in flight data using a multivariate Gaussian mixture model. PHM 2018 - 10th Annual Conference of the Prognostics and Health Management Society. editor / Marcos Orchard ; Anibal Bregon. Prognostics and Health Management Society, 2018. (Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM).
@inproceedings{4fbad4c4e6d04b6ba1d85b3a2aecf5d7,
title = "Operational anomaly detection in flight data using a multivariate Gaussian mixture model",
abstract = "This paper presents a robust real-time aircraft health monitoring framework using a machine learning based approach, specifically the multivariate Gaussian mixture model (mGMM), for the detection of in-air operational anomalies of an aircraft system. Sensor fusion and noise filtering algorithms have also been adopted to reduce dimensionality of the feature space while avoiding the elimination of useful information from the original flight data. Random noise in each feature, induced by the aircraft sensors and data acquisition system, is filtered out using a weighted averaging window while maintaining inherent variances. The filtered dataset is then fused according to the underlying physics of each sensed feature to reduce redundant features and subsequently trained using the mGMM. The methodology allows monitoring the behavior of each feature as well as correlations between features, significantly improving detection sensitivity. The high computational efficiency of this approach permits real-time monitoring of an aircraft system.",
author = "Guoyi Li and Ashwin Rai and Hyunseong Lee and Aditi Chattopadhyay",
year = "2018",
month = "8",
day = "24",
language = "English (US)",
series = "Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM",
publisher = "Prognostics and Health Management Society",
editor = "Marcos Orchard and Anibal Bregon",
booktitle = "PHM 2018 - 10th Annual Conference of the Prognostics and Health Management Society",

}

TY - GEN

T1 - Operational anomaly detection in flight data using a multivariate Gaussian mixture model

AU - Li, Guoyi

AU - Rai, Ashwin

AU - Lee, Hyunseong

AU - Chattopadhyay, Aditi

PY - 2018/8/24

Y1 - 2018/8/24

N2 - This paper presents a robust real-time aircraft health monitoring framework using a machine learning based approach, specifically the multivariate Gaussian mixture model (mGMM), for the detection of in-air operational anomalies of an aircraft system. Sensor fusion and noise filtering algorithms have also been adopted to reduce dimensionality of the feature space while avoiding the elimination of useful information from the original flight data. Random noise in each feature, induced by the aircraft sensors and data acquisition system, is filtered out using a weighted averaging window while maintaining inherent variances. The filtered dataset is then fused according to the underlying physics of each sensed feature to reduce redundant features and subsequently trained using the mGMM. The methodology allows monitoring the behavior of each feature as well as correlations between features, significantly improving detection sensitivity. The high computational efficiency of this approach permits real-time monitoring of an aircraft system.

AB - This paper presents a robust real-time aircraft health monitoring framework using a machine learning based approach, specifically the multivariate Gaussian mixture model (mGMM), for the detection of in-air operational anomalies of an aircraft system. Sensor fusion and noise filtering algorithms have also been adopted to reduce dimensionality of the feature space while avoiding the elimination of useful information from the original flight data. Random noise in each feature, induced by the aircraft sensors and data acquisition system, is filtered out using a weighted averaging window while maintaining inherent variances. The filtered dataset is then fused according to the underlying physics of each sensed feature to reduce redundant features and subsequently trained using the mGMM. The methodology allows monitoring the behavior of each feature as well as correlations between features, significantly improving detection sensitivity. The high computational efficiency of this approach permits real-time monitoring of an aircraft system.

UR - http://www.scopus.com/inward/record.url?scp=85069697193&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069697193&partnerID=8YFLogxK

M3 - Conference contribution

T3 - Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM

BT - PHM 2018 - 10th Annual Conference of the Prognostics and Health Management Society

A2 - Orchard, Marcos

A2 - Bregon, Anibal

PB - Prognostics and Health Management Society

ER -