Multiclass Anomaly Detection in Flight Data Using Semi-Supervised Explainable Deep Learning Model
- 1 February 2022
- journal article
- research article
- Published by American Institute of Aeronautics and Astronautics (AIAA) in Journal of Aerospace Information Systems
- Vol. 19 (2), 83-97
- https://doi.org/10.2514/1.i010959
Abstract
The identification of precursors to safety incidents in aviation data is a crucial task, yet extremely challenging. The main approach in practice leverages domain expertise to define expected tolerances in system behavior and flags exceedances from such safety margins. However, this approach is incapable of identifying unknown risks and vulnerabilities. Various machine-learning approaches have been investigated and deployed to identify anomalies, with the great challenge of procuring enough labeled data to achieve reliable and accurate performance. This paper presents an explainable deep semi-supervised model for anomaly detection in aviation, building upon recent advancements described in the machine-learning literature. The proposed model combines feature engineering and classification in feature space, while leveraging all available data (labeled and unlabeled). Our approach is validated with case studies of anomaly detection during the takeoff and landing phases of commercial aircraft. Our model outperforms the state-of-the-art supervised anomaly-detection model, reaching significantly higher accuracy and fewer false alarms, even if only small proportion of data in the training set is labeled.Keywords
Funding Information
- Ames Research Center (80ARC020D0010, NNA16BD14C)
This publication has 10 references indexed in Scilit:
- Anomaly Detection and Cause Analysis During Landing Approach Using Recurrent Neural NetworkJournal of Aerospace Information Systems, 2021
- Unsupervised Anomaly Detection in Flight Data Using Convolutional Variational Auto-EncoderAerospace, 2020
- Critical Parameter Identification for Safety Events in Commercial Aviation Using Machine LearningAerospace, 2020
- Real-time anomaly detection framework using a support vector regression for the safety monitoring of commercial aircraftAdvanced Engineering Informatics, 2020
- Explaining Aviation Safety Incidents Using Deep Temporal Multiple Instance LearningPublished by Association for Computing Machinery (ACM) ,2018
- Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic ThresholdingPublished by Association for Computing Machinery (ACM) ,2018
- Vector Autoregressive Model-Based Anomaly Detection in Aviation SystemsJournal of Aerospace Information Systems, 2016
- Analysis of Flight Data Using Clustering Techniques for Detecting Abnormal OperationsJournal of Aerospace Information Systems, 2015
- Anomaly Detection and Diagnosis Algorithms for Discrete Symbol Sequences with Applications to Airline SafetyIEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 2008
- Semi-Supervised LearningPublished by MIT Press ,2006