Hybrid data-driven anomaly detection method to improve UAV operating reliability
- 1 July 2017
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2017 Prognostics and System Health Management Conference (PHM-Harbin)
Abstract
The paper presents a hybrid data-driven approach of anomaly detection for UAV (Unmanned Aerial Vehicle) system. Specifically, it is focused on implementing on-line abnormal discovery to improve the operating reliability of UAV. The anomaly detection framework is based on time series segmentation, associated rules mining and associated anomaly detection. Experimental results through simulation and actual flight data, demonstrate that anomaly detection and identification with the monitoring sensor data can be conducted for UAV system.Keywords
This publication has 6 references indexed in Scilit:
- Multi-mode separation and nonlinear feature extraction of hybrid gear failures in coal cutters using adaptive nonstationary vibration analysisNonlinear Dynamics, 2015
- An anomaly detection approach for multiple monitoring data series based on latent correlation probabilistic modelApplied Intelligence, 2015
- Anomaly detection for satellite power subsystem with associated rules based on Kernel Principal Component AnalysisMicroelectronics Reliability, 2015
- Aircraft Sensor Health Monitoring Based on Transmissibility OperatorsJournal of Guidance, Control, and Dynamics, 2015
- Discovery of Temporal Associations in Multivariate Time SeriesIEEE Transactions on Knowledge and Data Engineering, 2014
- Semisupervised One-Class Support Vector Machines for Classification of Remote Sensing DataIEEE Transactions on Geoscience and Remote Sensing, 2010