Loading…
An embedded intelligent system for on-line anomaly detection of unmanned aerial vehicle
On-line anomaly detection is critical for the safety of unmanned aerial vehicles (UAVs). However, the flight status assessment still depends on ground control stations, which cannot meet the time requirement for autonomous and safe flight. The lack of on-board intelligent anomaly detection systems m...
Saved in:
Published in: | Journal of intelligent & fuzzy systems 2018-01, Vol.34 (6), p.3535-3545 |
---|---|
Main Authors: | , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | On-line anomaly detection is critical for the safety of unmanned aerial vehicles (UAVs). However, the flight status assessment still depends on ground control stations, which cannot meet the time requirement for autonomous and safe flight. The lack of on-board intelligent anomaly detection systems makes it rather difficult for on-line flight status estimation and assessment. In order to achieve real-time monitoring of UAV flight status and enhance the reliability and safety of UAVs, an embedded intelligent system is designed to address the challenging issues of UAV on-line anomaly detection in this paper. During the flight, the status of sensors and key components are continuously detected via flight data which can reflect the current status of the UAV. The proposed embedded anomaly detection system includes two main parts: (1) a general heterogeneous computing architecture which is based on Xilinx Zynq-7000 SoC with dual-core Cortex A9 processors and Field Programmable Gate Arrays (FPGA), (2) an on-line anomaly detection intelligent algorithm which is based on least squares support vector machine (LS-SVM) prediction model and utilized as a demonstration that needs high computing performance. The simulation flight data are used to verify the proposed system, and the experimental results show that the proposed intelligent system is capable of effective UAV on-line anomaly detection. |
---|---|
ISSN: | 1064-1246 1875-8967 |
DOI: | 10.3233/JIFS-169532 |