Fault classification and diagnostic system for UAV electrical networks based on hidden Markov models

Research output: Contribution to journalArticle

2 Citations (Scopus)
197 Downloads (Pure)

Abstract

In recent years there has been an increase in the number of unmanned aerial vehicle (UAV) applications intended for various missions in a variety of environments. The adoption of the more-electric aircraft (MEA) has led to a greater emphasis on electrical power systems (EPS) for safe flight through an increased number of critical loads being sourced with electrical power. Despite extensive literature detailing the development of systems to detect UAV failures and enhance overall system reliability, few have focussed directly on the increasingly complex and dynamic EPS. This paper outlines the development of a novel UAV EPS fault classification and diagnostic (FCD) system based on hidden Markov models (HMM) that will assist and improve EPS health management and control. The ability of the proposed FCD system to autonomously detect, classify and diagnose the severity of diverse EPS faults is validated with development of the system for NASA’s Advanced Diagnostic and Prognostic Testbed (ADAPT), a representative UAV EPS system. EPS data from the ADAPT network was used to develop the FCD system and results described within this paper show that a high classification and diagnostic accuracy can be achieved using the proposed system.
Original languageEnglish
Pages (from-to)103-111
Number of pages9
JournalIET Electrical Systems in Transportation
Volume5
Issue number3
Early online date8 Jan 2015
DOIs
Publication statusPublished - 7 Sep 2015

Fingerprint

Hidden Markov models
Unmanned aerial vehicles (UAV)
Testbeds
NASA
Aircraft
Health

Keywords

  • fault detection
  • fault location
  • uav power system
  • machine learning

Cite this

@article{1466c6c4770c4d45a029b5967bde2d9b,
title = "Fault classification and diagnostic system for UAV electrical networks based on hidden Markov models",
abstract = "In recent years there has been an increase in the number of unmanned aerial vehicle (UAV) applications intended for various missions in a variety of environments. The adoption of the more-electric aircraft (MEA) has led to a greater emphasis on electrical power systems (EPS) for safe flight through an increased number of critical loads being sourced with electrical power. Despite extensive literature detailing the development of systems to detect UAV failures and enhance overall system reliability, few have focussed directly on the increasingly complex and dynamic EPS. This paper outlines the development of a novel UAV EPS fault classification and diagnostic (FCD) system based on hidden Markov models (HMM) that will assist and improve EPS health management and control. The ability of the proposed FCD system to autonomously detect, classify and diagnose the severity of diverse EPS faults is validated with development of the system for NASA’s Advanced Diagnostic and Prognostic Testbed (ADAPT), a representative UAV EPS system. EPS data from the ADAPT network was used to develop the FCD system and results described within this paper show that a high classification and diagnostic accuracy can be achieved using the proposed system.",
keywords = "fault detection, fault location, uav power system, machine learning",
author = "Rory Telford and Stuart Galloway",
year = "2015",
month = "9",
day = "7",
doi = "10.1049/iet-est.2014.0042",
language = "English",
volume = "5",
pages = "103--111",
journal = "IET Electrical Systems in Transportation",
issn = "2042-9738",
number = "3",

}

TY - JOUR

T1 - Fault classification and diagnostic system for UAV electrical networks based on hidden Markov models

AU - Telford, Rory

AU - Galloway, Stuart

PY - 2015/9/7

Y1 - 2015/9/7

N2 - In recent years there has been an increase in the number of unmanned aerial vehicle (UAV) applications intended for various missions in a variety of environments. The adoption of the more-electric aircraft (MEA) has led to a greater emphasis on electrical power systems (EPS) for safe flight through an increased number of critical loads being sourced with electrical power. Despite extensive literature detailing the development of systems to detect UAV failures and enhance overall system reliability, few have focussed directly on the increasingly complex and dynamic EPS. This paper outlines the development of a novel UAV EPS fault classification and diagnostic (FCD) system based on hidden Markov models (HMM) that will assist and improve EPS health management and control. The ability of the proposed FCD system to autonomously detect, classify and diagnose the severity of diverse EPS faults is validated with development of the system for NASA’s Advanced Diagnostic and Prognostic Testbed (ADAPT), a representative UAV EPS system. EPS data from the ADAPT network was used to develop the FCD system and results described within this paper show that a high classification and diagnostic accuracy can be achieved using the proposed system.

AB - In recent years there has been an increase in the number of unmanned aerial vehicle (UAV) applications intended for various missions in a variety of environments. The adoption of the more-electric aircraft (MEA) has led to a greater emphasis on electrical power systems (EPS) for safe flight through an increased number of critical loads being sourced with electrical power. Despite extensive literature detailing the development of systems to detect UAV failures and enhance overall system reliability, few have focussed directly on the increasingly complex and dynamic EPS. This paper outlines the development of a novel UAV EPS fault classification and diagnostic (FCD) system based on hidden Markov models (HMM) that will assist and improve EPS health management and control. The ability of the proposed FCD system to autonomously detect, classify and diagnose the severity of diverse EPS faults is validated with development of the system for NASA’s Advanced Diagnostic and Prognostic Testbed (ADAPT), a representative UAV EPS system. EPS data from the ADAPT network was used to develop the FCD system and results described within this paper show that a high classification and diagnostic accuracy can be achieved using the proposed system.

KW - fault detection

KW - fault location

KW - uav power system

KW - machine learning

UR - http://digital-library.theiet.org/content/journals/iet-est

U2 - 10.1049/iet-est.2014.0042

DO - 10.1049/iet-est.2014.0042

M3 - Article

VL - 5

SP - 103

EP - 111

JO - IET Electrical Systems in Transportation

JF - IET Electrical Systems in Transportation

SN - 2042-9738

IS - 3

ER -