UAV actuator fault detection through artificial intelligent technique
The design of Fault Detection and Diagnosis (FDD) is a tedious and challenging task. It is due to the changes and uncertainties associated with the aircraft dynamics following an occurrence of a fault. It was believed that until recently, the control reallocation following a system fault was too com...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
2018
|
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uniten.dspace-10515 |
---|---|
record_format |
dspace |
spelling |
my.uniten.dspace-105152019-01-16T03:33:04Z UAV actuator fault detection through artificial intelligent technique Sahwee, Z. Mahmood, A.S. Rahman, N.A. Sahari, K.S.M. The design of Fault Detection and Diagnosis (FDD) is a tedious and challenging task. It is due to the changes and uncertainties associated with the aircraft dynamics following an occurrence of a fault. It was believed that until recently, the control reallocation following a system fault was too complex and computationally intensive for real world flight control cases. However, the recent, a dramatic improvement in computer speed and the development of more efficient algorithms have changed the situation considerably. This paper presents an artificial intelligent, in specific using Fuzzy Inference System method to detect an actuator fault. Three ground simulations were performed to validate the performances of the fault detection technique proposed. The residuals were evaluated by using three membership functions of the Fuzzy Inference System. The results show that the proposed technique was able to detect the actuator fault. © 2018 Faculty of Mechanical Engineering, Universiti Teknologi MARA (UiTM), Malaysia. 2018-11-07T08:11:27Z 2018-11-07T08:11:27Z 2018 Article en Journal of Mechanical Engineering Volume 5, Issue Specialissue6, 2018, Pages 141-154 |
institution |
Universiti Tenaga Nasional |
building |
UNITEN Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Tenaga Nasional |
content_source |
UNITEN Institutional Repository |
url_provider |
http://dspace.uniten.edu.my/ |
language |
English |
description |
The design of Fault Detection and Diagnosis (FDD) is a tedious and challenging task. It is due to the changes and uncertainties associated with the aircraft dynamics following an occurrence of a fault. It was believed that until recently, the control reallocation following a system fault was too complex and computationally intensive for real world flight control cases. However, the recent, a dramatic improvement in computer speed and the development of more efficient algorithms have changed the situation considerably. This paper presents an artificial intelligent, in specific using Fuzzy Inference System method to detect an actuator fault. Three ground simulations were performed to validate the performances of the fault detection technique proposed. The residuals were evaluated by using three membership functions of the Fuzzy Inference System. The results show that the proposed technique was able to detect the actuator fault. © 2018 Faculty of Mechanical Engineering, Universiti Teknologi MARA (UiTM), Malaysia. |
format |
Article |
author |
Sahwee, Z. Mahmood, A.S. Rahman, N.A. Sahari, K.S.M. |
spellingShingle |
Sahwee, Z. Mahmood, A.S. Rahman, N.A. Sahari, K.S.M. UAV actuator fault detection through artificial intelligent technique |
author_facet |
Sahwee, Z. Mahmood, A.S. Rahman, N.A. Sahari, K.S.M. |
author_sort |
Sahwee, Z. |
title |
UAV actuator fault detection through artificial intelligent technique |
title_short |
UAV actuator fault detection through artificial intelligent technique |
title_full |
UAV actuator fault detection through artificial intelligent technique |
title_fullStr |
UAV actuator fault detection through artificial intelligent technique |
title_full_unstemmed |
UAV actuator fault detection through artificial intelligent technique |
title_sort |
uav actuator fault detection through artificial intelligent technique |
publishDate |
2018 |
_version_ |
1644494992514744320 |
score |
13.160551 |