Special Issue Article
Advances in Mechanical Engineering
2017, Vol. 9(6) 1–10
Ó The Author(s) 2017
DOI: 10.1177/1687814017705068
journals.sagepub.com/home/ade
Extreme learning machine based
actuator fault detection of a quadrotor
helicopter
Chen Li, Yu Zhang and Ping Li
Abstract
Actuator fault might occur during quadrotor helicopter’s flight. It is a demand to detect actuator fault in real-time. An
actuator fault detection method based on extreme learning machine is proposed. An extreme learning machine network
is used to approximate the dynamic of the actuator, which is trained by the actuator’s inputs, outputs, and states. The
dynamic of the actuator is mapped to the output matrix of the proposed extreme learning machine network. By moni-
toring the norm of the output matrix, the dynamic of the actuator is supervised, and system fault can be detected. The
proposed extreme learning machine network is tested on a self-made experimental propeller system platform, and
results show that the method is sensitive and effective on both major and minor fault circumstances.
Keywords
Extreme learning machine, quadrotor, helicopter, actuator, fault detection
Date received: 15 January 2017; accepted: 22 March 2017
Academic Editor: Chenguang Yang
Introduction
Quadrotor helicopter is becoming more popular in
recent years. It has simple mechanical structures and
intuitive principles, and is convenient in use. With capa-
bility of hovering and vertical take-off and landing,
1
quadrotor helicopter receives considerable success in
areas of agricultural plant protection, aerial photogra-
phy, logistics, surveillance, and monitoring.
Along with the productization and commercializa-
tion of quadrotor helicopters, the importance of system
reliability is increasingly prominent. Electronic quadro-
tor helicopter is usually driven by a propeller system
based on brushless direct current (BLDC) motors.
Reliability of a quadrotor system largely depends on
the propeller system, for it is the only actuator of the
whole helicopter. The actuator is usually working
under rigorous conditions such as vibration, dusts, tem-
perature, salt mist, which significantly increase the
probability of actuator fault. Real-time actuator fault
detection is required. With the help of on-line actuator
fault detection, the quadrotor helicopter may be sur-
vived by fault-tolerant control under actuator fault
circumstance.
Researchers and engineers have made great achieve-
ments on actuators and sensors fault diagnosis of
Unmanned Aerial Vehicles (UAVs). A two-stage
Kalman filter is used by Moghadam and Caliskan
2
to
diagnose sensor and actuator fault. A t observer is pro-
posed by Freddi et al.
3
to estimate actuator state, and
actuator fault is further detected and isolated. Cen
et al.
4
use nonlinear state observer to diagnose the fault
of a propeller system. Yan et al.
5
diagnose a quadrotor
State Key Laboratory of Industrial Control Technology, College of
Control Science and Engineering, Zhejiang University, Hangzhou, China
Corresponding author:
Yu Zhang, State Key Laboratory of Industrial Control Technology, College
of Control Science and Engineering, Zhejiang University, Hangzhou
310027, China.
Email: zhangyu80@zju.edu.cn
Creative Commons CC-BY: This article is distributed under the terms of the Creative Commons Attribution 4.0 License
(http://www.creativecommons.org/licenses/by/4.0/) which permits any use, reproduction and distribution of the work without
further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/en-us/nam/
open-access-at-sage).
