Fault detection and diagnosis of permanent-magnet DC motor based onparameter estimation and neural network
Xiang-Qun Liu
Hong-Yue Zhang
Jun Liu
Jing Yang
Dept. of Autom. Control, Beijing Univ. of Aeronaut. & Astronaut.;
This paper appears in: Industrial Electronics, IEEE Transactions on
Publication Date: Oct 2000
Volume: 47,
Issue: 5
On page(s): 1021-1030
ISSN: 0278-0046
References Cited: 15
CODEN: ITIED6
INSPEC Accession Number: 6729431
Digital Object Identifier: 10.1109/41.873210
Current Version Published: 2002-08-06
Abstract
In this paper, fault detection and diagnosis of a permanent-magnet
DC motor is discussed. Parameter estimation based on block-pulse
function series is used to estimate the continuous-time model of the
motor. The electromechanical parameters of the motor can be obtained
from the estimated model parameters. The relative changes of
electromechanical parameters are used to detect motor faults. A
multilayer perceptron neural network is used to isolate faults based on
the patterns of parameter changes. Experiments with a real motor
validate the feasibility of the combined use of parameter estimation and
neural network classification for fault detection and isolation of the
motor
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
