Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.14279/8470
Title: AI-based actuator/sensor fault detection with low computational cost for industrial applications
Authors: Michail, Konstantinos 
Deliparaschos, Kyriakos M. 
Tzafestas, Spyros G. 
Zolotas, Argyrios C. 
metadata.dc.contributor.other: Δεληπαράσχος, Κυριάκος
Μιχαήλ, Κωνσταντίνος
Major Field of Science: Engineering and Technology
Field Category: Electrical Engineering - Electronic Engineering - Information Engineering
Keywords: Actuator/sensor fault detection (FD);Artificial intelligence (AI);Electromagnetic suspension (EMS);Fault tolerant control (FTC);Loop-shaping robust control design;Maglev trains;Neural networks (NNs);Reconfigurable control
Issue Date: Jan-2016
Source: IEEE Transactions on Control Systems Technology, 2016, vol. 24, nο 1, pp. 293-301
Volume: 24
Issue: 1
Start page: 293
End page: 301
Journal: IEEE Transactions on Control Systems Technology 
Abstract: A low computational cost method is proposed for detecting actuator/sensor faults. Typical model-based fault detection (FD) units for multiple sensor faults require a bank of estimators [i.e., conventional Kalman estimators or artificial intelligence (AI)-based ones]. The proposed FD scheme uses an AI approach for developing of a low computational power FD unit abbreviated as iFD. In contrast to the bank-of-estimators approach, the proposed iFD unit employs a single estimator for multiple actuator/sensor FD. The efficacy of the proposed FD scheme is illustrated through a rigorous analysis of the results for a number of sensor fault scenarios on an electromagnetic suspension system.
URI: https://hdl.handle.net/20.500.14279/8470
ISSN: 15580865
DOI: 10.1109/TCST.2015.2422794
Rights: © IEEE
Type: Article
Affiliation : Cyprus University of Technology 
SignalGeneriX Ltd 
University of Dublin 
National Technical University Of Athens 
University of Lincoln 
Publication Type: Peer Reviewed
Appears in Collections:Άρθρα/Articles

CORE Recommender
Show full item record

SCOPUSTM   
Citations

36
checked on Nov 9, 2023

WEB OF SCIENCETM
Citations 20

26
Last Week
0
Last month
0
checked on Oct 29, 2023

Page view(s)

432
Last Week
0
Last month
5
checked on Nov 21, 2024

Google ScholarTM

Check

Altmetric


Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.