Efficient Active Fault Diagnosis Using Adaptive Particle Filter

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F17%3A43932701" target="_blank" >RIV/49777513:23520/17:43932701 - isvavai.cz</a>
Result on the web
<a href="https://dx.doi.org/10.1109/CDC.2017.8264525" target="_blank" >https://dx.doi.org/10.1109/CDC.2017.8264525</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/CDC.2017.8264525" target="_blank" >10.1109/CDC.2017.8264525</a>

Result language
angličtina
Original language name
Efficient Active Fault Diagnosis Using Adaptive Particle Filter
Original language description
This paper presents a solution to a multiplemodel based stochastic active fault diagnosis problem over the infinite-time horizon. A general additive detection cost criterion is considered to reflect the objectives. Since the system state is unknown, the design consists of a perfect state information reformulation and optimization problem solution by approximate dynamic programming. An adaptive particle filter state estimation algorithm based on the efficient sample size is proposed to maintain the estimate quality while reducing computational costs. A reduction of information statistics of the state is carried out using non-resampled particles to make the solution feasible. Simulation results illustrate the effectiveness of the proposed design.
Czech name
—
Czech description
—

Project
<a href="/en/project/GA15-12068S" target="_blank" >GA15-12068S: Adaptive Approaches to State Estimation of Nonlinear Stochastic Systems</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 56th IEEE Conference on Decision and Control
ISBN
978-1-5090-2873-3
ISSN
0743-1546
e-ISSN
—
Number of pages
7
Pages from-to
5732-5738
Publisher name
IEEE
Place of publication
Melbourne
Event location
Melbourne, Austrálie
Event date
Dec 12, 2017
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000424696905083

Similar results(10)