Title:	Policy search for active fault diagnosis with partially observable state
Authors:	Král, Ladislav Punčochář, Ivo
Citation:	KRÁL, L. PUNČOCHÁŘ, I. Policy search for active fault diagnosis with partially observable state. International Journal of Adaptive Control and Signal Processing, 2022, roč. 36, č. 9, s. 2190-2216. ISSN: 0890-6327
Issue Date:	2022
Publisher:	Wiley
Document type:	článek article
URI:	2-s2.0-85131886551 http://hdl.handle.net/11025/50799
ISSN:	0890-6327
Keywords in different language:	approximate dynamic programming;fault detection;neural networks;reinforcement learning;state estimation
Abstract in different language:	The article deals with a novel design of an active fault detector (AFD) for a nonlinear stochastic system with a partially observable state. The imperfect state information problem is converted to a perfect state information problem using a state estimator. Subsequently, the problem is decomposed into separate tasks of an optimal fault detector design and an approximate input generator design using a dynamic programming technique. While the former task is straightforward, the latter represents a nonlinear functional optimization problem. The input generator is approximated by a multi-layer perceptron neural network, and its unknown parameters are found using the policy search method. Effectiveness of the proposed AFD design is demonstrated numerically on a pendulum system and a heating/cooling system.
Rights:	Plný text je přístupný v rámci univerzity přihlášeným uživatelům. © Wiley
Appears in Collections:	Články / Articles (NTIS) OBD

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