Mode estimation of probabilistic hybrid systems

DOI10.1007/3-540-45873-5_21MaRDI QIDQ4736589zbMATH OpenFDO

Authors Michael Hofbaur, Brian C. Williams

Publication date 9 August 2004

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL http://link.springer.de/link/service/series/0558/bibs/2289/22890253.htm

zbMATH Keywords

concurrent probabilistic hybrid automatafailureshidden Markov modelsmode estimationprobabilistic hybrid systems

Mathematics Subject Classification ID

Algebraic methods (93B25) Control/observation systems governed by functional relations other than differential equations (such as hybrid and switching systems) (93C30) Discrete event control/observation systems (93C65) Stochastic systems in control theory (general) (93E03) Estimation and detection in stochastic control theory (93E10)

Review text

Traditional methods for separately estimating discrete and continuous behaviour are extended to hybrid systems. The core problem is to estimate the mode of the system with failures due to state disturbances and measurement noise. A modeling formalism is introduced, called concurrent Probabilistic Hybrid Automata (cPHA), that merges hidden Markov models with continuous dynamical system models. A cPHA provides a modeling framework that captures probabilistic mode transitions. This is unlike most traditional approaches which define mode transitions to be deterministic or do not specify probabilities for transitions. Next, a hybrid mode observer is introduced. The observer uses the results of continuous state estimates to estimate a system's mode changes, and coordinates the actions of a set of continuous state observers. In addition a novel any-time, any-space algorithm is provided for computing approximate hybrid estimates. An illustrative example is considered. For the entire collection see [Zbl 0989.00055].

Recommendations

• Hybrid estimation of complex systems.
• Mode set focused hybrid estimation
• Modal estimation in hybrid systems
• Hybrid Estimation for Stochastic Piecewise Linear Systems
• Hybrid estimation algorithms. II

Cited in

(11)

• Modal estimation in hybrid systems
• Spectral Bayesian estimation for general stochastic hybrid systems
• Robust state estimation and fault diagnosis for uncertain hybrid nonlinear systems
• Predicting a hybrid system
• Hybrid estimation of complex systems.
• Mode set focused hybrid estimation
• scientific article; zbMATH DE number 7318980 (Why is no real title available?)
• Model-based diagnosis with probabilistic models
• Hybrid Systems: Computation and Control
• Extended hybrid timed Petri nets with semi-supervised anomaly detection for switched systems, modelling and fault detection
• Robust state estimation and fault diagnosis for uncertain hybrid systems

This page was built for publication: Mode estimation of probabilistic hybrid systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4736589)