Sigma2 project
Signals, models and algorithms
Group head : François LeGland
Foreword :
The Sigma2 project is now terminated, and three offspring projects
or future projects have been recently created (listed below by
alphabetical order)
- ASPI,
on Monte Carlo methods with interaction, and applications to tracking
and to risk evaluation,
- DistribCom,
on distributed iterative algorithms, self-modeling
and signal processing for telecommunications,
- Sisthem,
on statistical inference for structure health monitoring,
and applications to aeronautics and civil engineering.
[
Presentation |
Members |
Publications |
Software]
The objectives of the Sigma2 project are the design, analysis,
and implementation of statistical model-based algorithms,
for identification, monitoring and diagnosis of complex
industrial systems.
The models considered are on one hand the stochastic state-space models
of automatic control, with increasing emphasis on nonlinear models,
and on the other hand some partially stochastic models
(HMM, Petri nets, nets of automata, etc.)
on discrete structures (trees, graphs, etc.),
e.g. to model distributed discrete events systems.
The major methodological contributions of the project, which make
the scientific background for the current research activities,
consist of the use of the local asymptotic approach for monitoring
and diagnosis of continuous systems,
the design of particle filters for the statistical inference
of HMM,
and the design of distributed Viterbi-like state reconstruction
algorithms, for monitoring and diagnosis of distributed discrete
events systems.
The main applications considered are
monitoring and diagnosis of vibrating mechanical structures
(automobile, aerospace, civil engineering),
monitoring and diagnosis of automobile subsystems,
and fault diagnosis in telecommunications networks.
Sigma2 is a joint
INRIA /
CNRS project.
Research themes
- observers and filters for monitoring and diagnosis of nonlinear
dynamical systems,
- subspace methods for modal analysis and monitoring,
- statistics of HMM with general state space,
and associated particle methods
[ERCIM News
article,
Jan 00],
- monitoring and diagnosis of distributed discrete events systems,
- approximate state estimation algorithms in graphical models
and Bayesian networks, and application to turbo algorithms.
For more information, see the 2003
activity report.
Signal-Image seminar,
ASPI working group [in French].
Industrial and academic relations
- industrial projects :
with Renault on
identification of the dynamical behaviour of road vehicle,
and on
monitoring and diagnosis of automobile subsystems,
with Alcatel on
transparent BER estimation in optical network,
- multi-partner projects :
at national level on
fault diagnosis in
telecommunications networks (Magda2 / RNRT),
and at european level on
model-based structural monitoring using
in-operation system identification (Sinopsys / Eurêka),
on
exploitation of flight test data under natural
excitation conditions (Flite / Eurêka),
on
structural assessment, monitoring
and control (Samco / Growth),
on
distributed
control and stochastic analysis of hybrid systems
(Hybridge / IST),
- academic research networks :
at national level on
hidden Markov chains and particle filtering
(MathSTIC),
on
particle methods
(AS-STIC),
on
monitoring of mechanical structures
(ACI Sécurité),
and at european level on
system
identification (Ernsi / TMR),
on
statistical methods
for dynamical stochastic models (Dynstoch / IHP).
