Abstract

This article addresses maximum-a-posteriori (MAP) estimation of linear time-invariant state-space (LTI-SS) models. The joint posterior distribution of the model matrices and the unknown state sequence is approximated by using Rao-Blackwellized Monte-Carlo sampling algorithms. Specifically, the conditional distribution of the state sequence given the model parameters is derived analytically, while only the marginal posterior distribution of the model matrices is approximated using a Metropolis-Hastings Markov Chain Monte-Carlo sampler. From the joint distribution, MAP estimates of the unknown model matrices as well as the state sequence are computed. The performance of the proposed algorithm is demonstrated on a numerical example and on a real laboratory benchmark dataset of a hair dryer process.

References

1.
Ho
,
B.
, and
Kalman
,
R. E.
,
1965
, “
Effective Construction of Linear State-Variable Models From Input/Output Data
,”
Proceedings of 3rd Annual Allerton Conference on Circuit and System Theory
,
Monticello, IL
,
Oct.
, pp.
449
459
.
2.
Verhaegen
,
M.
, and
Dewilde
,
P.
,
1992
, “
Subspace Model Identification Part 1. The Output-Error State-Space Model Identification Class of Algorithms
,”
Int. J. Control.
,
56
(
5
), pp.
1187
1210
.
3.
Overschee
,
P.
, and
Moor
,
B.
,
1994
, “
N4SID: Subspace Algorithms for the Identification of Combined Deterministic-Stochastic Systems
,”
Automatica
,
30
(
1
), pp.
75
93
.
4.
Ljung
,
L.
,
2003
, “
Aspects and Experiences of User Choices in Subspace Identification Method
,”
Proceedings of the 13th IFAC Symposium on System Identification
,
Rotterdam, The Netherlands
,
August
.
5.
Bergboer
,
N.
,
Verdult
,
V.
, and
Verhaegen
,
M.
,
2002
, “
An Efficient Implementation of Maximum Likelihood Identification of LTI State-Space Models by Local Gradient Search
,”
Proceedings of Conference on Decision and Control
,
Las Vegas, NV
,
Dec
.
6.
Ninness
,
B.
, and
Henriksen
,
S.
,
2010
, “
Bayesian System Identification Via Markov Chain Monte Carlo Techniques
,”
Automatica
,
46
(
1
), pp.
40
51
.
7.
Wills
,
A.
,
Schön
,
T. B.
,
Lindsten
,
F.
, and
Ninness
,
B.
,
2012
, “
Estimation of Linear Systems Using a Gibbs Sampler
,”
Proceedings of the 16th IFAC Symposium on System Identification
,
Brussels, Belgium
,
July
.
8.
Kantas
,
N.
,
Doucet
,
A.
,
Singh
,
S. S.
,
Maciejowski
,
J.
, and
Chopin
,
N.
,
2015
, “
On Particle Methods for Parameter Estimation in State-Space Models
,”
Statist. Sci.
,
30
(
3
), pp.
328
351
.
9.
Schön
,
T. B.
,
Lindsten
,
F.
,
Dahlin
,
J.
,
Wågberg
,
J.
,
Naesseth
,
C. A.
,
Svensson
,
A.
, and
Dai
,
L.
,
2015
, “
Sequential Monte Carlo Methods for System Identification
,”
Proceedings of the 17th IFAC Symposium on System Identification
,
Beijing, China
,
Oct.
.
10.
Schön
,
T. B.
,
Svensson
,
A.
,
Murray
,
L.
, and
Lindsten
,
F.
,
2018
, “
Probabilistic Learning of Nonlinear Dynamical Systems Using Sequential Monte Carlo
,”
Mech. Syst. Signal. Process.
,
104
, pp.
866
883
.
11.
Roweis
,
S.
, and
Ghahramani
,
Z.
,
2001
,
Learning Nonlinear Dynamical Systems Using the Expectation–Maximization Algorithm
,
John Wiley & Sons, Ltd.
,
New York
, pp.
175
220
.
12.
Wan
,
E. A.
, and
Nelson
,
A. T.
,
2001
,
Dual Extended Kalman Filter Methods
,
John Wiley & Sons Ltd.
,
New York
, pp.
123
173
.
13.
Casella
,
G.
, and
Robert
,
C.
,
1996
, “
Rao-Blackwellisation of Sampling Schemes
,”
Biometrika
,
83
(
1
), pp.
81
94
.
14.
Andrieu
,
C.
,
de Freitas
,
N.
,
Doucet
,
A.
, and
Jordan
,
M. I.
,
2003
, “
An Introduction to MCMC for Machine Learning
,”
Mach. Learn.
,
50
(
1
), pp.
5
43
.
15.
Piga
,
D.
,
Bemporad
,
A.
, and
Benavoli
,
A.
,
2020
, “
Rao-Blackwellized Sampling for Batch and Recursive Bayesian Inference of Piecewise Affine Models
,”
Automatica
,
117
, p.
109002
.
16.
Moor
,
B. D.
,
Gersem
,
P. D.
,
Schutter
,
B. D.
, and
Favoreel
,
W.
,
1997
, “
DaISy: Database for the Identification of Systems
,”
Journal A, Special Issue on CACSD
,
38
(
3
), pp.
4
5
.
You do not currently have access to this content.