© The Institution of Engineering and Technology
In this study, we apply the expectation-maximisation (EM) algorithm to identify continuous-time state-space models from non-uniformly fast-sampled data. The sampling intervals are assumed to be small and uniformly bounded. The authors use a parameterisation of the sampled-data model in incremental form in order to modify the standard formulation of the EM algorithm for discrete-time models. The parameters of the incremental model converge to the parameter of the continuous-time system description as the sampling period goes to zero. The benefits of the proposed algorithm are successfully demonstrated via simulation studies.
References
-
-
1)
-
J. Durbin ,
S.J. Koopman
.
(2005)
Time series analysis by state space methods.
-
2)
-
H. Rauch ,
F. Tung ,
C. Striebel
.
Maximum likelihood estimates of linear dynamic systems.
AIAA J.
,
8 ,
1445 -
1450
-
3)
-
F. Ding ,
L. Qiu ,
T. Chen
.
Reconstruction of continuous-time systems from their non-uniformly sampled discrete-time systems.
Automatica
,
2 ,
324 -
332
-
4)
-
B. Øksendal
.
(2003)
Stochastic differential equations: an introduction with applications.
-
5)
-
M.J. Newman ,
D.G. Holmes
.
Delta operator digital filters for high performance inverter applications.
IEEE Trans. Power Electron.
,
1 ,
447 -
454
-
6)
-
M. Mansour
.
(1993)
Stability and robust stability of discrete-time systems in the δ-transform, Fundamentals of discrete-time systems: a tribute to Prof. Eliahu I. Jury.
-
7)
-
Agüero, J.C., Yuz, J.I., Goodwin, G.C.: `Frequency domain identification of MIMO state space models using the EM algorithm', European Control Conf. – ECC’07, 2007, Kos, Greece.
-
8)
-
S. Chirarattananon ,
B. Anderson
.
The fixed-lag smoother as a stable finite-dimensional linear system.
Automatica
,
6 ,
657 -
669
-
9)
-
G.C. Goodwin ,
S. Graebe ,
M.E. Salgado
.
(2001)
Control system design.
-
10)
-
McKelvey, T., Helmersson, A.: `State space parameterization of multivariable linear systems using tridiagonal matrix form', 35thIEEE Conf. on Decision and Control, 1996.
-
11)
-
A. Feuer ,
G.C. Goodwin
.
(1996)
Sampling in digital signal processing and control.
-
12)
-
J. Gillberg ,
L. Ljung
.
Frequency domain identification of continuous-time output error models, part II: non-uniformly sampled data and B-spline output approximation.
Automatica
,
1 ,
11 -
18
-
13)
-
A.P. Dempster ,
N.M. Laird ,
D.B. Rubin
.
Maximum likelihood from incomplete data via the EM algorithm.
J. R. Stat. Soc. B
,
1 ,
1 -
38
-
14)
-
K. Premaratne ,
E.I. Jury
.
Tabular method for determining root distribution of delta-operator formulated real polynomials.
IEEE Trans. Autom. Control
,
2 ,
352 -
355
-
15)
-
R.H. Shumway ,
D.S. Stoffer
.
An approach to time series smoothing and forecasting using the EM algorithm.
J. Time Ser. Anal.
,
253 -
264
-
16)
-
R. Pintelon ,
J. Schoukens
.
(2001)
System identification: a frequency domain approach.
-
17)
-
P. Suchomski
.
Numerically robust delta-domain solutions to discrete-time Lyapunov equations.
Syst. Control Lett.
,
4 ,
319 -
326
-
18)
-
T. Kailath ,
P. Frost
.
An innovations approach to least-squares estimation – part II: linear smoothing in additive white noise.
IEEE Trans, Autom. Control
,
6 ,
655 -
660
-
19)
-
R. Shumway ,
D. Stoffer
.
(2006)
Time series analysis and its applications.
-
20)
-
M.E. Salgado ,
R.H. Middleton ,
G.C. Goodwin
.
Connection between continuous and discrete Riccati equations with applications to Kalman filtering.
IEE Proc. Control Theory Appl.
,
1 ,
28 -
34
-
21)
-
K. Premaratne ,
S. Touset ,
E.I. Jury
.
Root distribution of delta-operator formulated polynomials.
IEE Proc. Control Theory Appl.
,
1 ,
1 -
12
-
22)
-
G.C. Goodwin ,
R.L. Payne
.
(1977)
Dynamic system identification: experiment design and data analysis.
-
23)
-
M. Deistler ,
G.C. Goodwin
.
(2000)
System identification-general aspects and structure, Model identification and adaptive control: from windsurfing to telecommunications.
-
24)
-
P.E. Kloeden ,
E. Platen
.
(1992)
Numerical solution of stochastic differential equations.
-
25)
-
Agüero, J.C., Yuz, J.I., Goodwin, G.C., Tang, W.: `Identification of state-space systems using a dual time-frequency domain approach', 49thIEEE Conf. on Decision and Control, 2010.
-
26)
-
V. Kadirkamanathan ,
S. Anderson
.
Maximum-likelihood estimation of delta-domain model parameters from noisy output signals.
IEEE Trans. Signal Process.
,
3765 -
3770
-
27)
-
K. Aström
.
(1970)
Introduction to stochastic control theory.
-
28)
-
C.F.J. Wu
.
On the convergence properties of the EM algorithm.
Ann. Stat.
,
1 ,
95 -
103
-
29)
-
S. Gibson ,
B. Ninness
.
Robust maximum-likelihood estimation of multivariables dynamic systems.
Automatica
,
10 ,
1667 -
1682
-
30)
-
A. Wills ,
B. Ninnesss ,
S. Gibson
.
Maximum likelihood estimation of state space models from frequency domain data.
IEEE Trans. Autom. Control
,
1 ,
19 -
33
-
31)
-
E.J. Hannan
.
The identification and parameterization of ARMAX and state space forms.
Econometrica
,
4 ,
713 -
723
-
32)
-
E. Larsson ,
T. Söderström
.
Identification of continuous-time AR processes from unevenly sampled data.
Automatica
,
709 -
718
-
33)
-
A.H. Jazwinski
.
(1970)
Stochastic processes and filtering theory.
-
34)
-
G.C. Goodwin ,
J.I. Yuz ,
M.E. Salgado ,
J.C. Agüero
.
Variance or spectral density in sampled data filtering?.
J. Glob. Optim. (to appear)
-
35)
-
G.C. Goodwin ,
R.H. Middleton ,
H.V. Poor
.
High-speed digital signal processing and control.
Proc. IEEE
,
2 ,
240 -
259
-
36)
-
G.C. Goodwin ,
A. Feuer
.
Estimation with missing data.
Math. Comput. Model. Dyn. Syst.
,
3 ,
220 -
244
-
37)
-
J. Meditch
.
A survey of data smoothing for linear and nonlinear dynamic systems.
Automatica
,
2 ,
151 -
162
-
38)
-
A. Bryson ,
Y. Ho
.
(1975)
Applied optimal control: optimization, estimation, and control.
-
39)
-
R.H. Middleton ,
G.C. Goodwin
.
(1990)
Digital control and estimation: a unified approach.
-
40)
-
L. Ljung ,
A. Wills
.
Issues in sampling and estimating continuous-time models with stochastic disturbances.
Automatica
,
5 ,
925 -
931
-
41)
-
A. Isaksson
.
Identification of ARX models subject to missing data.
IEEE Trans. Autom. Control
,
5 ,
813 -
819
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cta.2010.0246
Related content
content/journals/10.1049/iet-cta.2010.0246
pub_keyword,iet_inspecKeyword,pub_concept
6
6