An EM Algorithm for Lebesgue-sampled State-space Continuous-time System Identification

被引：1

作者：

Gonzalez, Rodrigo A. ^{[1
]}

Cedeno, Angel L. ^{[2
,3
]}

Coronel, Maria ^{[3
]}

Aguero, Juan C. ^{[2
,3
]}

Rojas, Cristian R. ^{[4
]}

机构：

[1] Eindhoven Univ Technol, Dept Mech Engn, Eindhoven, Netherlands

[2] Univ Tecn Federico Santa Maria, Elect Engn Dept, Valparaiso, Chile

[3] Adv Ctr Elect & Elect Engn AC3E, Valparaiso, Chile

[4] KTH Royal Inst Technol, Div Decis & Control Syst, Stockholm, Sweden

来源：

IFAC PAPERSONLINE | 2023年 / 56卷 / 02期

基金：

瑞典研究理事会;

关键词：

System identification; continuous-time systems; event-based sampling; expectation-maximization; MODELS;

D O I：

10.1016/j.ifacol.2023.10.1771

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper concerns the identification of continuous-time systems in state-space form that are subject to Lebesgue sampling. Contrary to equidistant (Riemann) sampling, Lebesgue sampling consists of taking measurements of a continuous-time signal whenever it crosses fixed and regularly partitioned thresholds. The knowledge of the intersample behavior of the output data is exploited in this work to derive an expectation-maximization (EM) algorithm for parameter estimation of the state-space and noise covariance matrices. For this purpose, we use the incremental discrete-time equivalent of the system, which leads to EM iterations of the continuous-time state-space matrices that can be computed by standard filtering and smoothing procedures. The effectiveness of the identification method is tested via Monte Carlo simulations.

引用

页码：4204 / 4209

页数：6

共 50 条

[21] Identification of continuous-time ARX models from irregularly sampled data
Larsson, Erik K.
Mossberg, Magnus
Soderstrom, Torsten
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2007, 52 (03) : 417 - 427
[22] Identification of continuous-time AR processes from unevenly sampled data
Larsson, EK
Söderström, T
AUTOMATICA, 2002, 38 (04) : 709 - 718
[23] Nuclear norm subspace identification of continuous time state-space models with missing outputs
Varanasi, Santhosh Kumar
Jampana, Phanindra
CONTROL ENGINEERING PRACTICE, 2020, 95
[24] Separable Identification of Continuous-Time Systems Having Multiple Unknown Time Delays from Sampled Data
Ghoul, Y.
Taarit, Ibn K.
Ksouri, M.
2016 4TH INTERNATIONAL CONFERENCE ON CONTROL ENGINEERING & INFORMATION TECHNOLOGY (CEIT), 2016,
[25] System identification of nonlinear state-space models
Schon, Thomas B.
Wills, Adrian
Ninness, Brett
AUTOMATICA, 2011, 47 (01) : 39 - 49
[26] Identification of continuous-time systems utilising Kautz basis functions from sampled-data
Coronel, Maria
Carvajal, Rodrigo
Aguero, Juan C.
IFAC PAPERSONLINE, 2020, 53 (02): : 536 - 541
[27] An asymptotically optimal indirect approach to continuous-time system identification
Gonzalez, Rodrigo A.
Rojas, Cristian R.
Welsh, James S.
2018 IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2018, : 638 - 643
[28] Identification of Continuous-Time Systems with Multiple Unknown Time Delays from Sampled Data
Ghoul, Yamna
Zitouni, Naoufel
Ibn Taarit, Kaouther
Ksouri, Moufida
MATHEMATICAL PROBLEMS IN ENGINEERING, 2022, 2022
[29] Parametric Continuous-Time Blind System Identification
Elton, Augustus
Gonzalez, Rodrigo A.
Welsh, James S.
Rojas, Cristian R.
Fu, Minyue
2023 62ND IEEE CONFERENCE ON DECISION AND CONTROL, CDC, 2023, : 1474 - 1479
[30] Identification of continuous-time systems via genetic algorithm
Inoue, K
Gan, C
Shibata, H
SICE 2002: PROCEEDINGS OF THE 41ST SICE ANNUAL CONFERENCE, VOLS 1-5, 2002, : 1989 - 1993

← 1 2 3 4 5 →