uu.seUppsala University Publications
Change search
Link to record
Permanent link

Direct link
BETA
Söderström, TorstenORCID iD iconorcid.org/0000-0003-4619-8879
Alternative names
Publications (10 of 213) Show all publications
Söderström, T. & Soverini, U. (2017). Errors-in-variables identification using maximum likelihood estimation in the frequency domain. Automatica, 79, 131-143
Open this publication in new window or tab >>Errors-in-variables identification using maximum likelihood estimation in the frequency domain
2017 (English)In: Automatica, ISSN 0005-1098, E-ISSN 1873-2836, Vol. 79, p. 131-143Article in journal (Refereed) Published
National Category
Control Engineering
Identifiers
urn:nbn:se:uu:diva-322085 (URN)10.1016/j.automatica.2017.01.016 (DOI)000399513300017 ()
Available from: 2017-03-02 Created: 2017-05-16 Last updated: 2017-05-17Bibliographically approved
Soverini, U. & Söderström, T. (2017). Frequency domain identification of ARX models in the presence of additive input–output noise. In: 20th IFAC World Congress: . Paper presented at 20th World Congress of the International-Federation-of-Automatic-Control (IFAC),Toulouse, France, July 09-14, 2017. (pp. 6226-6231). Elsevier, 50
Open this publication in new window or tab >>Frequency domain identification of ARX models in the presence of additive input–output noise
2017 (English)In: 20th IFAC World Congress, Elsevier, 2017, Vol. 50, p. 6226-6231Conference paper, Published paper (Refereed)
Abstract [en]

This paper describes a new approach for identifying ARX models from a finite number of measurements, in presence of additive and uncorrelated white noise. The proposed algorithm is based on some theoretical results concerning the so-called dynamic Frisch Scheme. As a major novelty, the proposed approach deals with frequency domain data. In some aspects, the method resembles the characteristics of other identification algorithms, originally developed in the time domain. The proposed method is compared with other techniques by means of Monte Carlo simulations. The benefits of filtering the data and using only part of the frequency domain is highlighted by means of a numerical example.

Place, publisher, year, edition, pages
Elsevier, 2017
Series
IFAC-PapersOnLine, E-ISSN 2405-8963 ; 50: 1
National Category
Signal Processing
Research subject
Electrical Engineering with specialization in Automatic Control
Identifiers
urn:nbn:se:uu:diva-334132 (URN)10.1016/j.ifacol.2017.08.1023 (DOI)000423964900038 ()
Conference
20th World Congress of the International-Federation-of-Automatic-Control (IFAC),Toulouse, France, July 09-14, 2017.
Available from: 2017-11-21 Created: 2017-11-21 Last updated: 2018-05-16Bibliographically approved
Soverini, U. & Söderström, T. (2017). Frequency domain identification of complex sinusoids in the presence of additive noise. In: 20th IFAC World Congress: . Paper presented at 20th World Congress of the International-Federation-of-Automatic-Control (IFAC),Toulouse,France,July 09-14, 2017 (pp. 6244-6250). Elsevier, 50
Open this publication in new window or tab >>Frequency domain identification of complex sinusoids in the presence of additive noise
2017 (English)In: 20th IFAC World Congress, Elsevier, 2017, Vol. 50, p. 6244-6250Conference paper, Published paper (Refereed)
Abstract [en]

his paper describes a new approach for identifying the parameters of complex sinusoids from a finite number of measurements, in presence of additive and uncorrelated white noise. The proposed approach deals with frequency domain data and as a major feature, it enables the estimation to be frequency selective. In many aspects the new method resembles the well known ESPRIT subspace algorithm, originally developed in the time domain. However, the sub band frequency selective feature allows a reduction of the computations and can improve the quality of the estimates. The properties of the proposed method are analyzed by means of Monte Carlo simulations and its performance is compared with those of other estimation algorithms.

Place, publisher, year, edition, pages
Elsevier, 2017
Series
IFAC-PapersOnLine, E-ISSN 2405-8963 ; 50:1
National Category
Signal Processing
Research subject
Electrical Engineering with specialization in Automatic Control
Identifiers
urn:nbn:se:uu:diva-334711 (URN)10.10164/j.facol.2017.08.848 (DOI)000423964900041 ()
Conference
20th World Congress of the International-Federation-of-Automatic-Control (IFAC),Toulouse,France,July 09-14, 2017
Available from: 2017-11-27 Created: 2017-11-27 Last updated: 2018-05-17Bibliographically approved
Kreiberg, D., Söderström, T. & Yang-Wallentin, F. (2016). Errors-in-variables system identification using structural equation modeling. Automatica, 66, 218-230
Open this publication in new window or tab >>Errors-in-variables system identification using structural equation modeling
2016 (English)In: Automatica, ISSN 0005-1098, E-ISSN 1873-2836, Vol. 66, p. 218-230Article in journal (Refereed) Published
Abstract [en]

Errors-in-variables (EIV) identification refers to the problem of consistently estimating linear dynamic systems whose output and input variables are affected by additive noise. Various solutions have been presented for identifying such systems. In this study, EIV identification using Structural Equation Modeling (SEM) is considered. Two schemes for how EIV Single-Input Single-Output (SISO) systems can be formulated as SEMs are presented. The proposed formulations allow for quick implementation using standard SEM software. By simulation examples, it is shown that compared to existing procedures, here represented by the covariance matching (CM) approach, SEM-based estimation provide parameter estimates of similar quality.

Keywords
System identification; Errors-in-variables models; Linear systems; Structural equation models
National Category
Control Engineering
Research subject
Statistics
Identifiers
urn:nbn:se:uu:diva-277383 (URN)10.1016/j.automatica.2015.12.007 (DOI)000371099300025 ()
Funder
Swedish Research Council, 421-2011-1727
Available from: 2016-01-25 Created: 2016-02-19 Last updated: 2017-11-30Bibliographically approved
Söderström, T., Diversi, R. & Soverini, U. (2014). A unified framework for EIV identification methods when the measurement noises are mutually correlated. Automatica, 50(12), 3216-3223
Open this publication in new window or tab >>A unified framework for EIV identification methods when the measurement noises are mutually correlated
2014 (English)In: Automatica, ISSN 0005-1098, E-ISSN 1873-2836, Vol. 50, no 12, p. 3216-3223Article in journal (Refereed) Published
Abstract [en]

In this paper, the previously introduced Generalized Instrumental Variable Estimator (GIVE) is extended to the case of errors-in-variables models where the additive input and output noises are mutually correlated white processes. It is shown how many estimators proposed in the literature can be described as various special cases of a generalized instrumental variable framework. It is also investigated how to analyze the common situation where some of the equations that define the estimator are to hold exactly, and others to hold approximately in a least squares sense, providing a detailed study of the accuracy analysis. 

National Category
Control Engineering
Identifiers
urn:nbn:se:uu:diva-244579 (URN)10.1016/j.automatica.2014.10.037 (DOI)000347760100027 ()
Available from: 2014-10-27 Created: 2015-02-18 Last updated: 2017-12-04Bibliographically approved
Söderström, T., Kreiberg, D. & Mossberg, M. (2014). Extended accuracy analysis of a covariance matching approach for identifying errors-in-variables systems. Automatica, 50(10), 2597-2605
Open this publication in new window or tab >>Extended accuracy analysis of a covariance matching approach for identifying errors-in-variables systems
2014 (English)In: Automatica, ISSN 0005-1098, E-ISSN 1873-2836, Vol. 50, no 10, p. 2597-2605Article in journal (Refereed) Published
Abstract [en]

A covariance matching approach for identifying errors-in-variables systems is analyzed for the general case. The asymptotic covariance matrix of the jointly estimated system parameters, noise variances and auxiliary parameters is derived. An algorithm for how to compute this covariance matrix from given system descriptions is also provided. The results generalize previous known special cases. Using Monte Carlo analysis, we illustrate the proposed algorithm. The results suggest close agreement between the theoretical and empirical accuracy.

National Category
Control Engineering
Identifiers
urn:nbn:se:uu:diva-238583 (URN)10.1016/j.automatica.2014.08.020 (DOI)000344207300018 ()
Available from: 2014-09-16 Created: 2014-12-14 Last updated: 2017-12-05Bibliographically approved
Söderström, T., Wang, L., Pintelon, R. & Schoukens, J. (2013). Can errors-in-variables systems be identified from closed-loop experiments?. Automatica, 49(2), 681-684
Open this publication in new window or tab >>Can errors-in-variables systems be identified from closed-loop experiments?
2013 (English)In: Automatica, ISSN 0005-1098, E-ISSN 1873-2836, Vol. 49, no 2, p. 681-684Article in journal (Refereed) Published
Abstract [en]

Errors-in-variables (EIV) systems are known to be identifiable not generally, but under some specific conditions. These conditions are normally formulated for open-loop systems. This paper examines to what extent an EIV system can be identifiable from closed-loop experiments.

Keywords
Errors-in-variables models, Linear systems, System identification, Closed-loop experiments, Errors in variables, Open loop systems, Experiments, Identification (control systems), Errors
National Category
Control Engineering
Identifiers
urn:nbn:se:uu:diva-194899 (URN)10.1016/j.automatica.2012.11.017 (DOI)000315003100045 ()
Available from: 2013-02-20 Created: 2013-02-19 Last updated: 2017-12-06Bibliographically approved
Söderström, T. (2013). Comparing some classes of bias-compensating least squares methods. Automatica, 49(3), 840-845
Open this publication in new window or tab >>Comparing some classes of bias-compensating least squares methods
2013 (English)In: Automatica, ISSN 0005-1098, E-ISSN 1873-2836, Vol. 49, no 3, p. 840-845Article in journal (Refereed) Published
Abstract [en]

Three different classes of bias-compensating least squares identification methods are compared, and shown to be identical. It is also discussed how the user parameters in the classes can be chosen to achieve optimal accuracy of the parameter estimates.

Keywords
System identification, Bias compensation, Errors-in-variables models, Linear systems
National Category
Control Engineering
Identifiers
urn:nbn:se:uu:diva-198924 (URN)10.1016/j.automatica.2013.01.003 (DOI)000316590300019 ()
Available from: 2013-04-29 Created: 2013-04-29 Last updated: 2017-12-06Bibliographically approved
Kreiberg, D., Söderström, T. & Yang-Wallentin, F. (2013). Errors-in-variables identification using covariance matching and structural equation modeling. In: Proc. 52nd Conference on Decision and Control: . Paper presented at CDC 2013, December 10-13, Florence, Italy (pp. 5852-5857). Piscataway, NJ: IEEE
Open this publication in new window or tab >>Errors-in-variables identification using covariance matching and structural equation modeling
2013 (English)In: Proc. 52nd Conference on Decision and Control, Piscataway, NJ: IEEE , 2013, p. 5852-5857Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Piscataway, NJ: IEEE, 2013
National Category
Control Engineering
Identifiers
urn:nbn:se:uu:diva-218042 (URN)10.1109/CDC.2013.6760812 (DOI)978-1-4673-5714-2 (ISBN)
Conference
CDC 2013, December 10-13, Florence, Italy
Available from: 2014-03-07 Created: 2014-02-07 Last updated: 2014-03-28Bibliographically approved
Söderström, T. & Yuz, J. (2013). Model validation methods for errors-in-variables estimation. In: Proc. 52nd Conference on Decision and Control: . Paper presented at CDC 2013, December 10-13, Florence, Italy (pp. 3882-3887). Piscataway, NJ: IEEE
Open this publication in new window or tab >>Model validation methods for errors-in-variables estimation
2013 (English)In: Proc. 52nd Conference on Decision and Control, Piscataway, NJ: IEEE , 2013, p. 3882-3887Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Piscataway, NJ: IEEE, 2013
National Category
Control Engineering
Identifiers
urn:nbn:se:uu:diva-218043 (URN)10.1109/CDC.2013.6760482 (DOI)978-1-4673-5714-2 (ISBN)
Conference
CDC 2013, December 10-13, Florence, Italy
Available from: 2014-03-07 Created: 2014-02-07 Last updated: 2014-03-11Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-4619-8879

Search in DiVA

Show all publications