Torsten Söderström's home page


#Background
#Research_interests
#Some research_projects
#Some other_professional_activities
#Ordering_of_the_book_System_Identification
#Some_recent_publications

NEW 


The book T. Söderström: Errors-in-Varibles Methods in System Identification, Springer, 2018 has recently appeared. It summarized my findings of the area from many years of research. See also
http://www.springer.com/gb/book/978331975000

I was given the IFAC TC 1.1 Award on System Identification 2021 for this book, with the citation "For a deep and broad analysis of EIV modeling of linear dynamic systems, treating identifiability, model selection and (parameter-) estimation procedures together with their statistical properties". This was the first time this tri-annual award is given. It is bestowed every three years to recognize the outstanding contribution of a publication (journal paper or book chapter or scientific monograph) in the area of system identification that has appeared in the six calendar years prior to the award year.


Background

I have a M Sc in engineering physics (Civilingenjör teknisk fysik), 1969, and a PhD in automatic control (Tekn Dr i reglerteknik), 1973, both from Lund Institute of Technology. I moved to Uppsala University in 1974, where I was a professor of automatic control until fall 2011, when I became professor emeritus. I was the head of the Department of Systems and Control 1975-1999. I am an IEEE Life Fellow and an IFAC Fellow.

Short CV

Research interests

My main research interests are in the fields of system identification, statistical signal processing, identification of continuous-time models,  error-in-variables problems, parameter estimation in infinite-dimensional systems, numerical algorithms in control and signal processing, adaptive filtering, and modelling and control of mechanical systems. 


Some research projects

* Identification of continuous-time systems 
(part of the multiproject Statistical signal processing)

* Errors-in-variables modelling

* Identification of nonlinear systems
(part of the multiproject Statistical signal processing)

* Identification of viscoelastic materials
(a previous progress report for this project)

* Parameter estimation in heat conduction and diffusion 
(a previous progress report for this project)

* Control of waves, vibrations and stability in mechanical structures

* Numerical algorithms in systems and control

Some graduated PhD's  engaged in these projects: 
Emad Abd-ElRady, Bharath Bhikkaji, Erik K. Larsson, Kaushik Mahata, Mei Hong Bjerstedt, Peter Nauclér, Hans Norlander, Agnes Rensfelt.


Some other professional activities

Editor of Automatica, subject area System Parameter Estimation/System Identification and Filtering, 1992-2022. 

Within IFAC, International Federation of Automatic Control
I was a Council member 1996-2002, 
Executive Board member 1999-2002, 
and Chair of the Awards Committee 1999-2002. 

Within EUCA, European Union Control Association
I was a Council member, 2001-2007.

The book 'System identification'

The textbook T. Söderström and P. Stoica: System Identification,
originally published by Prentice Hall International, is out of print.
It can, however, be freely downloaded:


Some recent publications


Books and book chapters
 

T. Söderström: Errors-in-Varibles Methods in System Identification, Springer, 2018.

T. Söderström: How accurate can instrumental variable models become? In  L. Wang and H. Garnier, eds: System Identification, Environmental Modelling and Control, Springer-Verlag, 2012.

T. Söderström: Linear stochastic input-output models. Chapter 60 In W. Levine, ed.: The Control Handbook, Control System Advance Methods, 2nd ed,Taylor and Francis, UK, 2011.

E. K. Larsson, M. Mossberg and T. Söderström: Estimation of Continuous-time Stochastic System Parameters. In H. Garnier and L. Wang, eds.: Identification of Continuous-time Models from Sampled Data. Springer-Verlag, 2008.

T. Söderström: Identifying characteristics of viscoelastic materials from wave propagation experiments -- recent advances. In T. Glad and G. Hendeby, eds.: Forever Ljung in System Identification, Studentlitteratur, Lund, 2006.

T. Söderström: Identification of linear systems in time domain. Encyclopedia of Life Support Systems (EOLSS), developed under the auspices of Unesco, EOLSS publishers, Oxford, UK, 2003. [http://www.eolss.net]

T. Söderström: Prediction error methods. Encyclopedia of Life Support Systems (EOLSS), developed under the auspices of Unesco, EOLSS publishers, Oxford, UK, 2003. [http://www.eolss.net]

T. Söderström: Discrete-Time Stochastic Systems - Estimation and Control
Second edition, Springer-Verlag, London, UK, 2002. (375 pp)


Journal papers


U. Soverini and T. Söderström: Frequency domain identification of FIR models in the presence of additive input-output noise. Automatica, vol 115, May 2020, 108879.

D. Verbeke, T. Söderström and U. Soverini: A note on the estimation of real- and complex-valued parameters in frequency domain maximum likelihood identification. Automatica, vol 110, December 2019, 108584.

T. Söderström: A user perspective on errors-in-variables methods in system identification. Control Engineering Practice, vol 89, pp 56-69, 2019. A feature paper for the series of Frontiers in Control Engineering Practice.

T. Söderström and U. Soverini: Errors-in-variables identification using maximum likelihood in the frequency domain. Automatica, vol 79, pp 131-143, May 2017.

D. Kreiberg, T. Söderström and F. Yang-Wallentin: Errors-in-variables identification using structural equation modeling. Automatica, vol 66, pp 218-230, April 2016.

T. Söderström, R. Diversi and U. Soverini: A unified framework for EIV identification methods when the measurement noises are mutually correlated. Automatica, vol 50, no 12, pp 3216-3223, December 2014.

T. Söderström, D. Kreiberg and M. Mossberg: Extended Accuracy Analysis of a Covariance Matching Approach for Identifying Errors-in-variables Systems. Automatica, vol 50, no 10, pp 2597-2605, October 2014.



Conference papers
 


T. Söderström and U. Soverini: Aspects of errors-in-variables identification: Some ways to mitigate a large bias. 22nd IFAC World Congress, Yokohama, Japan, July 9-14, 2023.

T. Söderström and U. Soverini: When are errors-in-variables aspects important to consider in system identification?, European Control Conference, London, UK, July 9-14, 2022.

U. Soverini and T. Söderström: Blind identification of two-channel FIR systems: a frequency domain approach. 21st IFAC World Congress, Berlin, Germany, July 12-17, 2000.

U. Soverini and T. Söderström: The Frisch scheme for EIV system identification: time and frequency domain formulations. 21st IFAC World Congress, Berlin, Germany, July 12-17, 2000.

U. Soverini and T. Söderström: 2D frequency domain identification of complex sinusoids in the presence of additive noise. 28th IFAC Symposium on System Identification, Stockholm, Sweden, July 9-11, 2018.

U. Soverini and T. Söderström: Identification of two-dimensional complex sinusoids in white noise: a state space frequency approach. 28th IFAC Symposium on System Identification, Stockholm, Sweden, July 9-11, 2018.

U. Soverini and T. Söderström: Frequency domain identification of complex sinusoids in the presence of additive noise. 20th IFAC World Congress, Toulouse, France, July 9-14, 2017.

U. Soverini and T. Söderström: Frequency domain identification of ARX models in the presence of additive input-output noise. 20th IFAC World Congress, Toulouse, France, July 9-14, 2017.

U. Soverini and T. Söderström: Frequency domain identification of autoregressive models in the presence of additive noise (Invited paper). WSEAS Conference Computer Science, ECCS16, Rome, Italy, October 21-23, 2016.

U. Soverini and T. Söderström: Frequency domain EIV identification combining the Frisch scheme and Yule-Walker equations. European Control Conference, Linz, Austria, July 15-17, 2015.

T. Söderström,  R. Diversi and U. Soverini: A unified framework for EIV identification methods in the presence of mutually correlated noises. IFAC 19th World Congress, Cape Town, South Africa, August 24-29, 2014.

U. Soverini and T. Söderström: Frequency domain maximum likelihood identification of noisy input-output models. IFAC 19th World Congress, Cape Town, South Africa, August 24-29, 2014.

U. Soverini and T. Söderström: Frequency domain EIV identification: a Frisch Scheme approach. IFAC 19th World Congress, Cape Town, South Africa, August 24-29, 2014.



Last updated: 17 May 2023 by Torsten Söderström