ROBUST RECURSIVE IDENTIFICATION OF HAMMERSTEIN MODELS BASED ON WEISZFALD ALGORITHM

Vojislav Filipović

DOI Number
https://doi.org/10.22190/FUACR1902127F
First page
127
Last page
140

Abstract


The Hammerstein models can accurately describe a wide variety of nonlinear systems (chemical process, power electronics, electrical drives, sticky control valves). Algorithms of identification depend, among other, on the assumption about the nature of stochastic disturbance. Practical research shows that disturbances, owing the presence of outliers, have a non-Gaussian distribution. In such case it is a common practice to use the robust statistics. In the paper, by analysis of the least favourable probability density, it is shown that the robust (Huber`s) estimation criterion can be presented as a sum of non-overlapping - norm and - norm criteria. By using a Weiszfald algorithm - norm criterion is converted to - norm criterion. So, the weighted - norm criterion is obtained for the identification. The main contributions of the paper are: (i) Presentation of the Huber`s criterion as a sum of - norm and - norm criteria; (ii) Using the Weiszfald algorithm  – norm criterion is converted to a weighted - norm criterion; (iii) Weighted extended least squares in which robustness is included through weighting coefficients are derived for NARMAX (nonlinear autoregressive moving average with exogenous variable) . The illustration of the behaviour of the proposed algorithm is presented through simulations.

Keywords

Hammerstein model, non-Gaussian noise, Weiszfald algorithm, weighted least squares

Full Text:

PDF

References


T. Soderstrom, P. Stoica, System Identification, Prentice-Hall, New Jersey,1989.

R. Pearson, Exploring Data in Engineering, the Science and Medicine, Oxford University Press, Oxford, 2011.

P. Huber, E. Ronchetti, Robust Statistics, Willey, New York, 2009.

H. Kodomama, B. Huang, R. Ranjan, Y. Zhao, R Tan, N. Sammakneyad, “Approaches to robust process identification: A review and tutorial of probability methods,“ Journal of Process Control, vol. 66, no.6 , pp. 68-83, 2018. [Online]. Available: https://doi.org/10.1016/j.jprocont.2018.02.011

V. Filipovic, “Outlier robust stochastic approximation algorithm for identification of MIMO Hammerstein models,“ Nonlinear Dynamics, vol. 90,no. 2, pp. 1427-1441, 2017. [Online]. Available: http://DOI10.1007/s11071-017-3736-2

V. Filipovic, “A global convergent outlier robust adaptive predictor for MIMO Hammerstein models,“ International Journal of Robust and Nonlinear Control, vol. 27, no.16, pp. 3350-3371, 2017. [Online]. Available: https://doi.org/10.1002/rnc.3705

V. Filipovic ,“Recursive identification of block-oriented nonlinear systems in the presence of outliers,“ Journal of Process Control, vol. 78, no.6, pp. 1-12, 2019. [Online]. Available: https://doi.org/10.1016/ j.jprocont.2019.03.015

M. Sugiyama, Introduction to Statistical Machine Learning, Morgan Kaufman, San Francisco, 2016.

M. Ghanmi, M. Elloumi, H. Salhi, S. Kamoun, “A recursive hierarchical parametric estimation algorithm for nonlinear systems described by Wiener – Hammerstein models,” Asian J. Control, vol. 21, no. 1, pp. 1-10, 2019. [Online]. Available: https://doi.org/10.1002/asjc.2029

F. Giri, E.W. Bai, Block-Oriented Nonlinear System Identification, Springer, Berlin, 2010.

E. Weiszfald, “Sur le point pour lequel la sommedes distances de n points donnes est minimum,” Tohoku Math. J., vol. 43, First series, pp.355-386, 1937. [Online]. Available: http://[pdf]jst.go.jp

E. Weiszfald, “On the point for which the sum of distances to n given points in minimum,” Anu. Oper. Res., vol. 167, no.1, pp. 7-41, 2009. Translate from the French original (Tohoku Math. J. vol. 43, First series, pp. 355-386, 1937. [Online]. Available: http://DOI10.1007/s10479-008-0352-z

P.A. Akimov, A.J. Matasov, “Level of non-optimality of the Weiszfald algorithm in the least-modules method,” Automation and Remote Control, vol. 71, no. 2, pp. 172-184, 2010. [Online]. Available: http://doi:10.1134/S0005117910020025

H.A. Eiselt, H Marianov, Foundations of Location Analysis, Springer, Berlin, 2011.

L. Mallozzi, E. D`Amato, P.M Pardalos, (Eds.), Spatial Interaction Models. Facility Location using Game Theory, Springer, Berlin, 2017.

Beck, S. Sabach, “Weiszfald method: old and new results,” Journal of Optimization Theory and Applications, vol. 164 , no. 1, pp. 1-40, 2015. [Online]. Available: http://DOI10.1007/s10957-011-0586-7

Weber, Theory of the Location of Industries. University of Chicago Press, Chicago, 1909.P. Bloomfield, W.L. Steiger, Least Absolute Deviations: Theory, Applications and Algorithms, Birkhauser, Basel, 1983.

V.I. Mudrov, V.L. Kushko, Methods of Measurements Processing, (in Russian), Radio Svjaz, Moscow, 1983.

S. Boyd,L. Vandenberghe, Convex Optimization, Cambridge University Press, Cambridge, 2004.

H. Kuhn, A note of Fermat problem. Math. Programming, vol. 4, no.1, pp. 98-107, 1973. [Online]. Available: http://DOI:10.1007/bfo1584648

V. Hutson, J. Pym, M. Cloud, Application of Functional Analysis and Operator Theory, Elsevier, London, 2005.

L. Ljung, T. Soderstrom, Theory and Practice of Recursive Identification, MIT Press, Massachusetts, 1983.

J.T. Barron, A general and adaptive robust loss function, arXiv: 1701.03077v10.




DOI: https://doi.org/10.22190/FUACR1902127F

Refbacks

  • There are currently no refbacks.


Print ISSN: 1820-6417
Online ISSN: 1820-6425