Comparison of several data-driven non-linear system identification methods on a simplified glucoregulatory system example

Anna Marconato; Maarten Schoukens; Koen Tiels; Widanalage Dhammika Widanage; Amjad Abu-Rmileh; Johan Schoukens

Comparison of several data-driven non-linear system identification methods on a simplified glucoregulatory system example

View Fulltext

Author(s): Anna Marconato ¹ ; Maarten Schoukens ¹ ; Koen Tiels ¹ ; Widanalage Dhammika Widanage ² ; Amjad Abu-Rmileh ³ ; Johan Schoukens ¹
- Affiliations: 1: Department ELEC, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Brussels, Belgium;
  2: WMG, University of Warwick, Coventry, CV4 7AL, U.K.;
  3: Department of Brain and Cognitive Sciences, Ben-Gurion University of the Negev, Beer-Sheva, 84105, Israel
Source: Volume 8, Issue 17, 20 November 2014, p. 1921 – 1930
DOI: 10.1049/iet-cta.2014.0534 , Print ISSN 1751-8644, Online ISSN 1751-8652

Received 09/05/2014, Accepted 24/07/2014, Published 29/08/2014

In this study, several advanced data-driven non-linear identification techniques are compared on a specific problem: a simplified glucoregulatory system modelling example. This problem represents a challenge in the development of an artificial pancreas for Type 1 diabetes mellitus treatment, since for this application good non-linear models are needed to design accurate closed-loop controllers to regulate the glucose level in the blood. Block-oriented as well as state-space models are used to describe both the dynamics and the non-linear behaviour of the insulin–glucose system, and the advantages and drawbacks of each method are pointed out. The obtained non-linear models are accurate in simulating the patient's behaviour, and some of them are also sufficiently simple to be considered in the implementation of a model-based controller to develop the artificial pancreas.

References

1. 1)
  - 19. Evans, C., Rees, D., Jones, L.: ‘Non-linear disturbance errors in system identification using multisine test signals’, IEEE Trans. Instrum. Meas., 1994, 43, pp. 238–244 (doi: 10.1109/19.293427).
2. 2)
  - 17. Pintelon, R., Schoukens, J., Vandersteen, G., Barbé, K.: ‘Estimation of nonparametric noise and FRF models for multivariable systems - Part I: Theory’, Mech. Syst. Signal Process., 2010, 24, (3), pp. 573–595 (doi: 10.1016/j.ymssp.2009.08.009).
3. 3)
  - 10. Abu-Rmileh, A., Schoukens, J.: ‘Frequency domain analysis of nonlinear glucose simulation models’. in 8th IFAC Symp. on Biological and Medical Systems, Budapest, Hungary, 2012, pp. 28–33.
4. 4)
  - 13. Pintelon, R., Schoukens, J.: ‘System identification: a frequency domain approach’ (2nd edn., Wiley-IEEE Press, 2012).
5. 5)
  - 14. Marchetti, G., Barolo, M., Jovanovic, L., Zisser, H., Seborg, D.E.: ‘A feedforward-feedback glucose control strategy for type 1 diabetes mellitus’, J. Process Control, 2008, 18, (2), pp. 149–162 (doi: 10.1016/j.jprocont.2007.07.008).
6. 6)
  - 16. Abu-Rmileh, A., Garcia-Gabin, W.: ‘Wiener sliding-mode control for artificial pancreas: a new nonlinear approach to glucose regulation’, Comput. Methods Programs Biomed., 2012, 107, (2), pp. 327–340 (doi: 10.1016/j.cmpb.2012.03.001).
7. 7)
  - 4. Paduart, J., Lauwers, L., Swevers, J., Smolders, K., Schoukens, J., Pintelon, R.: ‘Identification of nonlinear systems using polynomial nonlinear state space models’, Automatica, 2010, 46, (4), pp. 647–656 (doi: 10.1016/j.automatica.2010.01.001).
8. 8)
  - 2. Giri, F., Bai, E.W. (Eds.): ‘Block-oriented nonlinear system identification’ (Springer, 2010).
9. 9)
  - 20. Hunter, W.I., Korenberg, M.J.: ‘The identification of nonlinear biological systems: Wiener and Hammerstein cascade models’, Biol. Cybern., 1986, 55, (2-3), pp. 135–144.
10. 10)
  - 27. Paduart, J.: ‘Identification of Nonlinear Systems using Polynomial Nonlinear State Space Models’. PhD Thesis, Vrije Universiteit Brussel, 2008.
11. 11)
  - 32. Widanage, W.D., Stoev, J., Van Mulders, A., Schoukens, J., Pinte, G.: ‘Non-linear system-identification of the filling phase of a wet-clutch system’, Control Eng. Pract., 2011, 19, (12), pp. 1506–1516 (doi: 10.1016/j.conengprac.2011.09.002).
12. 12)
  - 12. Ljung, L.: ‘System Identification: Theory for the User’ (2nd edn., Prentice Hall, New Jersey, 1999).
13. 13)
  - 11. Cerone, V., Piga, D., Regruto, D., Berehanu, S.: ‘LPV identification of the glucose-insulin dynamics in type I diabetes’. in Sixteenth IFAC Symp. on System Identification, Brussels, Belgium, 2012, pp. 559–564.
14. 14)
  - 26. Tiels, K., Schoukens, J.: ‘Identifying a Wiener system using a variant of the Wiener G-Functionals’. in 50th IEEE Conf. Decision and Control and European Control Conf. (CDC-ECC11), Orlando, FL, USA, 2011, pp. 5780–5785.
15. 15)
  - 8. Cobelli, C., Dalla Man, C., Sparacino, G., Magni, L., De Nicolao, G., Kovatchev, B.: ‘Diabetes: Models, signals, and control’, IEEE Rev. Biomed. Eng., 2009, 2, pp. 54–96 (doi: 10.1109/RBME.2009.2036073).
16. 16)
  - 4. Hovorka, R., Canonico, V., Chassin, L.J., et al: ‘Nonlinear model predictive control of glucose concentration in subjects with type 1 diabetes’, Physiol. Meas., 2004, 25, (4), pp. 905–920 (doi: 10.1088/0967-3334/25/4/010).
17. 17)
  - 7. Bergman, R.N., Ider, Y.Z., Bowden, C.R., Cobelli, C.: ‘Quantitative estimation of insulin sensitivity’, Am. J. Physiol., 1979, 236, (6), pp. E667–E677.
18. 18)
  - 9. Bequette, B.W.: ‘Challenges and recent progress in the development of a closed-loop artificial pancreas’, Annu. Rev. Control, 201236, (2), pp. 255–266 (doi: 10.1016/j.arcontrol.2012.09.007).
19. 19)
  - 21. Zhu, Y.C.: ‘Distillation column identification for control using Wiener model’. in American Control Conf., San Diego, USA, 1999, pp. 3462–3466.
20. 20)
  - S. Boyd , L. Chua . Fading memory and the problem of approximating nonlinear operators with volterra series. IEEE Trans. Circuits Syst. , 11 , 1150 - 1161
21. 21)
  - 18. Kollár, I.: Frequency Domain System Identificaton Toolbox for Matlab’ (Gamax Ltd, Budapest, 2004–2009).
22. 22)
  - 31. Suykens, J.A.K., Van Gestel, T., De Brabanter, J., De Moor, B., Vandewalle, J.: ‘Least squares support vector machines’ World Scientific, (Singapore, 2002).
23. 23)
  - 5. Dalla Man, C., Rizza, R.A., Cobelli, C.: ‘Meal simulation model of the glucose–insulin system’, IEEE Trans. Biomed. Eng., 2007, 54, (10), pp. 1740–1749 (doi: 10.1109/TBME.2007.893506).
24. 24)
  - 23. Hastie, T., Tibshirani, R., Friedman, J.: ‘The elements of statistical learning: data mining, inference and prediction’ (Springer-Verlag, 2009).
25. 25)
  - 3. Verdult, V.: ‘Nonlinear system identification: a state-space approach’. PhD Thesis, University of Twente, 2002.
26. 26)
  - 24. Heuberger, P.S.C., Van den Hof, P.M.J., Wahlberg, B. (Eds.): ‘Modelling and identification with rational orthogonal basis functions’ (Springer, London, 2005).
27. 27)
  - 1. Ljung, L.: ‘Perspectives on system identification’, Annu. Rev. Control, 2010, 34, pp. 1–12 (doi: 10.1016/j.arcontrol.2009.12.001).
28. 28)
  - P. Crama , J. Schoukens . Initial estimates of Wiener and Hammerstein systems using multisine excitation. IEEE Trans. Instrum. Meas. , 6 , 1791 - 1795
29. 29)
  - 15. van Heusden, K., Dassau, E., Zisser, H.C., Seborg, D.E., Doyle, F.J.: ‘Control-relevant models for glucose control using a priori patient characteristics’, IEEE Trans. Biomed. Eng., 2012, 59, (7), pp. 1839–1849 (doi: 10.1109/TBME.2011.2176939).
30. 30)
  - 28. Marconato, A., Sjöberg, J., Schoukens, J.: ‘Initialization of nonlinear state-space models applied to the Wiener–Hammerstein benchmark’, Control Eng. Practice, 2012, 20, (11), pp. 1126–1132 (doi: 10.1016/j.conengprac.2012.07.004).
31. 31)
  - T. Mckelvey , H. Ackay , L. Ljung . Subspace-based multivariable system identification from frequency response data. IEEE Trans. Autom. Control , 7 , 960 - 979
32. 32)
  - 30. Vapnik, V.: ‘Statistical learning theory’ (Wiley, 1998).

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Comparison of several data-driven non-linear system identification methods on a simplified glucoregulatory system example

References

Related content