**Page description appears here**

“Parameter and State Estimation of Large-Scale Complex Systems Using Python Tools”

Authors: M. Anushka S. Perera, Tor A. Hauge and Carlos F. Pfeiffer,
Affiliation: Telemark University College and Glencore Nikkelverk (Kristiansand)
Reference: 2015, Vol 36, No 3, pp. 189-198.

     Valid XHTML 1.0 Strict

Keywords: Kalman filter, Modelica, Observability, Python, state and parameter estimation

Abstract: This paper discusses the topics related to automating parameter, disturbance and state estimation analysis of large-scale complex nonlinear dynamic systems using free programming tools. For large-scale complex systems, before implementing any state estimator, the system should be analyzed for structural observability and the structural observability analysis can be automated using Modelica and Python. As a result of structural observability analysis, the system may be decomposed into subsystems where some of them may be observable --- with respect to parameter, disturbances, and states --- while some may not. The state estimation process is carried out for those observable subsystems and the optimum number of additional measurements are prescribed for unobservable subsystems to make them observable. In this paper, an industrial case study is considered: the copper production process at Glencore Nikkelverk, Kristiansand, Norway. The copper production process is a large-scale complex system. It is shown how to implement various state estimators, in Python, to estimate parameters and disturbances, in addition to states, based on available measurements.

PDF PDF (4924 Kb)        DOI: 10.4173/mic.2015.3.6

DOI forward links to this article:
  [1] Sungho Kim, Jaejung Urm, Dae Shik Kim, Kihong Lee and Jong Min Lee (2018), doi:10.1007/s11814-018-0134-5

[1] Bona, B. and Smay, R.J. (1966). Optimum reset of ship's inertial navigation system, Aerospace and Electronic Systems, IEEE Transactions on. (4):409--414. doi:10.1109/TAES.1966.4501790
[2] Cox, H. (1964). On the estimation of state variables and parameters for noisy dynamic systems, Automatic Control, IEEE Transactions on. 9(1):5--12. doi:10.1109/TAC.1964.1105635
[3] Doucet, A., Godsill, S., and Andrieu, C. (2000). On sequential Monte Carlo sampling methods for Bayesian filtering, Statistics and computing. 10(3):197--208. doi:10.1023/A:1008935410038
[4] Fitzgerald, R.J. (1971). Divergence of the Kalman filter, Automatic Control, IEEE Transactions on. 16(6):736--747. doi:10.1109/TAC.1971.1099836
[5] Gelb, A. (2001). Applied optimal estimation, The M.I.T. press.
[6] Hermann, R. and Krener, A.J. (1977). Nonlinear controllability and observability, IEEE Transactions on automatic control. 22(5):728--740. doi:10.1109/TAC.1977.1101601
[7] Isidori, A. (1995). Nonlinear control systems, Springer Science & Business Media.
[8] Jazwinski, A.H. (2007). Stochastic processes and filtering theory, Courier Corporation.
[9] Julier, S.J., Uhlmann, J.K., and Durrant-Whyte, H.F. (1995). A new approach for filtering nonlinear systems, In American Control Conference, Proceedings of the 1995, volume3. IEEE, pages 1628--1632. doi:10.1109/ACC.1995.529783
[10] Kloeden, P.E., Platen, E., and Schurz, H. (2012). Numerical solution of SDE through computer experiments, Springer Science & Business Media.
[11] Lie, B. and Hauge, T.A. (2008). Modeling of an industrial copper leaching and electrowinning process, with validation against experimental data, In Proceedings SIMS. pages 7--8.
[12] Lin, C.T. (1974). Structural controllability, Automatic Control, IEEE Transactions on. 19(3):201--208. doi:10.1109/TAC.1974.1100557
[13] Liu, Y.-Y., Slotine, J.-J., and Barabasi, A.-L. (2013). Observability of complex systems, Proceedings of the National Academy of Sciences. 110(7):2460--2465. doi:10.1073/pnas.1215508110
[14] Ljung, L. (1979). Asymptotic behavior of the extended Kalman filter as a parameter estimator for linear systems, Automatic Control, IEEE Transactions on. 24(1):36--50. doi:10.1109/TAC.1979.1101943
[15] Margaria, G., Riccomagno, E., and White, L.J. (2004). Structural identifiability analysis of some highly structured families of statespace models using differential algebra, Journal of mathematical biology. 49(5):433--454. doi:10.1007/s00285-003-0261-3
[16] Moraal, P. and Grizzle, J. (1995). Observer design for nonlinear systems with discrete-time measurements, Automatic Control, IEEE Transactions on. 40(3):395--404. doi:10.1109/9.376051
[17] Perera, M. A.S., Lie, B., and Pfeiffer, C.F. (2015). Structural Observability Analysis of Large Scale Systems Using Modelica and Python, Modeling, Identification and Control. 36(1):53--65. doi:10.4173/mic.2015.1.4
[18] Potter, J.E. (1965). A matrix equation arising in statistical filter theory, volume 270, National Aeronautics and Space Administration.
[19] Reinschke, K.J. (1988). Multivariable control: a graph theoretic approach, 1988.
[20] Simon, D. (2006). Optimal State Estimation: Kalman, H-Infinity, and Nonlinear Approaches, Wiley-Interscience.
[21] Slotine, J.-J.E., Li, W., etal. (1991). Applied nonlinear control, volume 199, Prentice-hall Englewood Cliffs, NJ.
[22] Song, Y. and Grizzle, J.W. (1992). The extended Kalman filter as a local asymptotic observer for nonlinear discrete-time systems, In American Control Conference, 1992. IEEE, pages 3365--3369, 1992.
[23] Strang, G. and Borre, K. (1997). Linear algebra, geodesy, and GPS, Sia.

  title={{Parameter and State Estimation of Large-Scale Complex Systems Using Python Tools}},
  author={Perera, M. Anushka S. and Hauge, Tor A. and Pfeiffer, Carlos F.},
  journal={Modeling, Identification and Control},
  publisher={Norwegian Society of Automatic Control}


Oct 2018: MIC reaches 3000 DOI Forward Links. The last 1000 took 2 years and 5 months.

May 2016: MIC reaches 2000 DOI Forward Links. The first 1000 took 34 years, the next 1000 took 2.5 years.

July 2015: MIC's new impact factor is now 0.778. The number of papers published in 2014 was 21 compared to 15 in 2013, which partially explains the small decrease in impact factor.

Aug 2014: For the 3rd year in a row MIC's impact factor increases. It is now 0.826.

Dec 2013: New database-driven web-design enabling extended statistics. Article number 500 is published and MIC reaches 1000 DOI Forward Links.

Jan 2012: Follow MIC on your smartphone by using the RSS feed.


July 2011: MIC passes 1000 ISI Web of Science citations.

Mar 2010: MIC is now indexed by DOAJ and has received the Sparc Seal seal for open access journals.

Dec 2009: A MIC group is created at LinkedIn and Twitter.

Oct 2009: MIC is now fully updated in ISI Web of Knowledge.