Abstract
A system identification based on physical laws often involves a parameter estimation. Before performing an estimation problem, it is necessary to investigate its identifiability. This investigation leads often to painful calculations. Generally, the numerical computation of the parameters does not use these calculus. In this contribution we propose least-squares methods to link identifiability approaches with numerical parameter estimation.
Similar content being viewed by others
References
F. Boulier, D. Lazard, F. Ollivier and M. Petitot, Representation for the radical of a finitely generated differential ideal, in: Proc. of ISSAC'95, Internat. Symposium on Symbolic and Algebraic Computation, Montréal, Canada, 1995, pp. 158–166.
L. Denis-Vidal, G. Joly-Blanchard and C. Noiret, Some effective approaches to check the identifiability of uncontrolled nonlinear systems, Math. Comput. Simulation 57 (2001) 35–44.
L. Denis-Vidal, G. Joly-Blanchard, C. Noiret and M. Petitot, An algorithm to test identifiability of non-linear systems, in: Proc. of the 5th IFAC NOLCOS, St Petersburg, Russia, 2001, pp. 174–178.
L. Ljung, System Identification: Practice for the User (Prentice-Hall, Englewood Cliffs, NJ, 1989).
L. Ljung and T. Glad, On global identifiability for arbitrary model parametrizations, Automatica 30(2) (1994) 265–276.
M. Ouarit, J. P. Yvon and J. Henry, Optimal weighting design for distributed parameter system estimation, Optimal Control Appl. Methods 22 (2001) 37–49.
E. Walter, Identifiability of state space models, in: Lecture Notes Biomath., Vol. 46 (1982).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Denis-Vidal, L., Joly-Blanchard, G. & Noiret, C. System Identifiability (Symbolic Computation) and Parameter Estimation (Numerical Computation). Numerical Algorithms 34, 283–292 (2003). https://doi.org/10.1023/B:NUMA.0000005366.05704.88
Issue Date:
DOI: https://doi.org/10.1023/B:NUMA.0000005366.05704.88