Test for local structural identifiability of high-order non-linearly parametrized state space models (Q1923072)

From MaRDI portal





scientific article; zbMATH DE number 930714
Language Label Description Also known as
default for all languages
No label defined
    English
    Test for local structural identifiability of high-order non-linearly parametrized state space models
    scientific article; zbMATH DE number 930714

      Statements

      Test for local structural identifiability of high-order non-linearly parametrized state space models (English)
      0 references
      0 references
      0 references
      0 references
      11 April 1999
      0 references
      This paper presents tests for local identifiability of a deterministic single-input single-output linear system based on the sequence of Markov parameters \(\{h(k,\theta), k= 1,2,\dots, 2n\}\) where \(\theta\) is an unknown parameter and \(n\) is an upper bound to the McMillan degree. Part 3 of the paper is called: ``Identifiability analysis based on infinite-time information matrix'' and Part 4 is called ``Identifiability analysis based on finite-time information matrix''. Although the problem stated is deterministic, probabilistic calculations play an important role in this paper. The paper ends with an example. Numerical aspects are stressed.
      0 references
      state space models
      0 references
      gradients
      0 references
      Lyapunov equation
      0 references
      local identifiability
      0 references
      Markov parameters
      0 references

      Identifiers