Improved Initialization for Nonlinear State-Space Modeling
This work addresses the initialization problem for nonlinear system identification, offering a practical solution for practitioners who need reliable starting points for iterative estimation algorithms.
The paper proposes a novel initialization algorithm for nonlinear state-space models that separates linear dynamics from nonlinear terms, transforming the problem into an approximate static formulation for fast regression-based estimation. The method is validated on the Wiener-Hammerstein benchmark and a crystal detector identification, showing improved initialization.
This paper discusses a novel initialization algorithm for the estimation of nonlinear state-space models. Good initial values for the model parameters are obtained by identifying separately the linear dynamics and the nonlinear terms in the model. In particular, the nonlinear dynamic problem is transformed into an approximate static formulation, and simple regression methods are applied to obtain the solution in a fast and efficient way. The proposed method is validated by means of two measurement examples: the Wiener-Hammerstein benchmark problem, and the identification of a crystal detector.