On-line structure detection and parameter estimation with exponential windowing for nonlinear systems
A recursive algorithm for simultaneous on-line model structure selection and parameter estimation is proposed for a time-varying discrete-time nonlinear polynomial-type NARMAX model. The algorithm is based on the idea of orthogonal QR decomposition, extended to include on-line modification of the structure of the model, and exploits the Givens rotation method. The approach proposed, including exponential data windowing, minimizes the loss function by selecting significant regression variables, computing the parameter estimates and detecting the (variable) model structure on line. Simulation examples are included to illustrate the properties and efficiency of the algorithm.
- Consistent estimation of the order of stochastic control systems
- Correlation based model validity tests for non-linear models
- Extended model set, global data and threshold model identification of severely non-linear systems
- Factorization methods for discrete sequential estimation
- Input-output parametric models for non-linear systems Part II: stochastic non-linear systems
- Least Squares Computations by Givens Transformations Without Square Roots
- Numerical computations for univariate linear models
- Orthogonal least squares methods and their application to non-linear system identification
- Performance monitoring in non-linear adaptive noise cancellation
- Piecewise linear identification of non-linear systems
- Recursive identification of bilinear systems
- Recursive prediction error parameter estimator for non-linear models
- Representations of non-linear systems: the NARMAX model
- Structure detection and model validity tests in the identification of nonlinear systems
This page was built for publication: On-line structure detection and parameter estimation with exponential windowing for nonlinear systems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1352541)
