System identification: theory for the user
System identification: theory for the user
Grey-box modelling and identification using physical knowledge and Bayesian techniques
Automatica (Journal of IFAC)
Fault diagnosis of machines via parameter estimation and knowledge processing: tutorial paper
Automatica (Journal of IFAC) - Special section on fault detection, supervision and safety for technical processes
On Tikhonov regularization, bias and variance in nonlinear system identification
Automatica (Journal of IFAC)
Hi-index | 0.00 |
This article deals with the estimation of physical parameters. This estimation is performed using an Output Error algorithm based on nonlinear optimization. Output Error techniques permit to obtain unbiased estimation and can be applied either to linear systems or nonlinear ones. The usual quadratic criterion is modified in order to include prior physical knowledge. A deterministic interpretation of this criterion is given in the linear parameter case and in the nonlinear parameter one. Estimation is also improved using direct optimization by physical parameters, owing to a generalized formulation of sensitivity functions. A real electrical engineering example illustrates the efficiency of this methodology.