Robust multi-dataset identification with frequency domain decomposition

Mixed Time/Frequency-Domain Based Robust Identification

A new robust identification framework that incorporates both time and frequency domain data is proposed. ¹his framework avoids situations where a good data fit in one domain leads to poor fitting in the other. Abstract—In this paper we propose a new robust identification framework that combines both frequency and time-domain experimental data. The main result of the paper shows that the problem...

Robust Domain Decomposition Preconditioners For

An abstract framework for constructing stable decompositions of the spaces corresponding to general symmetric positive definite problems into “local” subspaces and a global “coarse” space is developed. Particular applications of this abstract framework include practically important problems in porous media applications such as: the scalar elliptic (pressure) equation and the stream function for...

Numerically robust frequency domain identification of multivariable systems

Frequency domain methods are known to suffer from a poor numerical conditioning when the frequency span and/or the model order become large (more than 2 decades and an order more than 20). This numerical problem ruins both the modeling performance and the model order selection capability. This paper presents a modeling approach that leads to (almost) optimal numerical conditioning of the normal...

Robust Frequency Domain ARMA Modelling

In this paper a method for the rejection of frequency domain outliers is proposed. The algorithm is based on the work by Huber on M-estimators and the concept of influence function introduced by Hampel. The estimation takes place in the context of frequency domain continuous-time ARMA modelling, but the method can be also be applied to the discrete time case.

Frequency Domain System Identification