Open AccessLanczos Model Reduction for Switched Linear Systems
Author(s) -
Kouki Mohamed,
Mehdi Abbes,
Abdelkader Mami
Publication year - 2020
Publication title -
international journal of computers and communications
Language(s) - English
Resource type - Journals
ISSN - 2074-1294
DOI - 10.46300/91013.2020.14.6
Subject(s) - krylov subspace , lanczos resampling , reduction (mathematics) , model order reduction , linear system , lanczos algorithm , generalized minimal residual method , moment (physics) , mathematics , lti system theory , computer science , stability (learning theory) , mathematical optimization , algorithm , control theory (sociology) , eigenvalues and eigenvectors , physics , mathematical analysis , projection (relational algebra) , geometry , control (management) , quantum mechanics , classical mechanics , machine learning , artificial intelligence
In today the methods reduction of large-scale linear time invariant and complexe systems are very many, the best choices today is the used of the krylov subspace methods based on moment matching. As hybrid dynamical systems are of rising spread and complexity, for these reasons, we present in this paper two model reduction methods applied to linear switched system. Which is an important class of hybrid and non linear system. Tow methods for reduction systems are present. In first part we present the modified non symmetric Lanczos algorithm, which is numerically efficient and applicable of any order. In second part we present the modified global lanczos algorithm, it is also numerically efficient, applicable of any order and having a best numerical stability. The effectivity and suitability of these new methods is illustrated by one simulation example.