The subject of this thesis is the controllability of interconnected linear systems, where the interconnection parameter are the control variables. The study of accessibility and controllability of bilinear systems is closely related to their system Lie algebra. In 1976, Brockett classified all possible system Lie algebras of linear single-input, single-output (SISO) systems under time-varying output feedback. Here, Brockett's results are generalized to networks of linear systems, where time-varying output feedback is applied according to the interconnection structure of the network. First, networks of linear SISO systems are studied and it is assumed that all interconnections are independently controllable. By calculating the system Lie algebra it is shown that accessibility of the controlled network is equivalent to the strong connectedness of the underlying interconnection graph in case the network has at least three subsystems. Networks with two subsystems are not captured by these proofs. Thus, we give results for this particular case under additional assumption either on the graph structure or on the dynamics of the node systems, which are both not necessary. Additionally, the system Lie algebra is studied in case the interconnection graph is not strongly connected. Then, we show how to adapt the ideas of proof to networks of multi-input, multi-output (MIMO) systems. We generalize results for the system Lie algebra on networks of MIMO systems both under output feedback and under restricted output feedback. Moreover, the case with generalized interconnections is studied, i.e. parallel edges and linear dependencies in the interconnection controls are allowed. The new setting demands to distinguish between homogeneous and heterogeneous networks. With this new setting only sufficient conditions can be found to guarantee accessibility of the controlled network. As an example, networks with Toeplitz interconnection structure are studied. / Gegenstand der Doktorarbeit ist die Steuerbarkeit vernetzter linearer Systeme, in denen Kopplungsparamter die Kontrollvariablen bilden. In 1976 hat Brockett alle möglichen System Lie Algebren klassifiziert, die bei einem single-input, single-output (SISO) System unter zeitvarianter Ausgangsrückführung auftreten können. Dieses Ergebnis wird auf Netzwerke von linearen Systemen, die durch zeitvariante Ausgangsrückführung miteinander gekoppelt sind, verallgemeinert. Als erstes werden hierfür Netzwerke von SISO Systemen unter der Annahme betrachtet, dass alle Kopplungen unabhängig voneinander kontrollierbar sind. Indem man die Lie Algebra berechnet, wird gezeigt, dass Akzessibilität des kontrollierten Netzwerkes äquivalent ist zum starken Zusammenhang des zugrundeliegenden Kopplungsgraphen falls das Netzwerk aus mindestens drei Subsystemen besteht. Der Beweis kann nicht auf Netzwerke mit zwei Subsystemen übertragen werden. Daher werden Resultate für diesen Fall unter Zusatzannahmen angegeben, einmal an die Graphstruktur und einmal an die Dynamik der Subsysteme, wobei beide Annahmen nicht notwendig sind. Zudem wird die Struktur der System Lie Algebra untersucht falls der zugrundeliegende Kopplungsgraph nicht stark zusammenhängend ist. Es werden dieselben Ergebnisse für Netzwerke von multi-input, multi-output (MIMO) Systemen verallgemeinert. Außerdem werden verallgemeinerte Kopplungen betrachtet, d.h. lineare Abhängigkeiten zwischen den Kopplungen und parallele Kopplungen können auftreten. Hierbei muss nun zwischen homogenen und heterogenen Netzwerken unterschieden werden. Die Ergebnisse liefern hinreichende Bedingungen für Akzessibilität. Als Beispiel werden Netzwerke, deren Kopplungsstruktur Toeplitz ist, betrachtet.

This dissertation is dealing with three mathematical areas, namely polynomial matrices over finite fields, linear systems and coding theory. Coprimeness properties of polynomial matrices provide criteria for the reachability and observability of interconnected linear systems. Since time-discrete linear systems over finite fields and convolutional codes are basically the same objects, these results could be transfered to criteria for non-catastrophicity of convolutional codes. We calculate the probability that specially structured polynomial matrices are right prime. In particular, formulas for the number of pairwise coprime polynomials and for the number of mutually left coprime polynomial matrices are calculated. This leads to the probability that a parallel connected linear system is reachable and that a parallel connected convolutional codes is non-catastrophic. Moreover, the corresponding probabilities are calculated for other networks of linear systems and convolutional codes, such as series connection. Furthermore, the probabilities that a convolutional codes is MDP and that a clock code is MDS are approximated. Finally, we consider the probability of finding a solution for a linear network coding problem. / Diese Dissertation beschäftigt sich mit drei Teilgebieten der Mathematik, nämlich Polynommatrizen über endlichen Körpern, linearen Systemen und Faltungscodes. Teilerfremdheitseigenschaften für Polynommatrizen stellen Kriterien für die Erreichbarkeit und Beoabachtbarkeit eines vernetzten linearen Systems zur Verfügung. Da zeit-diskrete lineare dynamische Systems und Faltungscodes im Prinzip diesselben Objekte darstellen, können diese Resultate in Kriterien dafür, dass ein Faltungscode nicht-katastrophal ist, übersetzt werden. Wir berechnen die Wahrscheinlichkeit, dass Polynommatrizen von spezieller Struktur rechtsprim sind. Im Besonderen, werden Formeln für die Anzahl paarweise teilerfremder Polynome sowie für die Anzahl wechselweise links-teilerfremder Polynommatrizen berechnet. Dies führt zu der Wahrscheinlichkeit, dass eine Parallelschaltung linearer Systeme erreichbar ist und dass eine Parallelschaltung von Faltungscodes nicht-katastrophal ist. Zudem werden andere Netzwerke linearen Systeme und von Faltungscodes, wie z.B. Reihenschaltung betrachtet. Des weiteren werden die Wahrscheinlichkeiten, dass ein Faltungscode MDP und dass ein Blockcode MDS ist, approximiert. Schließlich, betrachten wir die Wahrscheinlichkeit, eine Lösung für ein lineares Netzwerk-Kodierungsproblem zu finden.

Kath. Univ., Diss. von Ivan Markovsky--Leuven. / Literaturverz. S. 197 - 202.

University, Diss., 2002--Würzburg.

We present a multi-grid method for a class of structured generalized Lyapunov matrix equations. Such equations need to be solved in each step of the Newton method for algebraic Riccati equations, which arise from linear-quadratic optimal control problems governed by partial differential equations. We prove the rate of convergence of the two-grid method to be bounded independent of the dimension of the problem under certain assumptions. The multi-grid method is based on matrix-matrix multiplications and thus it offers a great potential for a parallelization. The efficiency of the method is demonstrated by numerical experiments.

Zugl.: Clausthal, Techn. Univ., Diss., 2005

After some remarks on the parallel implementation of the Finite Element package FEAP, our realisation of the parallel CG-algorithm is sketched. From a technical point of view, a hierarchical preconditioner with and without additional global crosspoint preconditioning is presented. The numerical properties of this preconditioners are discussed and compared to a Schur-complement-preconditioning, using a wide range of data from computations on technical and academic examples from elasticity.

We investigate the numerical solution of the stable generalized Lyapunov equation via the sign function method. This approach has already been proposed to solve standard Lyapunov equations in several publications. The extension to the generalized case is straightforward. We consider some modifications and discuss how to solve generalized Lyapunov equations with semidefinite constant term for the Cholesky factor. The basic computational tools of the method are basic linear algebra operations that can be implemented efficiently on modern computer architectures and in particular on parallel computers. Hence, a considerable speed-up as compared to the Bartels-Stewart and Hammarling's methods is to be expected. We compare the algorithms by performing a variety of numerical tests.

After some remarks on the parallel implementation of the Finite Element package FEAP, our realisation of the parallel CG-algorithm is sketched. From a technical point of view, a hierarchical preconditioner with and without additional global crosspoint preconditioning is presented. The numerical properties of this preconditioners are discussed and compared to a Schur-complement-preconditioning, using a wide range of data from computations on technical and academic examples from elasticity.

We investigate the numerical solution of the stable generalized Lyapunov equation via the sign function method. This approach has already been proposed to solve standard Lyapunov equations in several publications. The extension to the generalized case is straightforward. We consider some modifications and discuss how to solve generalized Lyapunov equations with semidefinite constant term for the Cholesky factor. The basic computational tools of the method are basic linear algebra operations that can be implemented efficiently on modern computer architectures and in particular on parallel computers. Hence, a considerable speed-up as compared to the Bartels-Stewart and Hammarling's methods is to be expected. We compare the algorithms by performing a variety of numerical tests.