Identification of dynamic networks operating in the presence of algebraic loops

When identifying all modules in a dynamic network it is natural to treat all node variables in a symmetric way, i.e. not having pre-assigned roles of ’inputs’ and ’outputs’. In a prediction error setting this implies that every node signal is predicted on the basis of all other nodes. A usual restriction in direct and joint-io methods for dynamic network and closed-loop identification is the need for a delay to be present in every loop (absence of algebraic loops).

Publication year:

Identifiability of dynamic networks with part of the nodes noise-free

In dynamic network identication a major goal is to uniquely identify the topology and dynamic links between the measured node variables. It is common practice to assume that process noises aect every output in multivariable system identication, and every node in dynamic networks with a full rank noise process. For many practical situations this assumption might be overly strong. This leads to the question of how to handle situations where the process noise is not full rank, i.e. when the number of white noise processes driving the network is strictly smaller than the number of nodes.

Publication year:

Topology detection in dynamic networks

picture: 

Poster on topology detection

Publication year:

Type:

Are model and predictor filters equivalent?

picture: 

Poster on identifiability in dynamic networks.

Publication year:

Type:

Noise-free signals make identification more difficult

In system identification the amount of information present in data is important. In this abstract it is argued that the absence of noise can lead to problems with the information content, and the identifiability of models.

Publication year:

System identification in dynamic networks

1 page abstract about system identification in dynamic networks and topology detection.

Publication year:

Topology detection in dynamic networks - MSc thesis

Dynamic networks are a way of describing related physical quantities as variables that dynamically influence each other. Models of dynamic networks can potentially be used in many branches of science such as engineering, finance, biology etc. Obtaining a mathematical model of the dynamics in a network, or even detecting the topology is challenging. Topology detection has been investigated by quite some authors, but a method that satisfies all desires has not been found.

Type:

Publication year:

Model-Based Predictive Control Scheme for Cost Optimization and Balancing Services for Supermarket Refrigeration Systems

A new formulation of model predictive control for supermarket refrigeration systems is proposed to facilitate the regulatory power services as well as energy cost optimization of such systems in the smart grid. Nonlinear dynamics existed in large-scale refrigeration plants challenges the predictive control design. It is however shown that taking into account the knowledge of different time scales in the dynamical subsystems makes possible a linear formulation of a centralized predictive controller.

Publication year:

Identifiability in dynamic network identification

Dynamic networks are structured interconnections of dynamical systems driven by external excitation and disturbance signals. We develop the notion of network identifiability, a property of a parameterized model set that ensures that module dynamics are uniquely related to the filters that specify the one-step-ahead predictors of all node signals in the network. It can be used to specify which presence of excitation signals will result in a unique representation of the network dynamics in a particular network model parametrization.

Publication year:

Website was created

As a first serious post I want to state that the website was created and that content is being added. Content consists of official publications I make, and this blog which will be filled with all my thoughts that I want to write down.

Subscribe to Weerts' laboratory RSS