State-space control of nonlinear systems identified by ANARX and Neural Network based SANARX models

Vassiljeva, Kristina; Petlenkov, Eduard; Belikov, Juri

doi:10.1109/ijcnn.2010.5596581

Cited by 11 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, ANARX model (3) can be directly represented via state equation. The latter can be used, for example, to design state controller Vassiljeva et al [2010].…”

Section: Preliminariesmentioning

confidence: 99%

Model based control of a water tank system

Belikov

Petlenkov

2014

IFAC Proceedings Volumes

View full text Add to dashboard Cite

“…In addition, ANARX model (3) can be directly represented via state equation. The latter can be used, for example, to design state controller Vassiljeva et al [2010].…”

Section: Preliminariesmentioning

confidence: 99%

Model based control of a water tank system

Belikov

Petlenkov

2014

IFAC Proceedings Volumes

View full text Add to dashboard Cite

“…We treat this as our unknown dynamic system, which is approximated by the NN-based Simplified Additive Nonlinear Autoregressive eXogenous (SANARX) model [9], [10]. To obtain such a model, system (1) was simulated with uniformed random signal.…”

Section: Numerical Examplementioning

confidence: 99%

Automated neural network model selection algorithm for feedback linearization based control

Vassiljeva

Petlenkov

Belikov³

2010

2010 12th Biennial Baltic Electronics Conference

Self Cite

View full text Add to dashboard Cite

For the best model identification a set of neural networks (NNs) must be trained. First of all it is necessary to obtain the optimal structure of the NN. In addition a good choice of the initial values of the NN parameters can be of tremendous help in a successful control application. Further fit of the model is evaluated using several control criteria, and the optimal among them is selected. This article presents an automated NN model selection method for control based on feedback linearization.

show abstract

“…As an alternative, a rather simple and effective architecture can be considered. It's the so-called ANARX-model (Additive NARX) that has the form [12,13]…”

Section: Introductionmentioning

confidence: 99%

“…Authors [12,13] used elementary Rosenblatt perceptrons with sigmoidal activation functions as such nodes. The ANARX-model provided high forecasting quality, but generally speaking it requires a large number of nodes in its architecture [14].…”

Section: Introductionmentioning

confidence: 99%