Prediction and predictive control using feedforward neural network

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28110%2F01%3A00000044" target="_blank" >RIV/70883521:28110/01:00000044 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Prediction and predictive control using feedforward neural network
Original language description
Predictive control using artificial neural network with algorithm backpropagation is presented in the paper. This is the "learning teacher" type of the ANN (artifiicial neural network). Pairs of corresponding values to each other are put at the inputs and outputs in the training phase. Then, the information "overflows" from inputs to outputs and back until it gains the minimal global error per the number of epochs. After teaching, the ANN is able to predict the output value perfectly although the disturbance signal is presented. Neural network is by this way used as nonlinear substitution for very complex systems and controlled output value is predicted. This value is then used for PSD controller adaptive control. The results are presented as simulatedexamples in the environment of MATLAB and Simulink programs.
Czech name
—
Czech description
—

Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year
2001
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proc. 4th International Conference on Prediction and Nonlinear Dynamics
ISBN
80-7318-030-8
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
1-6
Publisher name
UTB
Place of publication
Zlín
Event location
Zlín
Event date
Sep 25, 2001
Type of event by nationality
CST - Celostátní akce
UT code for WoS article
—

Similar results(10)