Detail publikačního výsledku

Adaptive Controllers by Using Neural Network Based Identification for Short Sampling Period

Pivoňka, P., Veleba, V., Ošmera, P.

Originální název

Adaptive Controllers by Using Neural Network Based Identification for Short Sampling Period

Anglický název

Adaptive Controllers by Using Neural Network Based Identification for Short Sampling Period

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

The use of short sampling period in adaptive control has not been described properly when controlling the real process by adaptive controller. The new approach to analysis of on-line identification methods based on one-step-ahead prediction clears up their sensitivity to disturbances in control loop. On one hand faster disturbance rejection due to short sampling period can be an advantage but on the other hand it brings us some practical problems. Particularly, quantization error and finite numerical precision of industrial controller must be considered in the real process control. We concentrate our attention on dealing with adverse effects that work on real-time identification of process, especially quantization. It is shown; that a neural network applied to on-line identification process produces more stable solution in the rapid sampling domain.

Anglický abstrakt

The use of short sampling period in adaptive control has not been described properly when controlling the real process by adaptive controller. The new approach to analysis of on-line identification methods based on one-step-ahead prediction clears up their sensitivity to disturbances in control loop. On one hand faster disturbance rejection due to short sampling period can be an advantage but on the other hand it brings us some practical problems. Particularly, quantization error and finite numerical precision of industrial controller must be considered in the real process control. We concentrate our attention on dealing with adverse effects that work on real-time identification of process, especially quantization. It is shown; that a neural network applied to on-line identification process produces more stable solution in the rapid sampling domain.

Klíčová slova

Adaptive Controllers, Neural Networks for Identification, Comparison of Identifications methods, Rapid Sampling Domain

Klíčová slova v angličtině

Adaptive Controllers, Neural Networks for Identification, Comparison of Identifications methods, Rapid Sampling Domain

Autoři

Pivoňka, P., Veleba, V., Ošmera, P.

Rok RIV

2010

Vydáno

05.12.2006

Nakladatel

Nanyang Technological University

Místo

Singapore

ISBN

1-4244-0342-1

Kniha

9th International Conference on Control, Automation, Robotics and Vision, IEEE ICARCV2006

Strany od

521

Strany počet

6

BibTex

@inproceedings{BUT22106,
  author="Petr {Pivoňka} and Václav {Veleba}",
  title="Adaptive Controllers by Using Neural Network Based Identification for Short Sampling Period",
  booktitle="9th International Conference on Control, Automation, Robotics and Vision, IEEE ICARCV2006",
  year="2006",
  pages="6",
  publisher="Nanyang Technological University",
  address="Singapore",
  isbn="1-4244-0342-1"
}