Detail publikace

Using of Neural Network Based Identification for Short Sampling Period in Adaptive Control

Originální název

Using of Neural Network Based Identification for Short Sampling Period in Adaptive Control

Anglický název

Using of Neural Network Based Identification for Short Sampling Period in Adaptive Control

Jazyk

en

Originální abstrakt

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 and explain why should be neural network based identification better then classical by using of short sampling period. The use of short sampling period in adaptive control has not been described properly when controlling the real process by adaptive controller. 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.

Anglický abstrakt

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 and explain why should be neural network based identification better then classical by using of short sampling period. The use of short sampling period in adaptive control has not been described properly when controlling the real process by adaptive controller. 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.

BibTex


@inproceedings{BUT28312,
  author="Petr {Pivoňka} and Václav {Veleba} and Pavel {Ošmera}",
  title="Using of Neural Network Based Identification for Short Sampling Period in Adaptive Control",
  annote="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 and explain why should be neural network based identification better then classical by using of short sampling period. The use of short sampling period in adaptive control has not been described properly when controlling the real process by adaptive controller. 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.",
  address="WSEAS",
  booktitle="Systems Theory and Applications",
  chapter="28312",
  edition="Vol. 2.",
  institution="WSEAS",
  year="2007",
  month="july",
  pages="217--222",
  publisher="WSEAS",
  type="conference paper"
}