Observer based iterative neural network model inversion

A. Várkonyi-Kóczy, András Rövid

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Recently model based techniques have become wide spread in solving measurement, control, identification, etc. problems. For measurement data evaluation and for controller design also the so called inverse models are of considerable interest. In this paper a technique to perform neural network inversion is introduced. For discrete time inputs the proposed method provides good performance if the iterative inversion is fast enough compared to system variations, i.e. the iteration is convergent within the sampling period applied. The proposed method can be considered also as a simple nonlinear state observer, which reconstructs the selected inputs of the neural network from its outputs.

Original languageEnglish
Title of host publicationIEEE International Conference on Fuzzy Systems
EditorsR. Krishnapuram, N. Pal
Pages402-407
Number of pages6
Publication statusPublished - 2005
EventIEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2005 - Reno, NV, United States
Duration: May 22 2005May 25 2005

Other

OtherIEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2005
CountryUnited States
CityReno, NV
Period5/22/055/25/05

Fingerprint

Neural networks
Sampling
Controllers

ASJC Scopus subject areas

  • Software
  • Safety, Risk, Reliability and Quality
  • Chemical Health and Safety

Cite this

Várkonyi-Kóczy, A., & Rövid, A. (2005). Observer based iterative neural network model inversion. In R. Krishnapuram, & N. Pal (Eds.), IEEE International Conference on Fuzzy Systems (pp. 402-407)

Observer based iterative neural network model inversion. / Várkonyi-Kóczy, A.; Rövid, András.

IEEE International Conference on Fuzzy Systems. ed. / R. Krishnapuram; N. Pal. 2005. p. 402-407.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Várkonyi-Kóczy, A & Rövid, A 2005, Observer based iterative neural network model inversion. in R Krishnapuram & N Pal (eds), IEEE International Conference on Fuzzy Systems. pp. 402-407, IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2005, Reno, NV, United States, 5/22/05.
Várkonyi-Kóczy A, Rövid A. Observer based iterative neural network model inversion. In Krishnapuram R, Pal N, editors, IEEE International Conference on Fuzzy Systems. 2005. p. 402-407
Várkonyi-Kóczy, A. ; Rövid, András. / Observer based iterative neural network model inversion. IEEE International Conference on Fuzzy Systems. editor / R. Krishnapuram ; N. Pal. 2005. pp. 402-407
@inproceedings{c7d00838af724e4dbceabf344188ff76,
title = "Observer based iterative neural network model inversion",
abstract = "Recently model based techniques have become wide spread in solving measurement, control, identification, etc. problems. For measurement data evaluation and for controller design also the so called inverse models are of considerable interest. In this paper a technique to perform neural network inversion is introduced. For discrete time inputs the proposed method provides good performance if the iterative inversion is fast enough compared to system variations, i.e. the iteration is convergent within the sampling period applied. The proposed method can be considered also as a simple nonlinear state observer, which reconstructs the selected inputs of the neural network from its outputs.",
author = "A. V{\'a}rkonyi-K{\'o}czy and Andr{\'a}s R{\"o}vid",
year = "2005",
language = "English",
pages = "402--407",
editor = "R. Krishnapuram and N. Pal",
booktitle = "IEEE International Conference on Fuzzy Systems",

}

TY - GEN

T1 - Observer based iterative neural network model inversion

AU - Várkonyi-Kóczy, A.

AU - Rövid, András

PY - 2005

Y1 - 2005

N2 - Recently model based techniques have become wide spread in solving measurement, control, identification, etc. problems. For measurement data evaluation and for controller design also the so called inverse models are of considerable interest. In this paper a technique to perform neural network inversion is introduced. For discrete time inputs the proposed method provides good performance if the iterative inversion is fast enough compared to system variations, i.e. the iteration is convergent within the sampling period applied. The proposed method can be considered also as a simple nonlinear state observer, which reconstructs the selected inputs of the neural network from its outputs.

AB - Recently model based techniques have become wide spread in solving measurement, control, identification, etc. problems. For measurement data evaluation and for controller design also the so called inverse models are of considerable interest. In this paper a technique to perform neural network inversion is introduced. For discrete time inputs the proposed method provides good performance if the iterative inversion is fast enough compared to system variations, i.e. the iteration is convergent within the sampling period applied. The proposed method can be considered also as a simple nonlinear state observer, which reconstructs the selected inputs of the neural network from its outputs.

UR - http://www.scopus.com/inward/record.url?scp=23944449886&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=23944449886&partnerID=8YFLogxK

M3 - Conference contribution

SP - 402

EP - 407

BT - IEEE International Conference on Fuzzy Systems

A2 - Krishnapuram, R.

A2 - Pal, N.

ER -