Inversion of Fuzzy Neural Networks for the Reduction of Noise in the Control Loop for Automotive Applications

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Standard

Inversion of Fuzzy Neural Networks for the Reduction of Noise in the Control Loop for Automotive Applications. / Nentwig, M.; Mercorelli, Paolo.
in: JAMRIS, Journal of Automation, Mobile Robotics & Intelligent Systems, Jahrgang 3, Nr. 3, 2009, S. 83-89.

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Harvard

APA

Vancouver

Bibtex

@article{f0069ea0ac8543b8add98a97bc6b4eba,
title = "Inversion of Fuzzy Neural Networks for the Reduction of Noise in the Control Loop for Automotive Applications",
abstract = "A robust throttle valve control has been an attractive problem since throttle bywire systems were established in the mid-nineties. Control strategies often use afeed-forward controller which use an inverse model; however, mathematical model inversions imply a high order of differentiation of the state variables resulting in noise effects. In general, neural networks are a very effective and popular tool for modeling. The inversion of a neural network makes it possible to use these networks in control problem schemes. This paper presents a control strategy based upon an inversion of a feed-forward trained local linear model tree. The local linear model tree is realized through a fuzzy neural network. Simulated results from real data measurements are presented, and two control loops are explicitly compared.",
keywords = "Engineering",
author = "M. Nentwig and Paolo Mercorelli",
year = "2009",
language = "English",
volume = "3",
pages = "83--89",
journal = "JAMRIS, Journal of Automation, Mobile Robotics & Intelligent Systems",
issn = "1897-8649",
publisher = "Industrial Research Institute for Automation and Measurements",
number = "3",

}

RIS

TY - JOUR

T1 - Inversion of Fuzzy Neural Networks for the Reduction of Noise in the Control Loop for Automotive Applications

AU - Nentwig, M.

AU - Mercorelli, Paolo

PY - 2009

Y1 - 2009

N2 - A robust throttle valve control has been an attractive problem since throttle bywire systems were established in the mid-nineties. Control strategies often use afeed-forward controller which use an inverse model; however, mathematical model inversions imply a high order of differentiation of the state variables resulting in noise effects. In general, neural networks are a very effective and popular tool for modeling. The inversion of a neural network makes it possible to use these networks in control problem schemes. This paper presents a control strategy based upon an inversion of a feed-forward trained local linear model tree. The local linear model tree is realized through a fuzzy neural network. Simulated results from real data measurements are presented, and two control loops are explicitly compared.

AB - A robust throttle valve control has been an attractive problem since throttle bywire systems were established in the mid-nineties. Control strategies often use afeed-forward controller which use an inverse model; however, mathematical model inversions imply a high order of differentiation of the state variables resulting in noise effects. In general, neural networks are a very effective and popular tool for modeling. The inversion of a neural network makes it possible to use these networks in control problem schemes. This paper presents a control strategy based upon an inversion of a feed-forward trained local linear model tree. The local linear model tree is realized through a fuzzy neural network. Simulated results from real data measurements are presented, and two control loops are explicitly compared.

KW - Engineering

M3 - Journal articles

VL - 3

SP - 83

EP - 89

JO - JAMRIS, Journal of Automation, Mobile Robotics & Intelligent Systems

JF - JAMRIS, Journal of Automation, Mobile Robotics & Intelligent Systems

SN - 1897-8649

IS - 3

ER -

Dokumente

Links