Detail publikace

Hot-Air Tunel Control Using Multi-Dimensional Predictive Controller Based on Neural Network Model

Nepevný, P., Pivoňka, P.

Originální název

Hot-Air Tunel Control Using Multi-Dimensional Predictive Controller Based on Neural Network Model

Anglický název

Hot-Air Tunel Control Using Multi-Dimensional Predictive Controller Based on Neural Network Model

Jazyk

en

Originální abstrakt

This paper presents using of a multi-dimensional model predictive controller for hot-air tunnel control. Two quantities of hot-air tunnel are controlled – the air flow and the temperature. Mode predictive controller is a kind of optimal controller based on model. Model predicts future system output, which is used for finding an optimal control action. We used a feed-forward neural network model with backpropagation learning algorithm. Obtained controller is adaptive, because the neural network model is able to observe system changes and adapt itself. The algorithm was implemented in MATLAB-Simulink and tested on a physical model. Communication between PC and hot-air tunnel was provided by PLC (connected via Ethernet.

Anglický abstrakt

This paper presents using of a multi-dimensional model predictive controller for hot-air tunnel control. Two quantities of hot-air tunnel are controlled – the air flow and the temperature. Mode predictive controller is a kind of optimal controller based on model. Model predicts future system output, which is used for finding an optimal control action. We used a feed-forward neural network model with backpropagation learning algorithm. Obtained controller is adaptive, because the neural network model is able to observe system changes and adapt itself. The algorithm was implemented in MATLAB-Simulink and tested on a physical model. Communication between PC and hot-air tunnel was provided by PLC (connected via Ethernet.

Dokumenty

BibTex


@inproceedings{BUT24156,
  author="Petr {Nepevný} and Petr {Pivoňka}",
  title="Hot-Air Tunel Control Using Multi-Dimensional Predictive Controller Based on Neural Network Model",
  annote="This paper presents using of a multi-dimensional
model predictive controller for hot-air tunnel control. Two quantities of hot-air tunnel are controlled – the air flow and the temperature. Mode predictive controller is a kind of optimal
controller based on model. Model predicts future system output, which is used for finding an optimal control action. We used a feed-forward neural network model with backpropagation
learning algorithm. Obtained controller is adaptive, because the neural network model is able to observe system changes and adapt itself. The algorithm was implemented in MATLAB-Simulink and tested on a physical model. Communication between PC and hot-air tunnel was provided by PLC (connected via Ethernet.",
  address="DAAAM International Vienna",
  booktitle="Anals of DAAAM for 2006 & Proceedings",
  chapter="24156",
  institution="DAAAM International Vienna",
  year="2006",
  month="november",
  pages="267",
  publisher="DAAAM International Vienna",
  type="conference paper"
}