Detail publikace

Generalized Predictive Control with Adaptive Model Based on Neural Networks

Originální název

Generalized Predictive Control with Adaptive Model Based on Neural Networks

Anglický název

Generalized Predictive Control with Adaptive Model Based on Neural Networks

Jazyk

en

Originální abstrakt

Generalized Predictive Control (GPC) is well known control algorithm. If we put together predictive strategy of GPC and Neural Networks model, which is adaptive, then we obtain new controller with many advantages. Neural model is able to observe system changes and adapt itself, therefore regulator based on this model is adaptive. Algorithm was implemented in MATLAB-Simulink with aspect of future implementation to Programmable Logic Controller (PLC) B&R. It was tested on mathematical and physical models in soft-real-time realization. Predictive controller in comparison with classical discrete PID controller and it’s advantages and disadvantages are shown.

Anglický abstrakt

Generalized Predictive Control (GPC) is well known control algorithm. If we put together predictive strategy of GPC and Neural Networks model, which is adaptive, then we obtain new controller with many advantages. Neural model is able to observe system changes and adapt itself, therefore regulator based on this model is adaptive. Algorithm was implemented in MATLAB-Simulink with aspect of future implementation to Programmable Logic Controller (PLC) B&R. It was tested on mathematical and physical models in soft-real-time realization. Predictive controller in comparison with classical discrete PID controller and it’s advantages and disadvantages are shown.

BibTex 


@article{BUT46530,
  author="Petr {Pivoňka} and Petr {Nepevný}",
  title="Generalized Predictive Control with Adaptive Model Based on Neural Networks",
  annote="Generalized Predictive Control (GPC) is well known control algorithm. If we put together predictive strategy of GPC and Neural Networks model, which is adaptive, then we obtain new controller with many advantages. Neural model is able to observe system changes and adapt itself, therefore regulator based on this model is adaptive. Algorithm was implemented in MATLAB-Simulink with aspect of future implementation to Programmable Logic Controller (PLC) B&R. It was tested on mathematical and physical models in soft-real-time realization. Predictive controller in comparison with classical discrete PID controller and it’s advantages and disadvantages are shown.",
  chapter="46530",
  journal="WSEAS Transactions on Circuits",
  number="4",
  volume="4",
  year="2005",
  month="may",
  pages="385",
  type="journal article - other"
}