Model-based predictive control of large-scale systems using a neural estimator

• Autorzy: Tzafestas S. , Kyriannakis E. , Anthopoulos Y.
• Języki publikacji: EN

Abstrakty

EN

An approach to the design of discrete-time decentralized controI systems based on model-based predictive controI (MBPC) and neural estimation is proposed. The class of interconnected large-scale systems (LSS) is considered, and a model is used at each controI station to predict the corresponding subsystem output over a long time period. In the case of subsystems with m-step delay information patterns the non-locally available interaction trajectories are estimated by a multi-layer neural network trained on-line with a modified backpropagationtype algortithm. Representative computer simulation results are provided and compared for a set of illustrative examples. The proposed controI scheme shows better performance than the other schemes, and also covers the important case where the subsystems' interactions are nonlinear.

Słowa kluczowe

EN

predictive control; automatics; robotics

PL

sterowanie predykcyjne; automatyka; robotyka

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: Applied Mathematics and Computer Science
• Rocznik: 1998
• Tom: Vol. 8, no 3
• Strony: 585--598
• Opis fizyczny: Bibliogr. 19 poz., rys., wykr.

Twórcy

autor

Tzafestas S.

autor

Kyriannakis E.

autor

Anthopoulos Y.

• Intelligent Robotics and Automation Laboratory, Departament of Electrical and Computer Engineering, National Technical University of Athens, Zographou 15773, Athens, Greece,