Predictive Optimal Control Strategy for Parallel Models

J. Štecha and V. Havlena (Czech Republic)


Control, Estimation, Parallel models, Mixture distribution.


Predictive control strategy has become a preferred control strategy for a large number of industrial processes. The main advantage for this preference is the ability of this strategy to handle the constraints in an optimal way. Pre dictive control is usually based on linear or nonlinear model of the plant and moving horizon estimation of the model. Sometimes there is no one model of the system, several possible models of the system are used. Bayesian approach enables updating the probability distribution over the set of possible models. The paper presents predictive control strategy for the set of parallel models with given probabilities of individual models.

Important Links:

Go Back