Identification of Nonlinear Systems Using Neural Networks and Polynomial Models: A Block-Oriented Approach (Lecture Notes in Control and Information Sciences)
Efficient model predictive control algorithm with fuzzy approximations of nonlinear models
ICANNGA'09 Proceedings of the 9th international conference on Adaptive and natural computing algorithms
On prediction generation in efficient MPC algorithms based on fuzzy hammerstein models
ICAISC'10 Proceedings of the 10th international conference on Artificial intelligence and soft computing: Part I
Fuzzy Modeling and Control
A refactoring method for cache-efficient swarm intelligence algorithms
Information Sciences: an International Journal
| Hi-index | 0.00 |
An advanced prediction method utilizing fuzzy Hammerstein models is proposed in the paper. The prediction has such a form that the Model Predictive Control (MPC) algorithm using it is formulated as a numerically efficient quadratic optimization problem. The prediction is described by relatively simple analytical formulas. The key feature of the proposed prediction method is the usage of values of the future control changes which were derived by the MPC algorithm in the last iteration. Thanks to such an approach the MPC algorithm using the proposed method of prediction offers very good control performance. It is demonstrated in the example control system of a nonlinear control plant with significant time delay that the obtained responses are much better than those obtained in the standard MPC algorithm based on a linear process model.