000 03986nam a22004935i 4500
001 978-3-319-04229-9
003 DE-He213
005 20200421111653.0
007 cr nn 008mamaa
008 140124s2014 gw | s |||| 0|eng d
020 _a9783319042299
_9978-3-319-04229-9
024 7 _a10.1007/978-3-319-04229-9
_2doi
050 4 _aQ342
072 7 _aUYQ
_2bicssc
072 7 _aCOM004000
_2bisacsh
082 0 4 _a006.3
_223
100 1 _a�awryńczuk, Maciej.
_eauthor.
245 1 0 _aComputationally Efficient Model Predictive Control Algorithms
_h[electronic resource] :
_bA Neural Network Approach /
_cby Maciej �awryńczuk.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2014.
300 _aXXIV, 316 p. 87 illus.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aStudies in Systems, Decision and Control,
_x2198-4182 ;
_v3
505 0 _aMPC Algorithms -- MPC Algorithms Based on Double-Layer Perceptron Neural Models: the Prototypes -- MPC Algorithms Based on Neural Hammerstein and Wiener Models -- MPC Algorithms Based on Neural State-Space Models -- MPC Algorithms Based on Neural Multi-Models -- MPC Algorithms with Neural Approximation -- Stability and Robustness of MPC Algorithms -- Cooperation Between MPC Algorithms and Set-Point Optimisation Algorithms.
520 _aThis book thoroughly discusses computationally efficient (suboptimal) Model Predictive Control (MPC) techniques based on neural models. The subjects treated include: �         A few types of suboptimal MPC algorithms in which a linear approximation of the model or of the predicted trajectory is successively calculated on-line and used for prediction. �         Implementation details of the MPC algorithms for feedforward perceptron neural models, neural Hammerstein models, neural Wiener models and state-space neural models. �         The MPC algorithms based on neural multi-models (inspired by the idea of predictive control). �         The MPC algorithms with neural approximation with no on-line linearization. �         The MPC algorithms with guaranteed stability and robustness. �         Cooperation between the MPC algorithms and set-point optimization. Thanks to linearization (or neural approximation), the presented suboptimal algorithms do not require demanding on-line nonlinear optimization. The presented simulation results demonstrate high accuracy and computational efficiency of the algorithms. For a few representative nonlinear benchmark processes, such as chemical reactors and a distillation column, for which the classical MPC algorithms based on linear models do not work properly, the trajectories obtained in the suboptimal MPC algorithms are very similar to those given by the ``ideal'' MPC algorithm with on-line nonlinear optimization repeated at each sampling instant. At the same time, the suboptimal MPC algorithms are significantly less computationally demanding.
650 0 _aEngineering.
650 0 _aArtificial intelligence.
650 0 _aComputational intelligence.
650 0 _aControl engineering.
650 1 4 _aEngineering.
650 2 4 _aComputational Intelligence.
650 2 4 _aControl.
650 2 4 _aArtificial Intelligence (incl. Robotics).
710 2 _aSpringerLink (Online service)
773 0 _tSpringer eBooks
776 0 8 _iPrinted edition:
_z9783319042282
830 0 _aStudies in Systems, Decision and Control,
_x2198-4182 ;
_v3
856 4 0 _uhttp://dx.doi.org/10.1007/978-3-319-04229-9
912 _aZDB-2-ENG
942 _cEBK
999 _c54557
_d54557