Titlebook: Computationally Efficient Model Predictive Control Algorithms; A Neural Network App Maciej ?awryńczuk Book 2014 Springer International Publ

Jejunum

書目名稱Computationally Efficient Model Predictive Control Algorithms影響因子(影響力)




書目名稱Computationally Efficient Model Predictive Control Algorithms影響因子(影響力)學(xué)科排名




書目名稱Computationally Efficient Model Predictive Control Algorithms網(wǎng)絡(luò)公開度




書目名稱Computationally Efficient Model Predictive Control Algorithms網(wǎng)絡(luò)公開度學(xué)科排名




書目名稱Computationally Efficient Model Predictive Control Algorithms被引頻次




書目名稱Computationally Efficient Model Predictive Control Algorithms被引頻次學(xué)科排名




書目名稱Computationally Efficient Model Predictive Control Algorithms年度引用




書目名稱Computationally Efficient Model Predictive Control Algorithms年度引用學(xué)科排名




書目名稱Computationally Efficient Model Predictive Control Algorithms讀者反饋




書目名稱Computationally Efficient Model Predictive Control Algorithms讀者反饋學(xué)科排名

起來了

MPC Algorithms Based on Double-Layer Perceptron Neural Models: the Prototypes,The “ideal” MPC algorithm with nonlinear optimisation and a few suboptimal MPC algorithms with different on-line linearisation methods are discussed. In order to illustrate properties of the considered MPC algorithms they are compared in two control systems: a yeast fermentation reactor and a high p

不遵守

單獨

MPC Algorithms Based on Neural State-Space Models,s well as of two suboptimal MPC-NPL and MPL-NPLPT algorithms are presented. All the algorithms are considered in two versions: with the state set-point trajectory and with the output set-point trajectory. Simulation results are concerned with the polymerisation reactor introduced in the previous cha

Accomplish

MPC Algorithms Based on Neural Multi-Models,hapter is concerned with MPC algorithms based on neural multi-models. The classical dynamic models, both input-output and state-space structures, are used recurrently in MPC algorithms as they calculate the predictions for the whole prediction horizon. In such a case the prediction error is propagat

陳列

MPC Algorithms with Neural Approximation,arisation. A specially designed neural network (the neural approximator) approximates on-line the step-response coefficients of the model linearised for the current operating point of the process (such an approach is used in the MPC-NPL-NA and DMC-NA algorithms which are extensions of the MPC-NPL an

陳列

Stability and Robustness of MPC Algorithms,ity and robustness are reviewed with a view to using them in the suboptimal MPC algorithms with on-line linearisation. A modification of the dual-mode MPC strategy is thoroughly discussed which leads to the suboptimal MPC algorithm with theoretically guaranteed stability. Finally, a modification of

微生物

Cooperation between MPC Algorithms and Set-Point Optimisation Algorithms,first, the classical multi-layer control system structure is discussed, the main disadvantage of which is the necessity of on-line nonlinear optimisation. Three control structures with on-line linearisation for set-point optimisation are presented next: the multi-layer structure with steady-state ta

engrave

Flat-Feet