Studies in Systems, Decision and Control

Computationally Efficient Model Predictive Control Algorithms

A Neural Network Approach

Authors: Lawrynczuk, Maciej

  • Presents recent research in Computationally Efficient Model Predictive Control Algorithms
  • Focuses on a Neural Network Approach for Model Predictive Control
  • Written by an expert in the field
see more benefits

Buy this book

eBook $99.00
price for USA (gross)
  • ISBN 978-3-319-04229-9
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Hardcover $129.00
price for USA
  • ISBN 978-3-319-04228-2
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Softcover $129.00
price for USA
  • Customers within the U.S. and Canada please contact Customer Service at 1-800-777-4643, Latin America please contact us at +1-212-460-1500 (Weekdays 8:30am – 5:30pm ET) to place your order.
  • Due: October 14, 2016
  • ISBN 978-3-319-35021-9
  • Free shipping for individuals worldwide
Rent the ebook  
  • Rental duration: 1 or 6 month
  • low-cost access
  • online reader with highlighting and note-making option
  • can be used across all devices
About this book

This 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 feed forward 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.

Reviews

“This is a monographic work that reflects a large experience in the exploitation of neural network scenarios for Model Predictive Control (MPC). The book provides a rigorous and self-contained material for some key theoretical topics, accompanied by the description of the associated algorithms. … The exposition is suitable for graduate studies or specialized research stages and requires a medium level of training in control systems engineering.” (Octavian Pastravanu, zbMATH 1330.93002, 2016)


Table of contents (9 chapters)

  • MPC Algorithms

    Ławryńczuk, Maciej

    Pages 1-30

  • MPC Algorithms Based on Double-Layer Perceptron Neural Models: the Prototypes

    Ławryńczuk, Maciej

    Pages 31-98

  • MPC Algorithms Based on Neural Hammerstein and Wiener Models

    Ławryńczuk, Maciej

    Pages 99-138

  • MPC Algorithms Based on Neural State-Space Models

    Ławryńczuk, Maciej

    Pages 139-166

  • MPC Algorithms Based on Neural Multi-Models

    Ławryńczuk, Maciej

    Pages 167-188

Buy this book

eBook $99.00
price for USA (gross)
  • ISBN 978-3-319-04229-9
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Hardcover $129.00
price for USA
  • ISBN 978-3-319-04228-2
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Softcover $129.00
price for USA
  • Customers within the U.S. and Canada please contact Customer Service at 1-800-777-4643, Latin America please contact us at +1-212-460-1500 (Weekdays 8:30am – 5:30pm ET) to place your order.
  • Due: October 14, 2016
  • ISBN 978-3-319-35021-9
  • Free shipping for individuals worldwide
Rent the ebook  
  • Rental duration: 1 or 6 month
  • low-cost access
  • online reader with highlighting and note-making option
  • can be used across all devices
Loading...

Recommended for you

Loading...

Bibliographic Information

Bibliographic Information
Book Title
Computationally Efficient Model Predictive Control Algorithms
Book Subtitle
A Neural Network Approach
Authors
Series Title
Studies in Systems, Decision and Control
Series Volume
3
Copyright
2014
Publisher
Springer International Publishing
Copyright Holder
Springer International Publishing Switzerland
eBook ISBN
978-3-319-04229-9
DOI
10.1007/978-3-319-04229-9
Hardcover ISBN
978-3-319-04228-2
Softcover ISBN
978-3-319-35021-9
Series ISSN
2198-4182
Edition Number
1
Number of Pages
XXIV, 316
Number of Illustrations and Tables
87 b/w illustrations
Topics