Recurrent neural network for solving model predictive control problem in application of four-tank benchmark

Based on model predictive control techniques, this paper presents a discrete-time recurrent neural network for solving four-tank benchmark problem which is reformulated to a convex programming problem. If the weighting matrices are positive definite symmetric, it is shown that the proposed neural ne...

Full description

Saved in:
Bibliographic Details
Published inNeurocomputing (Amsterdam) Vol. 190; pp. 172 - 178
Main Authors Xu, Jing, Li, Chuandong, He, Xing, Huang, Tingwen
Format Journal Article
LanguageEnglish
Published Elsevier B.V 19.05.2016
Subjects
Benchmarking
Discrete-time recurrent neural network
Four-tank benchmark
Globally exponentially stable
Mathematical models
Mathematical programming
Neural networks
Optimization
Predictive control
Recurrent neural networks
Symmetry
Four-tank benchmark
Discrete-time recurrent neural network
Globally exponentially stable
Online AccessGet full text

Cover

More Information
Summary:Based on model predictive control techniques, this paper presents a discrete-time recurrent neural network for solving four-tank benchmark problem which is reformulated to a convex programming problem. If the weighting matrices are positive definite symmetric, it is shown that the proposed neural network is globally exponentially stable and exponentially convergent to the exact optimal solutions. Finally, the experimental results have testified the effectiveness of the proposed approach and shown that the four-tank benchmark problem can be well resolved.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2016.01.020