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

abstract

• 2016 Elsevier B.V. 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.

authors

• Huang, Tingwen

published proceedings

• NEUROCOMPUTING

author list (cited authors)

• Xu, J., Li, C., He, X., & Huang, T.

citation count

• 26

complete list of authors

• Xu, Jing||Li, Chuandong||He, Xing||Huang, Tingwen

publication date

• May 2016

publisher

• Elsevier  Publisher

published in

• Neurocomputing  Journal

keywords

• Discrete-time Recurrent Neural Network
• Four-tank Benchmark
• Globally Exponentially Stable

Digital Object Identifier (DOI)

• 10.1016/j.neucom.2016.01.020

start page

• 172

end page

• 178

volume

• 190

URL

• http://dx.doi.org/10.1016/j.neucom.2016.01.020