## Elman neural network for modeling and predictive control of delayed dynamic systems

### Antoni Wysocki , Maciej Ławryńczuk

#### Abstract

The objective of this paper is to present a modified structure and a training algorithm of the recurrent Elman neural network which makes it possible to explicitly take into account the time-delay of the process and a Model Predictive Control (MPC) algorithm for such a network. In MPC the predicted output trajectory is repeatedly linearized on-line along the future input trajectory, which leads to a quadratic optimization problem, nonlinear optimization is not necessary. A strongly nonlinear benchmark process (a simulated neutralization reactor) is considered to show advantages of the modified Elman neural network and the discussed MPC algorithm. The modified neural model is more precise and has a lower number of parameters in comparison with the classical Elman structure. The discussed MPC algorithm with on-line linearization gives similar trajectories as MPC with nonlinear optimization repeated at each sampling instant.
Author
Journal seriesArchives of Control Sciences, ISSN 1230-2384, e-ISSN 2300-2611
Issue year2016
Vol26(LXII)
No1
Pages117-142
Publication size in sheets1.25
Keywords in Englishdynamic models, process control, model predictive control, neural networks, Elman neural network, delayed systems
ASJC Classification2606 Control and Optimization; 2611 Modelling and Simulation; 2207 Control and Systems Engineering
DOIDOI:10.1515/acsc-2016-0007
URL http://www.degruyter.com/dg/viewarticle.fullcontentlink:pdfeventlink/$002fj$002facsc.2016.26.issue-1$002facsc-2016-0007$002facsc-2016-0007.pdf?t:ac=j$002facsc.2016.26.issue-1$002facsc-2016-0007\$002facsc-2016-0007.xml
ProjectDevelopment of methodology of control, decision support and production management. Project leader: Zieliński Cezary, , Phone: 5102, start date 19-05-2015, end date 31-12-2016, 504/02233/1031, Completed
WEiTI Działalność statutowa
Languageen angielski
File
 Wysocki Lawrynczuk acsc-2016-0007-1.pdf 3.23 MB
Score (nominal)15
Score sourcejournalList
ScoreMinisterial score = 15.0, 02-02-2020, ArticleFromJournal
Ministerial score (2013-2016) = 15.0, 02-02-2020, ArticleFromJournal
Publication indicators Scopus Citations = 9; WoS Citations = 5; GS Citations = 9.0; Scopus SNIP (Source Normalised Impact per Paper): 2016 = 0.494; WoS Impact Factor: 2016 = 0.705 (2)
Citation count*13 (2020-09-09)
 Cite