Home > Research > Publications & Outputs > Wiener-neural identification and predictive con...

Research

Associated organisational unit

Links

Text available via DOI:

Keywords

View graph of relations

Wiener-neural identification and predictive control of a more realistic plug-flow tubular reactor

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Wiener-neural identification and predictive control of a more realistic plug-flow tubular reactor. / Arefi, Mohammad M.; Montazeri, A.; Poshtan, J. et al.
In: Chemical Engineering Journal, Vol. 138, No. 1-3, 01.05.2008, p. 274-282.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Arefi, MM, Montazeri, A, Poshtan, J & Jahed-Motlagh, MR 2008, 'Wiener-neural identification and predictive control of a more realistic plug-flow tubular reactor', Chemical Engineering Journal, vol. 138, no. 1-3, pp. 274-282. https://doi.org/10.1016/j.cej.2007.05.044

APA

Arefi, M. M., Montazeri, A., Poshtan, J., & Jahed-Motlagh, M. R. (2008). Wiener-neural identification and predictive control of a more realistic plug-flow tubular reactor. Chemical Engineering Journal, 138(1-3), 274-282. https://doi.org/10.1016/j.cej.2007.05.044

Vancouver

Arefi MM, Montazeri A, Poshtan J, Jahed-Motlagh MR. Wiener-neural identification and predictive control of a more realistic plug-flow tubular reactor. Chemical Engineering Journal. 2008 May 1;138(1-3):274-282. doi: 10.1016/j.cej.2007.05.044

Author

Arefi, Mohammad M. ; Montazeri, A. ; Poshtan, J. et al. / Wiener-neural identification and predictive control of a more realistic plug-flow tubular reactor. In: Chemical Engineering Journal. 2008 ; Vol. 138, No. 1-3. pp. 274-282.

Bibtex

@article{6e287f7191ff4898b60f15915e340329,
title = "Wiener-neural identification and predictive control of a more realistic plug-flow tubular reactor",
abstract = "Some chemical plants such as plug-flow tubular reactors have highly nonlinear behavior. Such processes demand a powerful identification method such as a neural-networks-based Wiener model. In this paper, a plug-flow reactor is simulated in a rather realistic environment by HYSYS, and the obtained data is in connection with MATLAB for identification and control purpose. The process is identified with NN-based Wiener identification method, and two linear and nonlinear model predictive controllers are applied with the ability of rejecting slowly varying unmeasured disturbances. The results are also compared with a common PI controller for temperature control of tubular reactor. Simulation results show that the obtained Wiener model has a good capability to predict the step response of the process. Parameters of both linear and nonlinear model predictive controllers are tuned and the best-obtained results are compared. For this purpose, different operating points are selected to have a wide range of operation for the nonlinear process. It is shown that the nonlinear controller has the fastest damped response in comparison with the other two controllers. ",
keywords = "SYSTEMS, STATE, HYSYS simulator, Wiener-neural identification, nonlinear model predictive control (NMPC), INTERNAL MODEL CONTROL, tubular reactor, NETWORKS",
author = "Arefi, {Mohammad M.} and A. Montazeri and J. Poshtan and Jahed-Motlagh, {M. R.}",
year = "2008",
month = may,
day = "1",
doi = "10.1016/j.cej.2007.05.044",
language = "English",
volume = "138",
pages = "274--282",
journal = "Chemical Engineering Journal",
issn = "1385-8947",
publisher = "Elsevier Science B.V.",
number = "1-3",

}

RIS

TY - JOUR

T1 - Wiener-neural identification and predictive control of a more realistic plug-flow tubular reactor

AU - Arefi, Mohammad M.

AU - Montazeri, A.

AU - Poshtan, J.

AU - Jahed-Motlagh, M. R.

PY - 2008/5/1

Y1 - 2008/5/1

N2 - Some chemical plants such as plug-flow tubular reactors have highly nonlinear behavior. Such processes demand a powerful identification method such as a neural-networks-based Wiener model. In this paper, a plug-flow reactor is simulated in a rather realistic environment by HYSYS, and the obtained data is in connection with MATLAB for identification and control purpose. The process is identified with NN-based Wiener identification method, and two linear and nonlinear model predictive controllers are applied with the ability of rejecting slowly varying unmeasured disturbances. The results are also compared with a common PI controller for temperature control of tubular reactor. Simulation results show that the obtained Wiener model has a good capability to predict the step response of the process. Parameters of both linear and nonlinear model predictive controllers are tuned and the best-obtained results are compared. For this purpose, different operating points are selected to have a wide range of operation for the nonlinear process. It is shown that the nonlinear controller has the fastest damped response in comparison with the other two controllers. 

AB - Some chemical plants such as plug-flow tubular reactors have highly nonlinear behavior. Such processes demand a powerful identification method such as a neural-networks-based Wiener model. In this paper, a plug-flow reactor is simulated in a rather realistic environment by HYSYS, and the obtained data is in connection with MATLAB for identification and control purpose. The process is identified with NN-based Wiener identification method, and two linear and nonlinear model predictive controllers are applied with the ability of rejecting slowly varying unmeasured disturbances. The results are also compared with a common PI controller for temperature control of tubular reactor. Simulation results show that the obtained Wiener model has a good capability to predict the step response of the process. Parameters of both linear and nonlinear model predictive controllers are tuned and the best-obtained results are compared. For this purpose, different operating points are selected to have a wide range of operation for the nonlinear process. It is shown that the nonlinear controller has the fastest damped response in comparison with the other two controllers. 

KW - SYSTEMS

KW - STATE

KW - HYSYS simulator

KW - Wiener-neural identification

KW - nonlinear model predictive control (NMPC)

KW - INTERNAL MODEL CONTROL

KW - tubular reactor

KW - NETWORKS

U2 - 10.1016/j.cej.2007.05.044

DO - 10.1016/j.cej.2007.05.044

M3 - Journal article

VL - 138

SP - 274

EP - 282

JO - Chemical Engineering Journal

JF - Chemical Engineering Journal

SN - 1385-8947

IS - 1-3

ER -