A runge-kutta MLP neural network based control method for nonlinear MIMO systems

Kemal Ucak

doi:10.1109/ICEEE2019.2019.00043

A runge-kutta MLP neural network based control method for nonlinear MIMO systems

Kemal Ucak^*

^*Corresponding author for this work

Mugla Sıtkı Kocman University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

In this paper, Runge-Kutta MLP based self-adaptive controller (SAC) is proposed for nonlinear multi-input multi output (MIMO) systems. The controller parameters are optimized by considering K-step ahead future behavior of the controlled system. The adjustment mechanism is composed of an online Runge-Kutta identification block which estimates a forward model of the system, an adaptive multi-input multi-output (MIMO) proportional-integral-derivative (PID) controller and an adjustment mechanism realized by separate online Runge-Kutta MLP neural networks to identify the dynamics of each tunable controller parameter. The performance of the introduced adjustment mechanism has been examined on a nonlinear three tank system for different cases, and the obtained results indicate that the RK-MLP-NN based adjustment mechanism and Runge-Kutta model acquire good control and identification performances.

Original language	English
Title of host publication	Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	186-192
Number of pages	7
ISBN (Electronic)	9781728139104
DOIs	https://doi.org/10.1109/ICEEE2019.2019.00043
Publication status	Published - Apr 2019
Externally published	Yes
Event	6th International Conference on Electrical and Electronics Engineering, ICEEE 2019 - Istanbul, Turkey Duration: 16 Apr 2019 → 17 Apr 2019

Publication series

Name	Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019

Conference

Conference	6th International Conference on Electrical and Electronics Engineering, ICEEE 2019
Country/Territory	Turkey
City	Istanbul
Period	16/04/19 → 17/04/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Adaptive controller
MIMO PID type RK MLP controller
Runge-Kutta EKF
Runge-Kutta Identification
Runge-Kutta MLP neural network
Runge-Kutta parameter estimator

Access to Document

10.1109/ICEEE2019.2019.00043

Cite this

Ucak, K. (2019). A runge-kutta MLP neural network based control method for nonlinear MIMO systems. In Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019 (pp. 186-192). Article 8792526 (Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICEEE2019.2019.00043

Ucak, Kemal. / A runge-kutta MLP neural network based control method for nonlinear MIMO systems. Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 186-192 (Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019).

@inproceedings{558c66e8be24465a92decabadaa4fdc2,

title = "A runge-kutta MLP neural network based control method for nonlinear MIMO systems",

abstract = "In this paper, Runge-Kutta MLP based self-adaptive controller (SAC) is proposed for nonlinear multi-input multi output (MIMO) systems. The controller parameters are optimized by considering K-step ahead future behavior of the controlled system. The adjustment mechanism is composed of an online Runge-Kutta identification block which estimates a forward model of the system, an adaptive multi-input multi-output (MIMO) proportional-integral-derivative (PID) controller and an adjustment mechanism realized by separate online Runge-Kutta MLP neural networks to identify the dynamics of each tunable controller parameter. The performance of the introduced adjustment mechanism has been examined on a nonlinear three tank system for different cases, and the obtained results indicate that the RK-MLP-NN based adjustment mechanism and Runge-Kutta model acquire good control and identification performances.",

keywords = "Adaptive controller, MIMO PID type RK MLP controller, Runge-Kutta EKF, Runge-Kutta Identification, Runge-Kutta MLP neural network, Runge-Kutta parameter estimator",

author = "Kemal Ucak",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019 ; Conference date: 16-04-2019 Through 17-04-2019",

year = "2019",

month = apr,

doi = "10.1109/ICEEE2019.2019.00043",

language = "English",

series = "Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "186--192",

booktitle = "Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019",

address = "United States",

}

Ucak, K 2019, A runge-kutta MLP neural network based control method for nonlinear MIMO systems. in Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019., 8792526, Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019, Institute of Electrical and Electronics Engineers Inc., pp. 186-192, 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019, Istanbul, Turkey, 16/04/19. https://doi.org/10.1109/ICEEE2019.2019.00043

A runge-kutta MLP neural network based control method for nonlinear MIMO systems. / Ucak, Kemal.
Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 186-192 8792526 (Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A runge-kutta MLP neural network based control method for nonlinear MIMO systems

AU - Ucak, Kemal

PY - 2019/4

Y1 - 2019/4

N2 - In this paper, Runge-Kutta MLP based self-adaptive controller (SAC) is proposed for nonlinear multi-input multi output (MIMO) systems. The controller parameters are optimized by considering K-step ahead future behavior of the controlled system. The adjustment mechanism is composed of an online Runge-Kutta identification block which estimates a forward model of the system, an adaptive multi-input multi-output (MIMO) proportional-integral-derivative (PID) controller and an adjustment mechanism realized by separate online Runge-Kutta MLP neural networks to identify the dynamics of each tunable controller parameter. The performance of the introduced adjustment mechanism has been examined on a nonlinear three tank system for different cases, and the obtained results indicate that the RK-MLP-NN based adjustment mechanism and Runge-Kutta model acquire good control and identification performances.

AB - In this paper, Runge-Kutta MLP based self-adaptive controller (SAC) is proposed for nonlinear multi-input multi output (MIMO) systems. The controller parameters are optimized by considering K-step ahead future behavior of the controlled system. The adjustment mechanism is composed of an online Runge-Kutta identification block which estimates a forward model of the system, an adaptive multi-input multi-output (MIMO) proportional-integral-derivative (PID) controller and an adjustment mechanism realized by separate online Runge-Kutta MLP neural networks to identify the dynamics of each tunable controller parameter. The performance of the introduced adjustment mechanism has been examined on a nonlinear three tank system for different cases, and the obtained results indicate that the RK-MLP-NN based adjustment mechanism and Runge-Kutta model acquire good control and identification performances.

KW - Adaptive controller

KW - MIMO PID type RK MLP controller

KW - Runge-Kutta EKF

KW - Runge-Kutta Identification

KW - Runge-Kutta MLP neural network

KW - Runge-Kutta parameter estimator

UR - http://www.scopus.com/inward/record.url?scp=85071471502&partnerID=8YFLogxK

U2 - 10.1109/ICEEE2019.2019.00043

DO - 10.1109/ICEEE2019.2019.00043

M3 - Conference contribution

AN - SCOPUS:85071471502

T3 - Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019

SP - 186

EP - 192

BT - Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019

Y2 - 16 April 2019 through 17 April 2019

ER -

Ucak K. A runge-kutta MLP neural network based control method for nonlinear MIMO systems. In Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 186-192. 8792526. (Proceedings - 2019 6th International Conference on Electrical and Electronics Engineering, ICEEE 2019). doi: 10.1109/ICEEE2019.2019.00043

A runge-kutta MLP neural network based control method for nonlinear MIMO systems

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this