Dynamic neural network-based system identification of a pressurized water reactor

Amine Naimi; Jiamei M. Deng; Altahhan Abdulrahman; Vineet Vajpayee; Victor Becerra; Nils Bausch

doi:10.1109/ICCMA51325.2020.9301483

Dynamic neural network-based system identification of a pressurized water reactor

Amine Naimi, Jiamei M. Deng, Altahhan Abdulrahman, Vineet Vajpayee, Victor Becerra, Nils Bausch

Leeds Beckett University

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

108 Downloads (Pure)

Abstract

This work presents a dynamic neural network-based (DNN) system identification approach for a pressurized water nuclear reactor. The presented empirical modelling approach describes the DNN structure using differential equations. Local optimization algorithms based on unconstrained Quasi-Newton and interior point approaches are used in the identification process. The efficacy of the proposed approach has been demonstrated by identifying a nuclear reactor core coupled with thermal-hydraulics. DNNs are employed to train the structure and validate it using the nuclear reactor data. The simulation results show that the neural network identified model is sufficiently able to capture the dynamics of the nuclear reactor and it is suitably able to approximate the complex nuclear reactor system.

Original language	English
Title of host publication	Proceedings of the 8th International Conference on Control, Mechatronics and Automation, (ICCMA 2020)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	100-104
Number of pages	5
ISBN (Electronic)	978-1-7281-9210-9, 978-1-7281-9209-3
ISBN (Print)	978-1-7281-9211-6
DOIs	https://doi.org/10.1109/ICCMA51325.2020.9301483
Publication status	Published - 29 Dec 2020
Event	The 8th International Conference on Control, Mechatronics and Automation - Moscow, Russian Federation Duration: 6 Nov 2020 → 8 Nov 2020 http://www.iccma.org/

Conference

Conference	The 8th International Conference on Control, Mechatronics and Automation
Abbreviated title	ICCMA 2020
Country/Territory	Russian Federation
City	Moscow
Period	6/11/20 → 8/11/20
Internet address	http://www.iccma.org/

Keywords

RCUK
EPSRC
EP/R021961/1
EP/R022062/1
EP/M018717/1

Access to Document

10.1109/ICCMA51325.2020.9301483

ICCMA20_DNN
© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 798 KB

Fault Tolerant Control for Increased Safety and Security of Nuclear Power Plants
Becerra, V. & Bausch, N.
Engineering and Physical Sciences Research Council
1/12/18 → 28/02/22
Project: Research

Cite this

Naimi, A., Deng, J. M., Abdulrahman, A., Vajpayee, V., Becerra, V., & Bausch, N. (2020). Dynamic neural network-based system identification of a pressurized water reactor. In Proceedings of the 8th International Conference on Control, Mechatronics and Automation, (ICCMA 2020) (pp. 100-104). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCMA51325.2020.9301483

@inproceedings{1eb7e33b58bf4706914a40a83e5d1290,

title = "Dynamic neural network-based system identification of a pressurized water reactor",

abstract = "This work presents a dynamic neural network-based (DNN) system identification approach for a pressurized water nuclear reactor. The presented empirical modelling approach describes the DNN structure using differential equations. Local optimization algorithms based on unconstrained Quasi-Newton and interior point approaches are used in the identification process. The efficacy of the proposed approach has been demonstrated by identifying a nuclear reactor core coupled with thermal-hydraulics. DNNs are employed to train the structure and validate it using the nuclear reactor data. The simulation results show that the neural network identified model is sufficiently able to capture the dynamics of the nuclear reactor and it is suitably able to approximate the complex nuclear reactor system.",

keywords = "RCUK, EPSRC, EP/R021961/1, EP/R022062/1, EP/M018717/1",

author = "Amine Naimi and Deng, {Jiamei M.} and Altahhan Abdulrahman and Vineet Vajpayee and Victor Becerra and Nils Bausch",

year = "2020",

month = dec,

day = "29",

doi = "10.1109/ICCMA51325.2020.9301483",

language = "English",

isbn = "978-1-7281-9211-6",

pages = "100--104",

booktitle = "Proceedings of the 8th International Conference on Control, Mechatronics and Automation, (ICCMA 2020)",

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

address = "United States",

note = "The 8th International Conference on Control, Mechatronics and Automation, ICCMA 2020 ; Conference date: 06-11-2020 Through 08-11-2020",

url = "http://www.iccma.org/",

}

Naimi, A, Deng, JM, Abdulrahman, A, Vajpayee, V, Becerra, V & Bausch, N 2020, Dynamic neural network-based system identification of a pressurized water reactor. in Proceedings of the 8th International Conference on Control, Mechatronics and Automation, (ICCMA 2020). Institute of Electrical and Electronics Engineers Inc., pp. 100-104, The 8th International Conference on Control, Mechatronics and Automation, Moscow, Russian Federation, 6/11/20. https://doi.org/10.1109/ICCMA51325.2020.9301483

Dynamic neural network-based system identification of a pressurized water reactor. / Naimi, Amine; Deng, Jiamei M.; Abdulrahman, Altahhan et al.
Proceedings of the 8th International Conference on Control, Mechatronics and Automation, (ICCMA 2020). Institute of Electrical and Electronics Engineers Inc., 2020. p. 100-104.

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

TY - GEN

T1 - Dynamic neural network-based system identification of a pressurized water reactor

AU - Naimi, Amine

AU - Deng, Jiamei M.

AU - Abdulrahman, Altahhan

AU - Vajpayee, Vineet

AU - Becerra, Victor

AU - Bausch, Nils

PY - 2020/12/29

Y1 - 2020/12/29

N2 - This work presents a dynamic neural network-based (DNN) system identification approach for a pressurized water nuclear reactor. The presented empirical modelling approach describes the DNN structure using differential equations. Local optimization algorithms based on unconstrained Quasi-Newton and interior point approaches are used in the identification process. The efficacy of the proposed approach has been demonstrated by identifying a nuclear reactor core coupled with thermal-hydraulics. DNNs are employed to train the structure and validate it using the nuclear reactor data. The simulation results show that the neural network identified model is sufficiently able to capture the dynamics of the nuclear reactor and it is suitably able to approximate the complex nuclear reactor system.

AB - This work presents a dynamic neural network-based (DNN) system identification approach for a pressurized water nuclear reactor. The presented empirical modelling approach describes the DNN structure using differential equations. Local optimization algorithms based on unconstrained Quasi-Newton and interior point approaches are used in the identification process. The efficacy of the proposed approach has been demonstrated by identifying a nuclear reactor core coupled with thermal-hydraulics. DNNs are employed to train the structure and validate it using the nuclear reactor data. The simulation results show that the neural network identified model is sufficiently able to capture the dynamics of the nuclear reactor and it is suitably able to approximate the complex nuclear reactor system.

KW - RCUK

KW - EPSRC

KW - EP/R021961/1

KW - EP/R022062/1

KW - EP/M018717/1

U2 - 10.1109/ICCMA51325.2020.9301483

DO - 10.1109/ICCMA51325.2020.9301483

M3 - Conference contribution

SN - 978-1-7281-9211-6

SP - 100

EP - 104

BT - Proceedings of the 8th International Conference on Control, Mechatronics and Automation, (ICCMA 2020)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - The 8th International Conference on Control, Mechatronics and Automation

Y2 - 6 November 2020 through 8 November 2020

ER -

Dynamic neural network-based system identification of a pressurized water reactor

Abstract

Conference

Keywords

Access to Document

Fingerprint

Projects

Fault Tolerant Control for Increased Safety and Security of Nuclear Power Plants

Cite this