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

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

31 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 languageEnglish
Title of host publicationProceedings of the 8th International Conference on Control, Mechatronics and Automation, (ICCMA 2020)
PublisherInstitute of Electrical and Electronics Engineers
Pages100-104
Number of pages5
ISBN (Electronic)978-1-7281-9210-9, 978-1-7281-9209-3
ISBN (Print)978-1-7281-9211-6
DOIs
Publication statusPublished - 29 Dec 2020
EventThe 8th International Conference on Control, Mechatronics and Automation - Moscow, Russian Federation
Duration: 6 Nov 20208 Nov 2020
http://www.iccma.org/

Conference

ConferenceThe 8th International Conference on Control, Mechatronics and Automation
Abbreviated titleICCMA 2020
Country/TerritoryRussian Federation
CityMoscow
Period6/11/208/11/20
Internet address

Keywords

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

Fingerprint

Dive into the research topics of 'Dynamic neural network-based system identification of a pressurized water reactor'. Together they form a unique fingerprint.

Cite this