Results of the application and demonstration calculations

Georgios Alexandridis, Christoph Blaesius, Christophe Demaziere, Christophe Destouches, Abdelhamid Dokhane, Aiden Durrant, Vladimir Fiser, Gaëtan Girardin, Joachim Herb, Georgios Ioannou, Robert Jacqmin, Alexander Knospe, Stefanos Kollias, Carsten Lange, Georgios Leontidis, Sandor Lipcsei, Cristina Montalvo, Antonios Mylonakis, Laurent Pantera, Yann PerinChristoph Pohl, Marcus Seidl, Andreas Stafylopatis, Petr Stulik, Luis Alejandro Torres, Gumersindo Verdu Martin, Vasudha Verma, Antoni Vidal-Ferràndiz, Marco Viebach, Paolo Vinai

Research output: Other contribution

6 Downloads (Pure)

Abstract

This report describes the results of the application of the newly developed tools for reactor noise analysis, advanced signal processing and machine learning methodologies to actual plant data. More specifically, the modeling tools developed in WP1 are used to simulate and analyze real plant measurements from the pre-Konvoi 3-loop NPP at Gösgen, a German pre-Konvoi 4-loop reactor, a Hungarian VVER-440 reactor and a Czech VVER-1000 reactor. Subsequently, the techniques developed in WP3 are used to identify the root causes of neutron flux fluctuations in the actual plant data for the reactors presented above. The results are compared with the simulation results corresponding to the selected power plants, based on the hypotheses developed for reactor noise analysis.
Original languageEnglish
PublisherEuropean Commission
Number of pages194
Publication statusPublished - 31 Jul 2020

Bibliographical note

CORTEX - Research and Innovation Action (RIA)
This project has received funding from the European
Union's Horizon 2020 research and innovation programme
under grant agreement No 754316.

Keywords

  • nuclear reactors
  • Machine learning
  • Anomaly detection
  • nuclear reactor noise analysis

Fingerprint

Dive into the research topics of 'Results of the application and demonstration calculations'. Together they form a unique fingerprint.

Cite this