publication . Other literature type . Conference object . Article . 2019

3D convolutional and recurrent neural networks for reactor perturbation unfolding and anomaly detection

Durrant, Aiden; Leontidis, Georgios; Kollias, Stefanos;
Open Access English
  • Published: 29 Nov 2019
  • Publisher: Zenodo
  • Country: United Kingdom
<jats:p>With Europe's ageing fleet of nuclear reactors operating closer to their safety limits, the monitoring of such reactors through complex models has become of great interest to maintain a high level of availability and safety. Therefore, we propose an extended Deep Learning framework as part of the CORTEX Horizon 2020 EU project for the unfolding of reactor transfer functions from induced neutron noise sources. The unfolding allows for the identification and localisation of reactor core perturbation sources from neutron detector readings in Pressurised Water Reactors. A 3D Convolutional Neural Network (3D-CNN) and Long Short-Term Memory (LSTM) Recurrent Ne...
free text keywords: Reactor safety, modeling, CORTEX, Reactor safety, modeling, CORTEX, H821 Nuclear Engineering, G400 Computer Science, G760 Machine Learning, Recurrent neural network, Convolutional neural network, Signal processing, Time domain, Frequency domain, Deep learning, Computer science, Anomaly detection, Nuclear reactor core, Artificial intelligence, business.industry, business, Algorithm, lcsh:Nuclear engineering. Atomic power, lcsh:TK9001-9401
Funded by
Organizing FISA and EuradWaste Conference under the Romanian Presidency of EU Council
  • Funder: European Commission (EC)
  • Project Code: 826027
  • Funding stream: H2020 | CSA
Validated by funder
Core monitoring techniques and experimental validation and demonstration
  • Funder: European Commission (EC)
  • Project Code: 754316
  • Funding stream: H2020 | RIA
Energy Research
Any information missing or wrong?Report an Issue