A deep learning approach to anomaly detection in nuclear reactors
Paper i proceeding, 2018

In this work, a novel deep learning approach to unfold nuclear power reactor signals is proposed. It includes a combination of convolutional neural networks (CNN), denoising autoencoders (DAE) and k-means clustering of representations. Monitoring nuclear reactors while running at nominal conditions is critical. Based on analysis of the core reactor neutron flux, it is possible to derive useful information for building fault/anomaly detection systems. By leveraging signal and image pre-processing techniques, the high and low energy spectra of the signals were appropriated into a compatible format for CNN training. Firstly, a CNN was employed to unfold the signal into either twelve or forty-eight perturbation location sources, followed by a k-means clustering and k-Nearest Neighbour coarse-to-fine procedure, which significantly increases the unfolding resolution. Secondly, a DAE was utilised to denoise and reconstruct power reactor signals at varying levels of noise and/or corruption. The reconstructed signals were evaluated w.r.t. their original counter parts, by way of normalised cross correlation and unfolding metrics. The results
illustrate that the origin of perturbations can be localised with high accuracy, despite limited training data and obscured/noisy signals, across various levels of granularity.

nuclear reactors

signal processing

clustering trained representations

deep learning


anomaly detection

denoising autoencoders

convolutional neural networks


Fabio De Sousa Ribeiro

University of Lincoln

Francesco Calivá

University of Lincoln

Antonios Mylonakis

Chalmers, Fysik, Subatomär fysik och plasmafysik

Christophe Demaziere

Chalmers, Fysik, Subatomär fysik och plasmafysik

Paolo Vinai

Chalmers, Fysik, Subatomär fysik och plasmafysik

Georgios Leontidis

University of Lincoln

Stefanos Kollias

University of Lincoln

2018 International Joint Conference on Neural Networks (IJCNN2018)
Rio de Janeiro, Brazil,

Core monitoring techniques and experimental validation and demonstration (CORTEX)

Europeiska kommissionen (Horisont 2020), 2017-09-01 -- 2021-08-31.


Data- och informationsvetenskap

Annan fysik



Mer information

Senast uppdaterat