Conference paper Open Access

# A Deep Learning Approach to Anomaly Detection in Nuclear Reactors

Francesco Caliva; Fabio De Sousa Ribeiro; Antonios Mylonakis; Christophe Demazière; Georgios Leontidis; Stefanos Kollias

### Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:creator>Francesco Caliva</dc:creator>
<dc:creator>Fabio De Sousa Ribeiro</dc:creator>
<dc:creator>Antonios Mylonakis</dc:creator>
<dc:creator>Christophe Demazière</dc:creator>
<dc:creator>Georgios Leontidis</dc:creator>
<dc:creator>Stefanos Kollias</dc:creator>
<dc:date>2018-09-06</dc:date>
<dc:description>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.</dc:description>
<dc:identifier>https://zenodo.org/record/1410084</dc:identifier>
<dc:identifier>10.5281/zenodo.1410084</dc:identifier>
<dc:identifier>oai:zenodo.org:1410084</dc:identifier>
<dc:language>eng</dc:language>
<dc:relation>info:eu-repo/grantAgreement/EC/H2020/754316/</dc:relation>
<dc:relation>doi:10.5281/zenodo.1410083</dc:relation>
<dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
<dc:subject>deep learning, convolutional neural networks, clustering trained representations, denoising autoencoders, signal processing, nuclear reactors, unfolding, anomaly detection</dc:subject>
<dc:title>A Deep Learning Approach to Anomaly Detection in Nuclear Reactors</dc:title>
<dc:type>info:eu-repo/semantics/conferencePaper</dc:type>
<dc:type>publication-conferencepaper</dc:type>
</oai_dc:dc>

52
137
views