1. A Deep Learning Approach to Anomaly Detection in Nuclear Reactors
- Author
-
Stefanos Kollias, Fabio Sousa De Ribeiro, Christophe Demazirere, Georgios Leontidis, Paolo Vinai, Antonios Mylonakis, and Francesco Caliva
- Subjects
Training set ,Noise measurement ,Computer science ,business.industry ,020209 energy ,Deep learning ,Pattern recognition ,02 engineering and technology ,G400 Computer Science ,Convolutional neural network ,0202 electrical engineering, electronic engineering, information engineering ,Anomaly detection ,Artificial intelligence ,G760 Machine Learning ,Cluster analysis ,business - Abstract
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.
- Published
- 2018