10.5281/zenodo.3547647
https://zenodo.org/records/3547647
oai:zenodo.org:3547647
Tagaris T., Ioannou G., Sdraka M., Alexandridis G., and Stafylopatis A
Tagaris T., Ioannou G., Sdraka M., Alexandridis G., and Stafylopatis A
Putting together wavelet-based scaleograms and convolutional neural networks for anomaly detection in nuclear reactors.
Zenodo
2019
2019-10-28
Poster
10.5281/zenodo.3547646
https://zenodo.org/communities/cortex
https://zenodo.org/communities/eu
Creative Commons Attribution 4.0 International
A critical issue for the safe operation of nuclear power plants is to quickly and accurately detect possible anomalies and perturbations in the reactor. Defects in operation are principally identified through changes in the neutron flux, as captured by detectors placed at various points inside and outside of the core. This work presents a novel technique for anomaly detection onĀ nuclear reactor signals through the combined use of wavelet-based analysis and convolutional neural networks. In essence, the wavelet transform is applied to the signals and the corresponding scaleograms are produced, which are subsequently used to train a convolutional neural network that detects possible perturbations in the reactor core. The overall methodology is experimentally validated on a set of simulated nuclear reactor signals generated by a well established relevant tool. The obtained results indicate that the trained network achieves high levels of accuracy in failure detection, while at the same time being robust to noise.
European Commission
10.13039/501100000780
754316
Core monitoring techniques and experimental validation and demonstration