Journal article Open Access

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

Aiden Durrant; Georgios Leontidis; Stefanos Kollias

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 Neural Network (RNN) have been presented, each to study the signals presented in frequency and time domain respectively. The proposed approach achieves state-of-the-art results with the classification of perturbation type in the frequency domain reaching 99.89% accuracy and localisation of the classified perturbation source being regressed to 0.2902 Mean Absolute Error (MAE).

Files (1.1 MB)
Name Size
2019_Durrant_EPJ_N_paper_V1.pdf
md5:62df12bbb8519aa3352c28aa7536304f
1.1 MB Download
15
22
views
downloads
Views 15
Downloads 22
Data volume 23.6 MB
Unique views 14
Unique downloads 22

Share

Cite as