Presentation Open Access
A deep learning approach to anomaly detection in nuclear reactors
Francesco Caliva
Presented at IJCNN 2018, this presentation contains the description of 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.
Files
(12.2 MB)
| Name | Size | |
|---|---|---|
|
2018_Caliva_IJCNN_ijcnn_presentation_V1.pdf
md5:2a023bec74cfaf1fcdf123f00ad5f3f5 |
12.2 MB | Download |
37
54
views
downloads
| All versions | This version | |
|---|---|---|
| Views | 37 | 37 |
| Downloads | 54 | 54 |
| Data volume | 659.1 MB | 659.1 MB |
| Unique views | 36 | 36 |
| Unique downloads | 52 | 52 |
Indexed in
- Publication date:
- July 13, 2018
- DOI:
-
- Keyword(s):
- deep learning, convolutional neural networks, clustering trained representations, denoising autoencoders, signal processing, nuclear reactors, unfolding, anomaly detection
- Grants:
-
European Commission:
- CORTEX - Core monitoring techniques and experimental validation and demonstration (754316)
- License (for files):
- Creative Commons Attribution 4.0 International