Assessing Sensor Integrity for Nuclear Waste Monitoring Using Graph Neural Networks
Article dans une revue avec comité de lecture
Abstract
A deep geological repository for radioactive waste, such as Andra’s Cigéo project, requires long-term (persistent) monitoring. To achieve this goal, data from a network of sensors are acquired. This network is subject to deterioration over time due to environmental effects (radioactivity, mechanical deterioration of the cell, etc.), and it is paramount to assess each sensor’s integrity and ensure data consistency to enable the precise monitoring of the facilities. Graph neural networks (GNNs) are suitable for detecting faulty sensors in complex networks because they accurately depict physical phenomena that occur in a system and take the sensor network’s local structure into consideration in the predictions. In this work, we leveraged the availability of the experimental data acquired in Andra’s Underground Research Laboratory (URL) to train a graph neural network for the assessment of data integrity. The experiment considered in this work emulated the thermal loading of a high-level waste (HLW) demonstrator cell (i.e., the heating of the containment cell by nuclear waste). Using real experiment data acquired in Andra’s URL in a deep geological layer was one of the novelties of this work. The used model was a GNN that inputted the temperature field from the sensors (at the current and past steps) and returned the state of each individual sensor, i.e., faulty or not. The other novelty of this work lay in the application of the GraphSAGE model which was modified with elements of the Graph Net framework to detect faulty sensors, with up to half of the sensors in the network being faulty at once. This proportion of faulty sensors was explained by the use of distributed sensors (optic fiber) and the environmental effects on the cell. The GNNs trained on the experimental data were ultimately compared against other standard classification methods (thresholding, artificial neural networks, etc.), which demonstrated their effectiveness in the assessment of data integrity.
Files in this item
- Name:
- PIMM_S_2024_HEMBERT.pdf
- Size:
- 9.703Mb
- Format:
- Description:
- Assessing Sensor Integrity for ...
Related items
Showing items related by title, author, creator and subject.
-
Article dans une revue avec comité de lectureElectromagnetic field propagation inside composite materials represents a challenge where fiber-scale simulation remains intractable using classical simulation methods. The present work proposes an original 3D simulation ...
-
Article dans une revue avec comité de lecture
CUETO, Elias; FALCO, Antonio; DUVAL, Jean-Louis;
GHNATIOS, Chady;
CHINESTA SORIA, Francisco (Springer Science and Business Media LLC, 2020)
Non-intrusive approaches for the construction of computational vademecums face different challenges, especially when a parameter variation affects the physics of the problem considerably. In these situations, classical ... -
Article dans une revue avec comité de lectureREILLE, Agathe; HASCOET, Nicolas;
CUETO, Elias; DUVAL, Jean-Louis; KEUNINGS, Roland;
GHNATIOS, Chady;
AMMAR, Amine;
CHINESTA SORIA, Francisco (Elsevier Masson, 2019)
The present work aims at proposing a new methodology for learning reduced models from a small amount of data. It is based on the fact that discrete models, or their transfer function counterparts, have a low rank and then ... -
Article dans une revue avec comité de lecture
GHNATIOS, Chady; DELPLACE, Frank; BARASINSKI, Anais; DUVAL, Jean-Louis;
CUETO, Elias;
AMMAR, Amine;
CHINESTA SORIA, Francisco (Wiley, 2020)
Composite manufacturing processes usually proceed from preimpregnated preforms that are consolidated by simultaneously applying heat and pressure, so as to ensure a perfect contact compulsory for making molecular diffusion ... -
Article dans une revue avec comité de lectureIBAÑEZ, Ruben; CASTERAN, Fanny; ARGERICH, Clara; HASCOET, Nicolas; CASSAGNAU, Philippe;
GHNATIOS, Chady;
AMMAR, Amine;
CHINESTA SORIA, Francisco (MDPI, 2020)
This paper analyzes the ability of different machine learning techniques, able to operate in the low-data limit, for constructing the model linking material and process parameters with the properties and performances of ...