RESUMEN
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.
RESUMEN
Understanding sliding and load-bearing mechanisms of biphasic soft matter is crucial for designing synthetic replacements of cartilage, contact-lens materials or coatings for medical instruments. Interstitial fluid pressurization is believed to be the intrinsic load-carrying phenomenon governing the frictional properties. In this study, we have characterized permeability and identified the fluid contribution to the support of load during Atomic Force Microscopy (AFM) nanoindentation of soft polymer brushes in aqueous environments, by means of the Proper Generalized Decomposition (PGD) approach. First, rate-dependent AFM nanoindentation was performed on a poly(acrylamide) (PAAm) brush in an aqueous environment, to probe the purely elastic as well as poro-viscoelastic properties. Second, a biphasic model decoupling the fluid and solid load contributions was proposed, using Darcy's equation for liquid flow in porous media. Using realistic time-dependent simulations requires many direct solutions of the 3D partial differential equation, making modeling very time-consuming. To efficiently alleviate the time-consumption of multi-dimensional modeling, we used PGD to solve a Darcy model defined in a 7D domain, considering all the unknowns and material properties as extra coordinates of the problem. The obtained 7D simulation results were compared to the experimental results by using a direct Newton algorithm, since all sensitivities with respect to the model parameters are readily available. Thus, a simulation-based solution for depth- and rate-dependent permeability can be obtained. From the PGD-based model permeability is calculated, and the velocity- and pressure-fields in the material can be obtained in real-time in 3D by adjusting the parameters to the experimental values. The result is a step forward in understanding the fluid flow, permeability and fluid contributions to the load support of biphasic soft matter.