Vincent Audoly

This study introduces AIA-Net, standing for Autoencoder Improved Attention Network, a novel neural-network (NN) architecture based on an attention mechanism for solving the non-linear inverse problem of Electrical Impedance Tomography (EIT). It aims at producing reliable reconstructed images of the conductivity distribution within a probed medium. To overcome the generalization problem inherent to deep learning approaches, AIA-Net is further improved using a latent space generative NN based on a Conditional Latent Diffusion Model. We present an end-to-end workflow from measurements to image reconstructions using AIA-Net. The EIT voltage excitations protocol considered relies on the ONe Excitation for Simultaneous High-speed Operation Tomography method. Static experimental tests are conducted, with plastic rods of different shapes and combinations emulating anomalous objects within a reference medium. Using a total of 16 320 data, comprising both voltage measurements and ground-truth images, some reference NNs for reconstructing conductivity images are deployed and compared, qualitatively and quantitatively, with the proposed AIA-Net architecture. The results presented highlight the excellent overall performance of AIA-Net compared to existing architectures, along with a further improvement provided by a generative model to overcome the generalization problem.

Carnot batteries (CBs) offer an appealing alternative to saturated pumped-hydro facilities and electrochemical batteries dependent on critical raw materials. A concept recently highlighted in the literature is that of coupled CBs, in which the discharge cycle of a CB interacts directly with the power cycle of a thermal power plant. Such configurations show promising gains in performance, cost, and responsiveness. However, their dynamic behavior remains insufficiently characterised, restricting assessment of the grid services they could realistically deliver. This work examines an innovative architecture in which a nuclear Rankine cycle is coupled to a CB to enhance operational flexibility. Following the preliminary system sizing, a detailed numerical analysis is performed using the CATHARE-3 thermal–hydraulic code to characterize the overall steady-state performance and transient behavior during CB discharge. The results show that the high-pressure turbine acts as an effective filter, absorbing most disturbances introduced by the CB. A refined breakdown of inertial contributions within both the Rankine cycle and the CB enables the identification of the most sensitive components. Finally, under these preliminary sizing assumptions, the coupled system exhibits high performance and would be capable of meeting the primary frequency control requirements during discharge operation, suggesting that coupled CBs constitutes a promising solution for providing fast frequency-regulation services to the electrical grid.