Lightweight CNN and Causal GNN for scene understanding
Scene understanding is a major challenge in computer vision, with recent approaches dominated by transformers (ViT, LLM, MLLM), which offer high performance but at a significant computational cost. This thesis proposes an innovative alternative combining lightweight convolutional neural networks (Lightweight CNN) and causal graph neural networks (Causal GNN) for efficient spatio-temporal analysis while optimizing computational resources. Lightweight CNNs enable high-performance extraction of visual features, while causal GNNs model dynamic relationships between objects in a scene graph, addressing challenges in object detection and relationship prediction in complex environments. Unlike current transformer-based models, this approach aims to reduce computational complexity while maintaining competitive accuracy, with potential applications in embedded vision and real-time systems.
Development of automatic gamma spectrum analysis using a hybrid machine learning algorithm for the radiological characterization of nuclear facilities decommissioning.
The application of gamma spectrometry to radiological characterization in nuclear facility decommissioning, requires the development of specific algorithms for automatic gamma spectrum analysis. In particular, the classification of concrete waste according to its level of contamination, is a crucial issue for controlling decommissioning costs.
Within CEA/List, LNHB, in collaboration with CEA/DEDIP, has been involved for several years in the development of tools for the automatic analysis of low-statistics gamma spectra, which can be applied to scintillator detectors (NaI(Tl), plastics). In this context, an original approach based on a hybrid machine learning/statistics spectral unmixing algorithm has been developed for the identification and quantification of radionuclides in the presence of significant deformations in the measured spectrum, due in particular to interactions between the gamma emission from the radioactive source and its environment.
The proposed subject follows on from thesis work that led to the development of the hybrid algorithm with the aim of extending this approach to the radiological characterization of concrete surfaces. The candidate will be involved in the evolution of the hybrid machine learning/statistical algorithm for the characterization of concrete for classification as conventional waste. The work will include a feasibility study of modeling the deviations of the learned model to optimize the robustness of decision-making.
Optimized control of a modular energy hub with minimal EMC signature
The integration of renewable energy sources (RES) has become an important issue for power converters. The increasing number of these converters and their average utilization rate allows for a rethink of energy exchange management at the system level. This leads us to the concept of an energy hub, which can interface, for example, a photovoltaic (PV) system, an electric vehicle, a grid, and stationary storage with loads.
The main objective of this thesis is to improve the efficiency, compactness, and modularity of the energy hub through control. Several ideas emerge to achieve this, such as advanced control to minimize losses, the use of AC input opposition to reduce electromagnetic compatibility (EMC) filtering, series/parallel DC output configurations to address 400Vdc/800Vdc batteries, and increasing the switching frequency to reduce volume, etc.
Thus, this thesis will, in the medium term, lead to the development of an optimal converter in terms of both energy efficiency and environmental impact.
Assessment of new models for the investigation of hypothetical accidents in GEN4 fast reactors.
Multi-component two-phase flows in conjunction with fluid-structure interaction (FSI) problems can occur in a very large variety of engineering applications; amongst them, the hypothetical severe accidents postulated in Generation IV sodium and lead fast-breeder reactors (respectively SFR and LFR).
In SFRs, the worst postulated severe accident is the so-called hypothetical core disruptive accident (HCDA), in which the partial melt of the core of the reactor interacts with the surrounding sodium and creates a high-pressure gas bubble, the expansion of which generates shock waves and is responsible of the motion of liquid sodium, thus eventually damaging internal and surrounding structures.
The LFR presents the advantage that, unlike sodium, lead does not chemically react with air and water and, therefore, is explosion-proof and fire-safe. On the one hand, this allows a steam generator inside the primary coolant. On the other hand, the so-called steam generator tube ruptures (SGTR) should be investigated to guarantee that, in the case of this hypothetical accident the structure integrity is preserved. In the first stage of a SGTR, it is supposed that the steam-generator high-pressure high-temperature water penetrates inside the primary containment, thus generating a BLEVE (boiling liquid expanding vapor explosion) with the same behavior and consequences as the high-pressure gas bubble of a HCDA.
In both HCDA and STGR, there are situations in which the multi-component two-phase flows is in low Mach number regime which, when studied with classical compressible solver, presents problems of loss of accuracy and efficiency. The purpose of this PhD is
* to design a multiphase solver, accurate and robust, to investigate HCDA STGR scenarios.
* to design a low Mach number approach for bubble expansion problem, based on the artificial compressibility method presented in the recent paper "Beccantini et al., Computer and fluids 2024".
The aspect FSI will be also taken into account.
Learning Mechanisms for Detecting Abnormal Behaviors in Embedded Systems
Embedded systems are increasingly used in critical infrastructures (e.g., energy production networks) and are therefore prime targets for malicious actors. The use of intrusion detection systems (IDS) that dynamically analyze the system's state is becoming necessary to detect an attack before its impacts become harmful.
The IDS that interest us are based on machine learning anomaly detection methods and allow learning the normal behavior of a system and raising an alert at the slightest deviation. However, the learning of normal behavior by the model is done only once beforehand on a static dataset, even though the embedded systems considered can evolve over time with updates affecting their nominal behavior or the addition of new behaviors deemed legitimate.
The subject of this thesis therefore focuses on studying re-learning mechanisms for anomaly detection models to update the model's knowledge of normal behavior without losing information about its prior knowledge. Other learning paradigms, such as reinforcement learning or federated learning, may also be studied to improve the performance of IDS and enable learning from the behavior of multiple systems.
Electromagnetic Signature Modeling and AI for Radar Object Recognition
This PhD thesis offers a unique opportunity to work at the crossroads of electromagnetics, numerical simulations, and artificial intelligence, contributing to the development of next-generation intelligent sensing and recognition systems. The intern will join the Antenna & Propagation Laboratory at CEA-LETI, Grenoble (France), a world-class research environment equipped with state-of-the-art tools for propagation channel characterization and modelling. A collaboration with the University of Bologna (Italy) is planned during the PhD.
This PhD thesis aims to develop advanced electromagnetic models of near-field radar backscattering, tailored to radar and Joint Communication and Sensing (JCAS) systems operating at mmWave and THz frequencies. The research will focus on the physics-based modeling of the radar signatures of extended objects, accounting for near-field effects, multistatic and multi-antenna configurations, as well as the influence of target materials and orientations. These models will be validated through electromagnetic simulations and dedicated measurement campaigns, and subsequently integrated into scene-level and multipath propagation simulation tools based on ray tracing. The resulting radar signatures will be exploited to train artificial intelligence algorithms for object recognition, material property inference, and radar imaging. In parallel, physics-assisted AI approaches will be investigated to accelerate electromagnetic simulations and reduce their computational complexity. The final objective of the thesis is to integrate radar backscattering-based information into a 3D Semantic Radio SLAM framework, in order to improve localization, mapping, and environmental understanding in complex or partially obstructed scenarios.
We are seeking a student at engineering school or Master’s level (MSc/M2), with a strong background in signal processing, electromagnetics, radar, or telecommunications. An interest in artificial intelligence, physics-based modeling, and numerical simulation is expected. Programming skills in Matlab and/or Python are appreciated, as well as the ability to work at the interface between theoretical models, simulations, and experimental validation. Scientific curiosity, autonomy, and strong motivation for research are essential.The application must include a CV, academic transcripts, and a motivation letter.
Study of Failure Modes and Mechanisms in RF Switches Based on Phase-Change Materials
Switches based on phase change materials (PCM) demonstrate excellent RF performance (FOM <10fs) and can be co-integrated into the BEOL of CMOS processes. However, their reliability is still very little studied today. Failure modes such as heater breakage, segregation, or the appearance of cavities in the material are shown during endurance tests, but the mechanisms of these failures are not discussed. The objective of this thesis will therefore be to study the failure modes and mechanisms for different operating conditions (endurance, hold, power). The analysis will be carried out through electrical and physical characterizations and accelerated aging methods will be implemented.
Code Development and Numerical Simulation of Gas Entrainment in Sodium-Cooled Fast Reactors
In sodium-cooled fast reactors (SFRs), the circulation of liquid sodium is ensured by immersed centrifugal pumps. Under certain conditions, vortices can develop in recirculation zones, promoting the entrainment of inert gas bubbles (typically argon) located above the free surface. If these bubbles are drawn into the primary circuit, they can damage pump components and compromise the safety of the installation. This phenomenon remains difficult to predict, particularly during the design phase, as it depends on numerous physical, geometrical, and numerical parameters.
The objective of this PhD work is to contribute to a better understanding and modeling of gas entrainment in free-surface flows typical of SFRs, through Computational Fluid Dynamics (CFD) simulations using the open-source code TrioCFD, developed by the CEA. This code includes an interface-tracking module (Front Tracking) that is particularly well-suited for simulating two-phase phenomena involving a deformable free interface.
Atomic scale modeling of radiation induced segregation in Zr(Nb) alloys
Nuclear fuel cladding made of zirconium alloys constitute the first safety barrier in pressurized water reactors. The microstructure of these alloys not only controls mechanical properties, but also phenomenon such as corrosion or growth under irradiation. Enabling a more flexible use of nuclear energy in the mix while maintaining the structural integrity of fuel cladding under both operating and accidental conditions, we must understand the detailed mechanisms of microstructure evolution under irradiation. Numerous studies point toward the center part played by Nb in such microstructural evolution. For instance, diffusion flux coupling between solutes (Nb) and point defect created by irradiation gives rise to local Nb segregation, as well as precipitates which are not seen in non-irradiated samples. Atomic scale modeling brings in information that complements that obtained from experimental observations, allowing to confirm or disprove the evolution scenarios found in the literature. The aim of this Ph.D. work is to use the tools which have been developed to study irradiation effects in ferritic steels, and apply them to Zr alloys, with a focus on radiation induced segregation. Electronic structure calculations in the density functional theory approximation will be used to study the interactions between niobium atoms and point defects. From this data, we are able to compute transport coefficients, from which we can discuss quantitatively solute/point defect flux coupling and radiation induced segregation effects.
Experimental study of Nanometric-Scale Microstructural and Microchemical Evolution in Zirconium Alloys under Irradiation
Zirconium-based alloys are used as fuel cladding material for pressurized water reactors due to their low thermal neutron absorption cross-section, good mechanical strength, and excellent corrosion resistance. However, despite decades of research, the mechanisms governing the evolution of their microstructure and microchemistry under irradiation are still not fully understood. These phenomena strongly influence the in-reactor performance and lifetime of the materials
Neutron irradiation generates displacement cascades in crystalline material, producing large numbers of point defects (vacancies and interstitials) that can cluster and drive atomic redistribution. The high concentration of point defects promotes radiation-induced segregation and precipitation of alloying elements. In Zr1%Nb alloys, irradiation leads to the unexpected formation of high density Nb-rich nanoprecipitates. This phenomenon has significant implications on the macroscopic properties of the material, notably its post-irradiation creep and corrosion behavior in reactors.
This PhD project aims to elucidate the mechanisms responsible for the precipitation of Nb-rich nanoprecipitates under irradiation. A Zr1%Nb alloy will be irradiated with ions at various doses and temperatures, followed by advanced nanoscale characterization using transmission electron microscopy (TEM) and atom probe tomography (APT). These complementary techniques will provide detailed information on the spatial distribution of alloying elements and the nature of point defect clusters at the atomic scale. Based on these results, a comprehensive mechanism for irradiation-induced precipitation will be proposed, and its implications for the macroscopic properties and in-reactor performance of zirconium alloys will be assessed. By improving the fundamental understanding of irradiation-induced microstructural evolution, this research aims to contribute to the development of more radiation-resistant zirconium alloys for nuclear applications.