Le sujet de la thèse s'inscrit dans le cadre de la rénovation des outils et des méthodes de calculs appliqués aux accidents graves des Réacteurs à Neutrons Rapides refroidis au Sodium (RNR-Na). En particulier, on s'intéresse aux biais et conservatismes liés à la méthodologie de calculs de la phase primaire d'un accident grave. Pour évaluer les conséquences d'un accident de fusion du coeur d'un RNR-Na, une approche déterministe est généralement réalisée en considérant des hypothèses dites "best-estimate". Cette approche repose sur l'utilisation de codes informatiques pour simuler numériquement le comportement du coeur en conditions accidentelles.La phase primaire de dégradation concerne les évènements se produisant tant que les boîtiers inter-assemblages sont intègres. Les assemblages combustibles conservent alors une indépendance les uns par rapport aux autres. Pour cette raison, la simulation de la phase primaire repose sur une approche multi-canaux. Cette approche consiste à regrouper les assemblages semblables en classes d'assemblages appelés canaux. Le modèle thermo-hydraulique en canaux est couplé à un calcul neutronique pour évaluer le niveau de puissance et de réactivité au cours du transitoire accidentel. La méthodologie de calcul de la phase primaire d'un accident grave repose sur des hypothèses fortes en termes de modélisation neutronique et thermo-hydraulique. Après avoir identifié les principales sources d'erreur, la thèse a consisté à développer un nouvel outil de calcul pour la phase primaire en vue d'évaluer les biais et conservatismes méthodologiques. / This project is dedicated to the analysis and the quantification of bias corresponding to the computational methodology for simulating the initiating phase of severe accidents on Sodium Fast Reactors. A deterministic approach is carried out to assess the consequences of a severe accident by adopting best estimate design evaluations. An objective of this deterministic approach is to provide guidance to mitigate severe accident developments and recriticalities through the implementation of adequate design measures. These studies are generally based on modern simulation techniques to test and verify a given design. The new approach developed in this project aims to improve the safety assessment of Sodium Fast Reactors by decreasing the bias related to the deterministic analysis of severe accident scenarios.During the initiating phase, the subassembly wrapper tubes keep their mechanical integrity. Material disruption and dispersal is primarily one-dimensional. For this reason, evaluation methodology for the initiating phase relies on a multiple-channel approach. Typically a channel represents an average pin in a subassembly or a group of similar subassemblies. Inthe multiple-channel approach, the core thermal-hydraulics model is composed of 1 or 2 D channels. The thermal-hydraulics model is coupled to a neutronics module to provide an estimate of the reactor power level.In this project, a new computational model has been developed to extend the initiating phase modeling. This new model is based on a multi-physics coupling. This model has been applied to obtain information unavailable up to now in regards to neutronics and thermal-hydraulics models and their coupling.

The demand for computational tools that are capable to reliably predict the behavior of a nuclear reactor core in a variety of static and dynamic conditions does inevitably require a proper qualification of these tools for the intended purposes. One of the qualification methods is the verification of the code in question. Hereby, the correct implementation of the applied model as well as its flawless implementation in the code are scrutinized. The present work concerns with benchmarking as a substantial part of the verification of the three-dimensional, multigroup neutron kinetics model employed in the transient code POLCA-T. The benchmarking is done by solving some specified and widely used space-time kinetics benchmark problems and comparing the results to those of other, established and well-proven spatial kinetics codes. It is shown that the obtained results are accurate and consistent with corresponding solutions of other codes. In addition, a sensitivity analysis is carried out with the objective to study the sensitivity of the POLCA-T neutronics to variations in different numerical options. It is demonstrated that the model is numerically stable and provide reproducible results for a wide range of various numerical settings. Thus, the model is shown to be rather insensitive to significant variations in input, for example. The other consequence of this analysis is that, depending on the treated transient, the computing costs can be reduced by, for instance, employing larger time-steps during the time-integration process or using a reduced number of iterations. Based on the outcome of this study, one can finally conclude that the POLCA-T neutron kinetics is modeled and implemented correctly and thus, the model is fully capable to perform the assigned tasks.