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.

This project’s idea revolved around utilizing the most recent techniques in MachineLearning, Neural Networks, and Data processing to construct a model to be used asa tool to determine stability during core design work. This goal will be achieved bycollecting distribution profiles describing the core state from different steady statesin five burn-up cycles in a reactor to serve as the dataset for training the model. Anadditional cycle will be reserved as a blind testing dataset for the trained model topredict. The variables that will be the target for the predictions are the decay ratioand the frequency since they describe the core stability.The distribution profiles extracted from the core simulator POLCA7 were subjectedto many different Data processing techniques to isolate the most relevant variablesto stability. The processed input variables were merged with the decay ratio andfrequency for those cases, as calculated with POLCA-T. Two different MachineLearning models, one for each output parameter, were designed with Pytorch toanalyze those labeled datasets. The goal of the project was to predict the outputvariables with an error lower than 0.1 for decay ratio and 0.05 for frequency. Themodels were able to predict the testing data with an RMSE of 0.0767 for decay ratioand 0.0354 for frequency.Finally, the trained models were saved and tasked with predicting the outputparameters for a completely unknown cycle. The RMSE was even better forthe unknown cycle, with 0.0615 for decay ratio and 0.0257 for frequency,respectively. / Idén bakom detta projekt var att använda de senaste teknikerna inom maskininlärning, neurala nätverk och databehandling för att konstruera en modell att använda som ett verktyg för att avgöra stabilitet under härddesignsarbete. Detta mål kommer uppnås genom att samla distribueringsprofiler av härdens tillstånd från olika stabila lägen i fem förbränningscyklar (burn-up cycles) i en reaktor, som tjänar som en datamängd att träna modellen på.En sjätte förbränningscykel användes som en datamängd för ett blindprov som den tränade modellen ska förutse. Variablerna som kommer tjäna som mål för förutsägelserna är sönderfallsförhållandet (decay ratio) och frekvensen, då dessa beskriver härdens stabilitet. Distribueringsprofilerna som extraherats från härdsimulatorn POLCA7 utsattes för många olika databehandlingstekniker för att isolera de mest relevanta variablerna för stabilitet. De behandlade indatavariablerna blandades med sönderfallsförhållandet och frekvensen för dessa fall, som beräknats med POLCA-T. Två olika maskininlärningsmodeller, en för varje utdataparameter, designades med Pytorch för att analysera dessa märkta datamängder. Projektets mål var att förutse utdatavariablerna med ett fel under 0.1 för sönderfallsförhållandet och 0.05 för frekvensen. Modellerna lyckades förutse testdatan med en RMSE på 0.0767 för sönderfallsförhållande och 0.0354 för frekvensen.Slutligen sparades de tränade modellerna och gavs uppgiften att förutse utdataparametrarna för en komplett okänd cykel. För den okända cykeln var RMSE ännu lägre, med 0.0615 för sönderfallsförhållande och 0.0257 för frekvensen.