Neural Network Acceleration of Genetic Algorithms for the Optimization of a Coupled Fast/Thermal Nuclear Experiment

Genetic algorithms (GA) are used to optimize the Fast Neutron Source (FNS) core fuel loading maximize a multiobjective function. The FNS has 150 material locations that can be loaded with one of three different materials resulting in over 3E+71 combinations. individual designs evaluated computationally intensive calls MCNP. To speed up optimization, convolutional neural networks (CNN) trained as surrogate models and produce better performing candidates will meet design constraints before they sent costly MCNP evaluations. A major hurdle training all kinds is availability robust data. In this application, we use data produced by GA for which combine geometric features system predict objectives constraint objectives. Utilizing models, accelerated algorithm more viable significantly improved objective function utilizing same computational resources.