Multi-objective Optimization of Nuclear Microreactor Control System Operation with Swarm and Evolutionary Algorithms

Abstract

To improve the marketability of novel microreactor designs, there is a need for automated and optimal control of these reactors. This paper presents a methodology for performing multi-objective optimization of control drum operation for a microreactor under normal and accident conditions. Two different case studies are used where the control drum configuration is optimized for the reactor to be critical with some desired power distribution that would satisfy peaking limits. In addition to these objectives, one case study seeks to minimize control drum travel distance where the other maximizes control drum differential worth. A surrogate model for power distribution is developed based on a feedforward neural network. The process for determining weights for scalarization of the multi-objective optimization problem is also detailed. Six optimization algorithms: evolutionary strategies, differential evolution, grey wolf optimization, Harris hawks optimization, moth flame optimization and particle swarm optimization, are all applied to these cases and the results analyzed. All algorithms demonstrated optima-seeking behavior and could present reasonable optima in minutes. The moth flame optimization algorithm was found to perform particularly well on both cases. Overall, it was found that the algorithms capable of supplying the best optima were also the most consistent. Finally, the found optima were verified with the original model used to train surrogates.