Analysis and optimization of gas-centrifugal separation of uranium isotopes by neural networks

Abstract

-Neural networks are an attractive alternative for modeling complex problems with too many difficulties to be solved by a phenomenological model. A feed-forward neural network was used to model a gas-centrifugal separation of uranium isotopes. The prediction showed good agreement with the experimental data. An optimization study was carried out. The optimal operational condition was tested by a new experiment and a difference of less than 1% was found.

Investigation of Cut Control Equations in the Gas Centrifuge Cascades

“…In 2014 Borisevich et al [2] proposed that it is possible to find the optimum parameters of a cascade that operates in the minimum total flow. In general behavior the separation work, U, is a function of F, α and θ [7], however experimental data show that U is a function of the feed flow F, θ and pressure in the product line, Pp [8,9]. In fact, the external parameters influence on the internal parameters (F, α and cut θ) in the cascade.…”