Use of Neural Network for the Simulation of a Gas Centrifuge.

Abstract

The prediction by a mathematical model of the separation of uranium isotopes using a gas centrifuge process is a hard task. The gas motion can be described by analytical or numerical solutions of the system of equations defined by the equation of continuity, the Navier-Stokes equation and the equation of energy. However, these calculations cannot be performed for actual centrifuges.Neural networks are an alternative for modelling complex problems that show too many difficulties to be solved by phenomenological models.The authors propose the use of neural networks for the simulation and prevision of the separative and operational parameters of a gas centrifuge separating uranium isotopes. The results from the uranium separation experiments (Zippe data) are compiled and presented to the neural network in the learning and testing processes. The prediction using the neural network model shows good agreement with the experimental data.

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

“…Many applications in modeling and optimization of chemical processes are available in the open literature (Nascimento et al, 1999;Nascimento et al, 2000). In nuclear technology, the use of neural networks dates bake to the end of the 80's.…”

“…Using Zippe's data (1960), Migliavacca et al (1999) simulated the separation of uranium isotopes with a neural network model. Good agreement was achieved.…”

Detection of outliers in a gas centrifuge experimental data

“…On the other hand, it is very difficult to relate the parameters used to describe numerically the countercurrent with the physical devices used in the centrifuge (Kai, 1989;Migliavacca et al, 1999;Migliavacca, 1999). Since it is a process where by the gas flows at supersonic speeds, the resulting flow is very sensitive to variations in the characteristics of centrifuge construction, and even to differences possible mechanical precision.…”