Artificial Neural Network Solutions of Slab-Geometry Neutron Diffusion Problems

Conference · Mon Jun 12 00:00:00 EDT 2000

OSTI ID:793624

Brantley, P S

Artificial neural network (ANN) methods have been researched extensively within the nuclear community for applications in systems control, diagnostics, and signal processing. We consider here the use of multilayer perceptron ANNs as an alternative to finite-difference and finite-element methods for obtaining solutions to neutron diffusion problems. This work is based on a method proposed by van Milligen et. al. to obtain solutions of the differential equations arising in plasma physics applications. This ANN method has the potential advantage of yielding an accurate, differentiable approximation to the solution of diffusion problems at all points in the spatial domain.

• Research Organization: Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
• Sponsoring Organization: USDOE Office of Defense Programs (DP) (US)
• DOE Contract Number: W-7405-Eng-48
• OSTI ID: 793624
• Report Number(s): UCRL-JC-139281; TRN: US0205251
• Resource Relation: Conference: 2000 International Winter Meeting and Embedded Topical Meetings, Washington, DC (US), 11/12/2000--11/16/2000; Other Information: PBD: 12 Jun 2000
• Country of Publication: United States
• Language: English

Related Subjects

71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS
DIFFERENTIAL EQUATIONS
DIFFUSION
FINITE ELEMENT METHOD
NEURAL NETWORKS
NEUTRONS
PHYSICS
PLASMA