Neural network analysis of Doppler-broadened neutron absorption resonance data

Abstract

Thermally-induced Doppler broadening of neutron absorption resonances can be used as a unique signature of the temperature of individual isotopes in a mixture. This principle can be exploited for temperature measurements in situations where conventional measurement techniques are not available, such as measurement of temperatures of individual parts of a system in a severe environment, or of components selectively heated by chemical, electromagnetic, or nuclear processes. Interpretation of the broadened absorption data is normally done by comparison to a nuclear physics model of the absorption process. This paper reports a study of the feasibility of interpreting the data with a trained neural network model.