You need JavaScript to view this

Uranium enrichment measurement task with a connectionist architecture

Abstract

Layered Neural Networks, which are a class of models based on neural computation, are applied to the measurement of uranium enrichment, i.e. the isotope ration {sup 235} U/({sup 235} U+{sup 236} U+{sup 238} U). The usual methods consider a limited number of {gamma}-ray and X-ray peaks, and requires previously calibrated instrumentation for each sample. But, in practice, the source-detector ensemble geometry conditions are critically different, thus a means of improving the above conventional methods is to reduce the region of interest: this is possible by focusing on the region called K{sub {alpha}}X where the three elementary components are present. The measurement of these components in mixtures leads to the desired ratio. Real data are used to study its performance. Training is done with a Maximum Likelihood method. We show the encoding of data by Neural Networks is a promising method to measure uranium {sup 235} U and {sup 238} U quantities in infinitely thick samples. (authors). 7 refs., 2 figs., 1 tab.
Authors:
Vigneron, V; Martinez, J M; [1]  Morel, J; Lepy, M C [2] 
  1. CEA Centre d`Etudes de Saclay, 91 - Gif-sur-Yvette (France). Dept. de Mecanique et de Technologie
  2. CEA Centre d`Etudes de Saclay, 91 - Gif-sur-Yvette (France). Dept. des Applications et de la Metrologie des Rayonnements Ionisants
Publication Date:
Dec 31, 1995
Product Type:
Conference
Report Number:
CEA-CONF-12324; CONF-9508260-
Reference Number:
SCA: 440102; 990200; PA: AIX-28:031300; EDB-97:056968; NTS-97:012126; SN: 97001765585
Resource Relation:
Conference: International conference on engineering of neural networks, Helsinki (Finland), 21-23 Aug 1995; Other Information: PBD: 1995
Subject:
44 INSTRUMENTATION, INCLUDING NUCLEAR AND PARTICLE DETECTORS; 99 MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS; NEURAL NETWORKS; ISOTOPE SEPARATION; ARTIFICIAL INTELLIGENCE; AUTOMATION; COMPUTER ARCHITECTURE; COMPUTERIZED SIMULATION; DOSIMETRY; DUAL-ISOTOPE SUBTRACTION TECHNIQUE; GAMMA SPECTROSCOPY; ISOTOPE RATIO; MEASURING METHODS; QUANTITATIVE CHEMICAL ANALYSIS; RADIATION DETECTION; RESOLUTION; URANIUM 235; URANIUM 238; X-RAY SPECTROSCOPY
OSTI ID:
456105
Research Organizations:
CEA Centre d`Etudes de Saclay, 91 - Gif-sur-Yvette (France). Dept. de Mecanique et de Technologie
Country of Origin:
France
Language:
English
Other Identifying Numbers:
Other: ON: DE97620783; TRN: FR9601558031300
Availability:
INIS; OSTI as DE97620783
Submitting Site:
FRN
Size:
6 p.
Announcement Date:

Citation Formats

Vigneron, V, Martinez, J M, Morel, J, and Lepy, M C. Uranium enrichment measurement task with a connectionist architecture. France: N. p., 1995. Web.
Vigneron, V, Martinez, J M, Morel, J, & Lepy, M C. Uranium enrichment measurement task with a connectionist architecture. France.
Vigneron, V, Martinez, J M, Morel, J, and Lepy, M C. 1995. "Uranium enrichment measurement task with a connectionist architecture." France.
@misc{etde_456105,
title = {Uranium enrichment measurement task with a connectionist architecture}
author = {Vigneron, V, Martinez, J M, Morel, J, and Lepy, M C}
abstractNote = {Layered Neural Networks, which are a class of models based on neural computation, are applied to the measurement of uranium enrichment, i.e. the isotope ration {sup 235} U/({sup 235} U+{sup 236} U+{sup 238} U). The usual methods consider a limited number of {gamma}-ray and X-ray peaks, and requires previously calibrated instrumentation for each sample. But, in practice, the source-detector ensemble geometry conditions are critically different, thus a means of improving the above conventional methods is to reduce the region of interest: this is possible by focusing on the region called K{sub {alpha}}X where the three elementary components are present. The measurement of these components in mixtures leads to the desired ratio. Real data are used to study its performance. Training is done with a Maximum Likelihood method. We show the encoding of data by Neural Networks is a promising method to measure uranium {sup 235} U and {sup 238} U quantities in infinitely thick samples. (authors). 7 refs., 2 figs., 1 tab.}
place = {France}
year = {1995}
month = {Dec}
}