DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: System for identifying known materials within a mixture of unknowns

Abstract

One or both of two methods and systems are used to determine concentration of a known material in an unknown mixture on the basis of the measured interaction of electromagnetic waves upon the mixture. One technique is to utilize a multivariate analysis patch technique to develop a library of optimized patches of spectral signatures of known materials containing only those pixels most descriptive of the known materials by an evolutionary algorithm. Identity and concentration of the known materials within the unknown mixture is then determined by minimizing the residuals between the measurements from the library of optimized patches and the measurements from the same pixels from the unknown mixture. Another technique is to train a neural network by the genetic algorithm to determine the identity and concentration of known materials in the unknown mixture. The two techniques may be combined into an expert system providing cross checks for accuracy.

Inventors:
 [1]
  1. Albuquerque, NM
Issue Date:
Research Org.:
Sandia National Laboratories (SNL), Albuquerque, NM, and Livermore, CA (United States)
OSTI Identifier:
872401
Patent Number(s):
5926773
Assignee:
Sandia Corporation (Albuquerque, NM)
Patent Classifications (CPCs):
G - PHYSICS G01 - MEASURING G01J - MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRA-RED, VISIBLE OR ULTRA-VIOLET LIGHT
G - PHYSICS G01 - MEASURING G01N - INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
DOE Contract Number:  
AC04-94AL85000
Resource Type:
Patent
Country of Publication:
United States
Language:
English
Subject:
identifying; materials; mixture; unknowns; methods; systems; determine; concentration; material; basis; measured; interaction; electromagnetic; waves; technique; utilize; multivariate; analysis; patch; library; optimized; patches; spectral; signatures; containing; pixels; descriptive; evolutionary; algorithm; identity; determined; minimizing; residuals; measurements; train; neural; network; genetic; techniques; combined; expert; providing; checks; accuracy; magnetic wave; materials containing; neural network; electromagnetic waves; electromagnetic wave; measured interaction; genetic algorithm; neural net; spectral signature; determine concentration; /702/250/356/422/

Citation Formats

Wagner, John S. System for identifying known materials within a mixture of unknowns. United States: N. p., 1999. Web.
Wagner, John S. System for identifying known materials within a mixture of unknowns. United States.
Wagner, John S. Fri . "System for identifying known materials within a mixture of unknowns". United States. https://www.osti.gov/servlets/purl/872401.
@article{osti_872401,
title = {System for identifying known materials within a mixture of unknowns},
author = {Wagner, John S},
abstractNote = {One or both of two methods and systems are used to determine concentration of a known material in an unknown mixture on the basis of the measured interaction of electromagnetic waves upon the mixture. One technique is to utilize a multivariate analysis patch technique to develop a library of optimized patches of spectral signatures of known materials containing only those pixels most descriptive of the known materials by an evolutionary algorithm. Identity and concentration of the known materials within the unknown mixture is then determined by minimizing the residuals between the measurements from the library of optimized patches and the measurements from the same pixels from the unknown mixture. Another technique is to train a neural network by the genetic algorithm to determine the identity and concentration of known materials in the unknown mixture. The two techniques may be combined into an expert system providing cross checks for accuracy.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Fri Jan 01 00:00:00 EST 1999},
month = {Fri Jan 01 00:00:00 EST 1999}
}