×

Composition analysis

  • US 5,946,640 A
  • Filed: 12/08/1997
  • Issued: 08/31/1999
  • Est. Priority Date: 06/08/1995
  • Status: Expired due to Fees
First Claim
Patent Images

1. A method of analysing a sample, comprising the steps of training a neural network to correct for measurement drift of a given analytical instrument, said training being carried out using a first set of data obtained by said instrument from samples of known compositions at an initial instant of time and a second set of data obtained by said instrument from samples of the same known compositions at a subsequent instant of time, then using said neural network to transform data, obtained by said instrument from a sample of unknown composition at said subsequent instant of time, to an estimate of the data which would have been obtained by said instrument from said sample of unknown composition at said initial instant of time, and analysing the transformed data to analyse said sample of unknown composition.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×