Premium
A Bayesian online inferential model for evaluation of analyzer performance
Author(s) -
Willis A. J.
Publication year - 2005
Publication title -
journal of chemometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.47
H-Index - 92
eISSN - 1099-128X
pISSN - 0886-9383
DOI - 10.1002/cem.913
Subject(s) - bayesian probability , computer science , weighting , spectrum analyzer , algorithm , data mining , artificial intelligence , medicine , telecommunications , radiology
An iterative Bayesian approach is developed for the inversion of flow instrumentation condition‐monitoring problems. For the case of Gaussian random variables the solution reduces to an iterative weighted least squares approach amenable to online implementation, with a weighting derived from the Bayesian prior. The algorithm is illustrated with reference to a Sulfreen unit in a refinery, where concentrations of H 2 S and SO 2 are measured by a number of input analyzers in parallel, prior to their combination and reaction. This paper discusses approaches to evaluating the performance of each instrument separately by monitoring the inferred bias using output data from the process. Copyright © 2005 John Wiley & Sons, Ltd.