Premium
Nonlinear Calibration for Near‐Infrared Spectroscopy
Author(s) -
Dadhe K.
Publication year - 2004
Publication title -
chemical engineering and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.403
H-Index - 81
eISSN - 1521-4125
pISSN - 0930-7516
DOI - 10.1002/ceat.200403212
Subject(s) - calibration , nonlinear system , distillation , generalization , artificial neural network , component (thermodynamics) , fraction (chemistry) , biological system , mole fraction , support vector machine , infrared spectroscopy , chemistry , analytical chemistry (journal) , computer science , mathematics , process engineering , artificial intelligence , chromatography , engineering , thermodynamics , statistics , organic chemistry , physics , mathematical analysis , quantum mechanics , biology
Nonlinear models such as neural networks and support vector machines are used with particular consideration of their generalization potential. To assess the model predictions without knowledge of the true output, prediction intervals are calculated by bootstrap procedures. As an example, the estimation of methyl acetate mole fraction in a four‐component mixture is described. The experimental values are taken from a reactive distillation pilot plant.