Jm. Andrade et al., A REVIEW OF THE MAIN FACTORS INFLUENCING THE FT-IR-PLS ABILITIES EXEMPLIFIED WITH PETROCHEMICAL QUALIMETRIC APPLICATIONS, Talanta, 44(12), 1997, pp. 2167-2184
Quality control usually involves monitoring several variables directly
related with industrial necessities using univariate tests. One power
ful alternative is to link multivariate analytical techniques and mult
ivariate chemometrics. In this way, Fourier Transform Infrared spectro
scopy and Partial Least Squares regression are used to discuss and rev
iew several advantages and drawbacks encountered in using such combina
tion in industrial facilities. Typical drawbacks are selection of data
pretreatment, errors in reference methods, selection of calibration a
nd Validation sets and model-aging. This review is exemplified with pe
trochemical applications although other fields are also considered (ma
inly when dealing with data pretreatment). (C) 1997 Elsevier Science B
.V.