Probabilistic PCR based near-infrared modeling with temperature compensation

Considering that temperature makes a difference to near-infrared spectrum, a probabilistic principle component regression (PPCR) based temperature compensation modeling strategy is investigated under the framework of maximum likelihood estimation. First, a PPCR model is established to extract the dynamic information of the spectra at designated experimental temperature. Then, by decomposing the temperature-induced spectral variation into the shift in horizontal direction and the drift in vertical direction, the quantitative expression between spectral variation and temperature change is derived. Based on the decomposition, the estimation of new latent variables that vary with temperature is derived according to the spectral data set collected at certain temperatures. Finally, for performance evaluation, applications of the theoretical results to bisphenol-A and gasoline-ethanol mixture illustrate the effectiveness and advantages of the developed techniques.