Optimizing meta-parameters in continuous piecewise direct standardization

When in-line or on-lint spectroscopy is performed on a process, different t ypes of variations are present in the measured spectrum. The variation due to the chemistry of tile process is the wanted variation, which should be u sed for monitoring the process. Also unwanted variation is present in the m easured spectrum, Orle example is variation due to changes in the temperatu re of the sample, This unwanted variation will cause deterioration of the p erformance of the spectroscopic analyzer, In this paper the properties of c ontinuous piecewise direct standardization (CPDS) for temperature correctio ns in near-infrared (NIR) spectra are discussed, A procedure to obtain sens ible settings of the meta-parameters in the CPDS algorithm has been develop ed, Initial values of the meta-parameters can be found for each data set by looking at spectra as a function of temperature. Particularly, difference spectra are shown to be useful in order to determine the degree of linearit y of the spectral disturbances caused hg the temperature change;. A cross-v alidation procedure around these initial settings is proposed to establish the optimum meta-parameters. This procedure nias successfully applied to tw o NW data sets. For each data set, it was found that CPDS corrected for tem perature disturbances in art independent test data set and maintained the p rediction errors on the same low level as for a calibration model built at tile calibration temperature.