Tolerance of near Infrared Calibrations to Temperature Variations; A Practical Evaluation

Abstract

Process samples of esters have been analysed by transmittance near infrared (NIR) at temperatures between 60 and 70°C (±0.2). Apart from density changes, these small temperature variations affect molecular associations by H-bonding. Partial Least Square (PLS) models based on the first OH overtone (1350–1500nm) have been made for hydroxyl value determination, including implicitly the temperature variable. The sensitivity of these NIR calibrations to temperature has been evaluated by an analysis of variance and the “Taguchi principle”, using both average model performance and model variance. An accurate and precise control of the sample temperature prior to scanning leads to the lowest prediction error. When temperature fluctuations can not be avoided, introduction of temperature variance in the calibration set can improve the model robustness; this strategy is only beneficial if temperature range, temperature distribution and number of PLS factors have been carefully optimised.