Dynamic system multivariate calibration based on multirate sampling data

The statistical principal component regression (PCR) and chemometric partia l least squares regression (PLSR) algorithms based on latent variables (LV) modeling are effective tools for handling ill-conditioned regression data. In many process related cases the data form time series, and it may then b e possible to improve the prediction/estimation results by utilizing the au tocorrelation in the observations. This can be done by use of estimators fo und from experimental data by use of a combination of statistical/chemometr ic and system identification methods. In important industrial cases, the re sponse variables are product qualities which also in the experimental data are sampled at a low and possibly irregular rate, while the regressor varia bles are sampled at a higher rate. After a discussion of the options availa ble, the paper shows how the autocorrelation of the regressor variables in such multirate sampling cases may be utilized by identification of latent v ariables based output error (LV + OE) estimators. An example using acoustic power spectrum regressor data is finally presented.