Enhanced modeling of distillation columns using integrated multiscale latent variable regression

Operating distillation columns under control requires inferring the compositions of the distillate and bottom streams (which are challenging to measure) from other more easily measured variables, such as temperatures at different trays of the column. Models that can be used in this regard are called inferential models. Commonly used inferential models include latent variable regression (LVR) techniques, such as principal component regression (PCR), partial least square (PLS), and regularized canonical correlation analysis (RCCA). Unfortunately, measured practical data are usually contaminated with errors, which degrade the prediction accuracy of inferential models. Therefore, noisy measurements need to be filtered to enhance the prediction ability of these models. Wavelet-based multiscale filtering has been shown to be a powerful denoising tool. In this work, the advantages of multiscale filtering are utilized to enhance the prediction accuracy of LVR models by developing an integrated multiscale LVR (IMSLVR) modeling algorithm that integrates modeling and filtering. The idea behind the IMSLVR modeling algorithm is to filter the process data at different decomposition levels, model the filtered data from each level, and then select the LVR model that optimizes a model selection criterion. The performance of the developed IMSLVR algorithm is illustrated using two examples, one using synthetic data and the other using simulated distillation column data. Both examples clearly demonstrate the effectiveness of the IMSLVR algorithm.