Small Moving Window Calibration Models for Soft Sensing Processes with Limited History

TL;DR

This paper compares five soft sensor calibration methods, including a novel RF-PLS ensemble, for rapid online application with limited historical data, demonstrating RF-PLS's superior accuracy and stability on most datasets.

Contribution

Introduces a new RF-PLS ensemble method and evaluates its performance against existing soft sensor calibration techniques with small sample sizes.

Findings

RF-PLS achieved the lowest prediction errors on most datasets.

Small window sizes generally led to lower errors across methods.

RF-PLS showed greater stability at larger time delays.

Abstract

Five simple soft sensor methodologies with two update conditions were compared on two experimentally-obtained datasets and one simulated dataset. The soft sensors investigated were moving window partial least squares regression (and a recursive variant), moving window random forest regression, the mean moving window of $y$, and a novel random forest partial least squares regression ensemble (RF-PLS), all of which can be used with small sample sizes so that they can be rapidly placed online. It was found that, on two of the datasets studied, small window sizes led to the lowest prediction errors for all of the moving window methods studied. On the majority of datasets studied, the RF-PLS calibration method offered the lowest one-step-ahead prediction errors compared to those of the other methods, and it demonstrated greater predictive stability at larger time delays than moving window PLS alone. It was found that both the random forest and RF-PLS methods most adequately modeled the datasets that did not feature purely monotonic increases in property values, but that both methods performed more poorly than moving window PLS models on one dataset with purely monotonic property values. Other data dependent findings are presented and discussed.