Small moving window calibration models for soft sensing processes with limited history

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 onestep-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.

Machine Learning for Process Monitoring and Control of Hot-Melt Extrusion: Current State of the Art and Future Directions

“…Another method that can be used to update the calibration model for new data is to use a ‘moving window’ modelling approach. Adaptive methods require extensive training data to calibrate a model, while the moving window modelling approach is fast, can be used with small historical data, and is easy to implement [ 126 ].…”

A digital twin–driven method for online quality control in process industry

“…The former is commonly based on the first principle model but hard to be extensively used on account of its complicated processes and unquantifiable parametric relationships. The most popular modeling techniques for data-driven soft sensors include principal component regression (PCR) [12,13], partial least squares (PLS) [14,15], artificial neural networks (ANN) [16,17] and support vector machines (SVM) [18,19]. Wang et al [20] integrated random forest with Bayesian optimization to predict and maintain product quality and validated model superiorities through semiconductor production line data.…”

Soft metrology based on machine learning: a review

“…The main idea is to update the model over time, discarding older data points and including new ones. Many of the previously mentioned methods, such as PLS, ANN and GPR have been used in combination with a time window scheme [63,94,123], where a method based on PLS that uses a moving window to recursively update the model were developed.…”