Synchronizing process variables in time for industrial process monitoring and control

A Regularized Mixture of Linear Experts for Quality Prediction in Multimode and Multiphase Industrial Processes

“…By doing so, it allows the online inference of the quality variables, allowing operators to get earlier information about the quality of the process and take corrective actions on time. The common steps to deploy a soft sensor are: data cleaning/synchronization [4], feature selection [5], model learning/validation [2], and model maintenance [6]. During the learning phase, it is beneficial to take, as much as possible, the process properties into consideration.…”

Data-Driven Process Monitoring and Fault Diagnosis: A Comprehensive Survey

“…On the broad theme of exploration, characterization and treatment of process data, it is also worth highlighting the recent works by: Li et al [583], which proposed dataset division based on the nature of the correlation (linear or non-linear) detected between variables and the application of a hierarchical strategy in these datasets to monitor linear and non-linear characteristics at different levels; Thomas et al [584], who presented an integrated approach to data clustering and feature extraction, as an aid to increase knowledge about process data; Parente et al [585], who proposed the application of the Monte Carlo technique to increase the amount of data used in training a monitoring model for a paper production process; Offermans et al [586], which compared different methods for dynamically synchronizing process variables; and Rhyu et al [587], which proposed an integrated methodology for automated outlier detection and missing data estimation.…”

Process Expert Knowledge is Essential in Creating Value from Data-Driven Industrial Soft Sensors

“…Firstly, the process variable measurements were synchronized to the product quality measurements. This step is necessary because the process variables are sampled at higher-frequency than that the product quality is, and are not all sampled at the same (higher) frequency (Offermans et al, 2020). The synchronization was performed by using median-filtering with a 3-hours wide window placed before the quality measurements.…”