Semi-supervised Learning for Data-driven Soft-sensing of Biological and Chemical Processes
This addresses the challenge of process control in the (bio-)chemical industry by potentially reducing measurement costs, though it appears incremental as it compares existing methods in specific applications.
The paper tackled the problem of estimating rarely measured concentrations in (bio-)chemical processes, which are expensive to measure, by comparing semi-supervised regression against standard regression in two case studies, showing that semi-supervised methods can improve accuracy in scenarios with limited labeled data.
Continuously operated (bio-)chemical processes increasingly suffer from external disturbances, such as feed fluctuations or changes in market conditions. Product quality often hinges on control of rarely measured concentrations, which are expensive to measure. Semi-supervised regression is a possible building block and method from machine learning to construct soft-sensors for such infrequently measured states. Using two case studies, i.e., the Williams-Otto process and a bioethanol production process, semi-supervised regression is compared against standard regression to evaluate its merits and its possible scope of application for process control in the (bio-)chemical industry.