Automating Data Pre-processing for Online and Dynamic Processes in the Chemical Industry

This source preferred by Manuel Salvador

Authors: Salvador, M.M.

In process industry, chemical processes are controlled and monitored by using readings from multiple physical sensors across the plants. Such physical sensors are also supplemented by soft sensors, i.e. adaptive predictive models, which are often used for computing hard-to-measure variables of the process. For soft sensors to work well they need to be provided with relevant data. For that, a sequence of preprocessing steps are carried out over the raw data such us replacement of missing values or noise removal. The decision of how to approach each step in this process has often been made manually by experts. However, experts cannot be aware of all methods, nor is it feasible to try all of them. Different approaches for automating, or at least advising, the stages of this process have been proposed. This poster will outline the challenges, current approaches and future directions in this topic.

The data on this page was last updated at 05:09 on February 20, 2020.