Combine data-driven and knowledge-driven AI for the chemical industry.
  • ML models are pure data-driven
  • Black-box models are hardto understand
  • The ML needs to be able to deal with conflicting feedback
  • Project in progress
  • Imec (IDLab)
  • P&G
  • allnex
  • Catilisti

Today, finetuning and optimizing chemical processes is mainly done by experienced process engineers.
Process engineers interpret a high volume of data from sensors to steer chemical processes. However, before acquiring the necessary experience, they need to supervise actual production environments for years. 


In the project, industrial and research partners work together to design explainable, hybrid AI algorithms that can assist with this optimization. This allows process engineers to gain experience faster and to make better use of the available expertise. It also enables a more efficient scaling-up of chemical production processes.


AI assistant
Explainable hybrid AI algorithms incorporate expert knowledge into the machine learning. As a result, datastreams will automatically be translated into contextualized insights, outcome predictions, and suggested control actions.
Two-fold benefit
The insights, predictions, and suggested actions will be brought to both operators and experienced process engineers through contextualized and dynamic visualization in responsive dashboards to aid in their daily optimization processes.
Workforce optimization
Improvements are made in the standardization of processes, the amount of expert attention needed for low-level routine monitoring, and the speed and quality of the process outcome.
Download our whitepaper on creating business value with smart data
Short description of whitepaper CTA