TwinGuide: Digital Twins for Autonomous Control of Fluidized Beds

In order to minimize unwanted process status and defect production, process monitoring and control are critical in industrial particulate production. In this trilateral project involving TUHH SPE, Fraunhofer IFF and Pergande Group, a framework for intelligent digital twins is developed and tested for a fluidized bed spray granulation process, with the goal of improving process engineering efficiency by predicting future process behavior and ensuring reliable process control. Based on dynamic models for flowsheet simulations implemented in Dyssol, the corresponding knowledge module is established, which interacts with the communication interface for data exchange and set point adjustments. This involves the usage of supervised machine learning for the development of soft sensors as well as reinforcement learning for autonomous control.

Robert Kräuter

Control Engineering and Machine Learning for Digital Twins of Fluidized Beds