DigiFloat

The DigiFloat project aims to provide generic impulses for the optimization of complex reprocessing processes through digitalization. Flotation, a physical-chemical separation process for fine-grained solids, which is important in ore processing, wastewater treatment and recycling, among others, serves as an example.

An important point is the detailed and complete acquisition of process data. In the project, the possibilities of substance-related sensor technology are to be expanded to the extent that a system for the online acquisition of chemical compositions in complex structures (e.g. foam) in the dynamic process under industrial conditions is to be established by spectroscopic systems. In addition, miniaturization of sensors in contact with the media will improve the reliability and relevance of the process data, as invasive measurement techniques will have less impact on the process.

The next step in the data flow is acquisition, validation and evaluation. This is where the project ties in by establishing a data lake that processes the raw data from the new sensors. This data is enriched together with offline results and information on energy and raw material use, analyzed and visualized in such a way that multivariate relationships of the complex flotation process become transparent. The result is a system that can alert users to potential action needs with AI-assisted data fusion. The system will also exhibit the function of predictive process control. For this purpose, KPIs will be formed from data and information, which can be used to dynamically evaluate and control the flotation process. The main objective is thus to optimize complex processes in terms of yield and efficiency by predicting the process results. For this purpose, a concept study will be available at the end of the project, which will summarize the findings of the individual objectives and describe the scale-up for industrial plants in detail.