TVB: Machine Learning Components for Automated Sewer systems

In order to minimize the entry of pollutants into the environment, sewage systems must be adapted to the consequences of climate change. With the planned measures, the environment and water can be protected and the goals of the EU Water Framework Directive can be achieved.

Discharge of untreated combined sewer overflow (CSO) wastewater into the environment can cause hydraulic stress, oxygen depletion, and increases in contaminant concentrations in receiving waters. The joint project aims to develop an edge-based, automated wastewater control system through metrological data acquisition and analysis, which makes it possible to reduce environmentally harmful mixed water discharges during rain / heavy rain as much as possible. However, the project does not only pursue ecological goals. Several economic policy goals are achieved at the same time, e.g. Job effects, competition and value creation.

The aim of the sub-project (BHT) is the conception, implementation and maintenance of the AI ​​components in close cooperation with the other consortium partners.

 

Partners:
  • Universität Duisburg-Essen
  • Verein Deutscher Ingenieure
  • KROHNE
  • Okeanos
  • HST System-Technik
  • RWTH Aachen
  • Berliner Hochschule für Technik (BHT)

 

Funded by:

BMWK: Edge Datenwirtschaft, Förderrahmen "Entwicklung digitaler Technologien"

 

Project duration:

1.10.2022 - 30.09.2025

 

Contact:

felix.biessmann (@) bht-berlin.de