Condition Monitoring with KI/ML

Condition Monitoring with KI/ML

VIPFLUID
Predictive maintenance for pump systems based on federated learning and synthesis of multiple sensor data-Subproject vibration diagnostics, feature extraction, fault diagnostics

Climate change and also dwindling resources require careful and sustainable handling in the wastewater industry too. Innovative solutions based on digital technologies offer the opportunity to save resources and at the same time contribute to strengthening the resilience of critical infrastructures.
VIPFLUID aims to record the status data of wastewater pumps using suitable sensor technology and utilise it for machine learning. Adaptive sensor technology and an intelligent sensor hub will initially record the pump data and pre-process it locally at the edge in order to send a compressed data stream to local computing resources (fog). Synthetic data through machine learning (ML) then enables local and resource-saving, adaptive models for forecasting.
The software solutions developed are based on generative neural networks and federated learning and are intended to establish the use of machine learning in the field of predictive maintenance in an economical and ecological manner. This enables proactive maintenance and minimises reactive action. This avoids expensive and system-critical failures and significantly improves process reliability. The reliable prediction results generated enable a significant reduction in maintenance resources is made possible. This technology enables a significant reduction in CO2 emissions and thus supports the achievement of climate and environmental protection targets.

Partnership:

  • • Technische Universität Dresden
  • • Herborner Pumpentechnik GmbH & Co KG
  • • Gesellschaft zur Förderung von Medizin-, Bio- und Umwelttechnologien (GMBU e. V.)
  • • Ingenieurbetrieb für Automatisierungstechnik Rudolphi & Rau GmbH
  • • Pumpen-Service-Deutschland GmbH
  • • SPEKTRA Schwingungstechnik und Akustik GmbH Dresden

Further Informations: www.vipfluid.de


  • Projektlaufzeit: 01.05.2023 bis 30.04.2026
  • Teilprojekt: GMBU Halle
  • Ansprechpartner: Dr. Stefan Gai
  • Tel: 0345777 96 40
  • E-Mail: stefangai@gmbu.de